Disclosure of Invention
The invention aims to solve the technical problem of providing an ISP self-adaptive adjustment control method and device based on face images, which can dynamically adjust the ISP according to actual conditions and realize real-time and accurate acquisition of the face images.
In order to solve the technical problem, the first aspect of the present invention discloses an ISP adaptive adjustment control method based on a face image, the method comprising:
Acquiring a face image acquired by image acquisition equipment, and inputting the face image into a predetermined face image quality evaluation model for analysis;
Acquiring an analysis result of the face image quality evaluation model as an image analysis parameter of the face image, and judging whether an ISP corresponding to the image acquisition equipment needs to be adjusted according to the image analysis parameter;
And when judging that the ISP needs to be adjusted, adjusting the ISP according to the image analysis parameters until the parameters of the ISP meet preset conditions, and re-triggering and executing the operation of acquiring the face image acquired by the image acquisition equipment.
As an optional implementation manner, in the first aspect of the present invention, the image analysis parameter includes at least one of an exposure parameter of the face image, a white balance parameter of the face image, and a focus parameter of the face image;
The determining whether the ISP corresponding to the image acquisition device needs to be adjusted according to the image analysis parameters includes:
when the image analysis parameters are exposure parameters of the face image, intercepting the face image based on a calibration result corresponding to the determined face key points to obtain a target face area, wherein the area of the target face area is smaller than that of the face image;
Acquiring a first brightness value corresponding to the target face region, judging whether the first brightness value is larger than or equal to a preset brightness value threshold, and determining that ISP corresponding to the image acquisition equipment needs to be adjusted when the first brightness value is larger than or equal to the preset brightness value threshold, or
When the image analysis parameters are white balance parameters of the face image, determining the average value of each channel in the RGB three channels of the target face area, judging whether the proportional distribution of all the channels is matched with the predetermined proportional distribution according to all the average values, and determining that ISP corresponding to the image acquisition equipment needs to be adjusted when the judging result is negative, or
When the image analysis parameters are focusing parameters of the face image, acquiring a target position of the target face region on the image acquisition equipment, judging whether the target position is in a predetermined position range, and when the judgment result is negative, determining that the ISP corresponding to the image acquisition equipment needs to be adjusted.
As an alternative embodiment, in the first aspect of the present invention, the method further includes:
When the first brightness value is not larger than or equal to the preset brightness value threshold value, expanding the effective area of the target face area according to a preset expansion mode to obtain an expanded target face area, wherein the preset expansion mode is a mode set based on the central position of the target face area;
Determining a second brightness value of a background area corresponding to the enlarged target face area, and calculating the inverse luminosity of the face image based on the first brightness value and the second brightness value;
judging whether the backlight degree is smaller than or equal to a preset backlight degree threshold value, and determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when judging that the backlight degree is smaller than or equal to the preset backlight degree threshold value.
As an optional implementation manner, in the first aspect of the present invention, before the acquiring the face image acquired by the image acquisition device, the method further includes:
judging whether the ISP needs to be adjusted according to the current state of the ISP, and triggering and executing the operation of acquiring the face image acquired by the image acquisition equipment when judging that the ISP needs to be adjusted;
wherein the determining whether the ISP needs to be adjusted according to the current state of the ISP includes:
reading the current displayed target moment of the image processing system corresponding to the ISP, and obtaining the finishing moment corresponding to the ISP adjusted last time;
calculating the interval duration between the target time and the finishing time, judging whether the interval duration is smaller than or equal to a predetermined interval duration threshold, and determining that the ISP needs to be adjusted when the interval duration is smaller than or equal to the interval duration threshold.
As an optional implementation manner, in the first aspect of the present invention, after determining that the interval duration is less than or equal to the interval duration threshold and before determining that the ISP needs to be adjusted, the method further includes:
Acquiring the total adjustment times of the ISP in a first preset time length, judging whether the total adjustment times are smaller than a preset adjustment times threshold, and triggering and executing the operation for determining that the ISP needs to be adjusted when the total adjustment times are smaller than the preset adjustment times threshold, wherein the cut-off time of the first preset time length is the time for adjusting the ISP last time.
As an optional implementation manner, in the first aspect of the present invention, after the acquiring a face image acquired by the image acquiring device and before the inputting the face image into a predetermined face image quality assessment model for analysis, the method further includes:
Determining image parameters corresponding to the face image, wherein the image parameters comprise at least one of the area of the face image, the position of the face image appearing in the image acquisition equipment and the face information of the face image, and the face information of the face image comprises the position of a left virtual pupil, the position of a right virtual pupil, the position of a left mouth angle of a virtual mouth, the position of a right mouth angle of the virtual mouth and the position of a virtual nose tip of the face image;
judging whether the face image meets the preset ISP adjustment conditions according to the image parameters, and triggering and executing the operation of inputting the face image into a preset face image quality evaluation model for analysis when judging that the face image meets the ISP adjustment conditions.
As an optional implementation manner, in a first aspect of the present invention, the adjusting the ISP according to the image analysis parameter until after the current parameter of the ISP meets a preset condition and before the retrigging execution of the operation of acquiring the face image acquired by the image acquisition device, the method further includes:
judging whether the real-time display time of the image processing system corresponding to the ISP reaches the cut-off time of a second preset time length, and when the real-time display time reaches the cut-off time of the second preset time length, re-triggering and executing the operation of acquiring the face image acquired by the image acquisition equipment, wherein the starting time of the second preset time length is the time for determining the ISP to adjust.
The invention discloses an ISP self-adaptive adjustment control device based on a face image, which comprises an acquisition module, an analysis module, a first judgment module and an adjustment module, wherein:
the acquisition module is used for acquiring the face image acquired by the image acquisition equipment;
The analysis module is used for inputting the face image into a predetermined face image quality evaluation model for analysis;
The acquisition module is further used for acquiring an analysis result of the face image quality evaluation model as an image analysis parameter of the face image;
The first judging module is used for judging whether the ISP corresponding to the image acquisition equipment needs to be adjusted according to the image analysis parameters;
The adjusting module is configured to adjust the ISP according to the image analysis parameter when the first judging module judges that the ISP needs to be adjusted, until the parameter of the ISP meets a preset condition, and trigger the acquiring module to re-execute the operation of acquiring the face image acquired by the image acquiring device.
As an optional implementation manner, in the second aspect of the present invention, the image analysis parameter includes at least one of an exposure parameter of the face image, a white balance parameter of the face image, and a focus parameter of the face image;
The first judging module comprises a first judging sub-module or a second judging sub-module or a third judging sub-module, wherein the first judging sub-module comprises an intercepting unit, an acquiring unit, a judging unit and a determining unit, and the first judging sub-module comprises a first judging sub-module, a second judging sub-module and a third judging sub-module, wherein:
the intercepting unit is used for intercepting the face image based on a calibration result corresponding to the determined face key point to obtain a target face area when the image analysis parameter is an exposure parameter of the face image, wherein the area of the target face area is smaller than that of the face image;
the acquisition unit is used for acquiring a first brightness value corresponding to the target face area;
The judging unit is used for judging whether the first brightness value is larger than or equal to a preset brightness value threshold value;
The determining unit is configured to determine that the ISP corresponding to the image capturing device needs to be adjusted when the determining unit determines that the first luminance value is greater than or equal to the preset luminance value threshold value, or
The second judging sub-module is used for determining the average value of each channel in the RGB three channels of the target face area when the image analysis parameter is the white balance parameter of the face image, judging whether the proportional distribution of all the channels is matched with the predetermined proportional distribution according to all the average values, and determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when the judging result is negative, or
The third judging sub-module is configured to obtain, when the image analysis parameter is a focusing parameter of the face image, a target position of the target face area in the image acquisition device, judge whether the target position is in a predetermined position range, and determine that an ISP corresponding to the image acquisition device needs to be adjusted when the judgment result is negative.
As an optional implementation manner, in the second aspect of the present invention, the obtaining unit is further configured to, when the determining unit determines that the first luminance value is not greater than the preset luminance value threshold, expand the effective area of the target face area according to a preset expansion manner, to obtain an expanded target face area, where the preset expansion manner is a manner set based on a central position of the target face area;
the determining unit is further configured to determine a second luminance value of a background area corresponding to the enlarged target face area;
the acquisition unit is further used for calculating the inverse luminosity of the face image based on the first brightness value and the second brightness value;
The judging unit is used for judging whether the backlight degree is smaller than or equal to a preset backlight degree threshold value, and triggering the determining unit to execute the operation of determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when judging that the backlight degree is smaller than or equal to the preset backlight degree threshold value.
As an optional implementation manner, in the second aspect of the present invention, the apparatus further includes a second judging module, where:
The second judging module is used for judging whether the ISP needs to be regulated according to the current state of the ISP before the acquiring module acquires the face image acquired by the image acquisition equipment;
The second judging module comprises a reading sub-module, an obtaining sub-module, a calculating sub-module and a fourth judging sub-module, wherein:
the reading submodule is used for reading the target moment currently displayed by the image processing system corresponding to the ISP;
the obtaining submodule is used for obtaining the finishing moment corresponding to the ISP adjusted last time;
the calculating submodule is used for calculating the interval duration between the target time and the finishing time;
the fourth judging submodule is used for judging whether the interval duration is smaller than or equal to a predetermined interval duration threshold value;
the obtaining submodule is further configured to determine that the ISP needs to be adjusted when the fourth judging submodule judges that the interval duration is less than or equal to the interval duration threshold.
As an optional implementation manner, in the second aspect of the present invention, the obtaining submodule is further configured to obtain, after the fourth judging submodule judges that the interval duration is less than or equal to the interval duration threshold and before it is determined that the ISP needs to be adjusted, a total adjustment number of times of the ISP within a first preset duration, where a deadline time of the first preset duration is a time of last adjustment of the ISP;
the fourth judging sub-module is further configured to judge whether the total adjustment frequency is smaller than a preset adjustment frequency threshold, and trigger the obtaining sub-module to execute the operation of determining that the ISP needs to be adjusted when the total adjustment frequency is determined to be smaller than the preset adjustment frequency threshold.
In a second aspect of the present invention, as an optional implementation manner, the apparatus further includes a determining module and a third judging module, where:
The determining module is used for determining image parameters corresponding to the face image after the face image acquired by the image acquisition device is acquired by the acquisition module and before the face image is input into a predetermined face image quality evaluation model by the analysis module for analysis, wherein the image parameters comprise at least one of the area of the face image, the position of the face image appearing on the image acquisition device and the face information of the face image, and the face information of the face image comprises the position of a left virtual pupil, the position of a right virtual pupil, the position of a left mouth corner of a virtual mouth, the position of a right mouth corner of the virtual mouth and the position of a virtual nose tip of the face image;
The third judging module is configured to judge whether the face image meets the predetermined adjustment condition of the ISP according to the image parameter, and trigger the analyzing module to perform the operation of inputting the face image into the predetermined face image quality evaluation model for analysis when judging that the face image meets the adjustment condition of the ISP.
As an optional implementation manner, in the second aspect of the present invention, the apparatus further includes a fourth judging module, where:
The fourth judging module is configured to judge whether a real-time display time of the image processing system corresponding to the ISP reaches a second preset duration of time when the real-time display time is judged to reach the second preset duration of time, and trigger the acquiring module to re-trigger and execute the operation of acquiring the face image acquired by the image acquisition device when the real-time display time is judged to reach the second preset duration of time, after the adjusting module adjusts the ISP according to the image analysis parameters until the current parameters of the ISP meet the preset conditions and before triggering the acquiring module to re-trigger and execute the operation of acquiring the face image acquired by the image acquisition device, where a start time of the second preset duration is a time for determining that the ISP needs to be adjusted.
The third aspect of the present invention discloses another ISP adaptive adjustment control device based on face images, the device comprising:
a memory storing executable program code;
a processor coupled to the memory;
The processor invokes the executable program code stored in the memory to execute the ISP adaptive adjustment control method based on the face image disclosed in the first aspect of the present invention.
A fourth aspect of the present invention discloses a computer storage medium storing computer instructions for executing the ISP adaptive adjustment control method based on a face image disclosed in the first aspect of the present invention when the computer instructions are called.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
The embodiment of the invention discloses an ISP self-adaptive adjustment control method and device based on a face image, wherein the method comprises the steps of acquiring the face image acquired by image acquisition equipment, and inputting the face image into a pre-determined face image quality evaluation model for analysis; and when judging that the ISP needs to be adjusted, adjusting the ISP according to the image analysis parameters until the parameters of the ISP meet preset conditions, and re-triggering and executing the operation of acquiring the face image acquired by the image acquisition equipment. Therefore, the embodiment of the invention combines the ISP of the image acquisition equipment with the face related application carrying the face image quality evaluation model, inputs the acquired face image into the face image quality evaluation model for analysis, can evaluate the parameter setting of the ISP according to the image analysis parameter, namely the imaging quality of the ISP, adjusts the ISP according to the image analysis parameter when the ISP needs to be adjusted, reacquires the face image to execute the adjustment operation of the same ISP, can realize the dynamic adjustment of the ISP, ensures that the ISP is always in a state matched with the face application, realizes the acquisition of the face image in real time and precision, is beneficial to ensuring the face application to acquire relatively stable face input data with high quality, thereby improving the effectiveness and the safety of face verification (such as access control face brushing authentication and the like), and fully utilizes the self-adjusting function of the ISP of the existing image acquisition equipment on the premise of not increasing the cost according to the self-adaptive adjustment of the face imaging result of the ISP, and obviously improves the imaging effect of the existing image equipment.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses an ISP self-adaptive adjustment control method and device based on a face image, which can combine the ISP of an image acquisition device with a face related application bearing a face image quality evaluation model, input the acquired face image into the face image quality evaluation model for analysis, evaluate the parameter setting of the ISP according to the image analysis parameters, namely the imaging quality of the ISP, adjust the ISP according to the image analysis parameters when the ISP needs to be adjusted, reacquire the face image and execute the adjustment operation of the same ISP, realize the dynamic adjustment of the ISP, ensure that the ISP is always in a state matched with the face application, realize the acquisition of the face image in real time and precision, be beneficial to ensuring that the face application acquires relatively stable high-quality face input data, thereby improving the effectiveness and the safety of face verification (such as access control face verification, etc.), and fully utilize the self-adjusting function of the prior image acquisition device on the premise of not increasing the cost of the ISP according to the self-adaptive adjustment of the face imaging result, and obviously improve the imaging effect of the prior image acquisition device. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of an ISP adaptive adjustment control method based on a face image according to an embodiment of the present invention. The method for controlling ISP adaptive adjustment based on face image described in fig. 1 is applicable to an image processing system, where the image processing system may be used to adjust ISP, and the image processing system is built in a terminal device capable of collecting face, where the terminal device includes a user terminal and/or an access control device. As shown in fig. 1, the ISP adaptive adjustment control method based on the face image may include the following operations:
101. And acquiring the face image acquired by the image acquisition equipment.
In the embodiment of the invention, the image acquisition device is provided with the ISP, and the face image can be a real-time image acquired by the image acquisition device or an image acquired at intervals of a preset time length (for example, 30 s).
In the embodiment of the present invention, after the face image is obtained, further, a preprocessing operation is performed on the face image, where the face image in step 102 is a preprocessed face image, where the preprocessing operation includes a filtering operation, an image segmentation operation, and the like. After the face image is obtained, preprocessing operation is performed on the face image, and the face image with high quality can be obtained, so that the analysis result of the face image is improved, and the judgment accuracy of the ISP is improved.
In an alternative embodiment, before performing step 101, the method for controlling ISP adaptive adjustment based on face images may further include the following operations:
Initializing an image processing system, specifically initializing an ISP adjustment information structure of the image processing system, wherein the ISP adjustment information structure is used for storing variables of the ISP in the adjustment process, such as face information of the detected latest frame (namely, the face appears at a specific position of a sensor included in an image acquisition device), specific adjustment time of the last ISP, adjustment times of the ISP in the current operation of the image processing system and the like;
after the initialization of the image processing system is completed, execution of step 101 may be triggered.
It can be seen that this alternative embodiment initializes the image processing system before acquiring the face image, so as to improve the information processing capability of the image processing system.
102. Inputting the face image into a predetermined face image quality evaluation model for analysis, and obtaining an analysis result of the face image quality evaluation model as an image analysis parameter of the face image.
In the embodiment of the present invention, the image analysis parameter (i.e. a representation of the imaging quality of the sensor of the image acquisition device) includes at least one of an exposure parameter of the face image, a white balance parameter of the face image, and a focusing parameter of the face image. Further, the image analysis parameters may include, but are not limited to, color correction matrix, sharpness, curve attribute, and saturation, so that the more the image analysis parameters include, the more advantageous the accuracy of determining whether the ISP needs to adjust.
103. Judging whether the ISP corresponding to the image acquisition equipment needs to be adjusted according to the image analysis parameters, triggering and executing step 103 when judging that the ISP needs to be adjusted, and ending the flow when judging that the ISP does not need to be adjusted.
104. And adjusting the ISP according to the image analysis parameters until the parameters of the ISP meet preset conditions, and re-triggering the step 101.
In an embodiment of the present invention, as an optional implementation manner, determining, according to an image analysis parameter, whether an ISP corresponding to an image acquisition device needs to be adjusted includes:
when the image analysis parameters are exposure parameters of the face image, the face image is intercepted based on a calibration result (for example, 106 face key points) corresponding to the determined face key points, and a target face area is obtained, wherein the area of the target face area is smaller than that of the face image;
And acquiring a first brightness value corresponding to the target face region, judging whether the first brightness value is larger than or equal to a preset brightness value threshold, and determining that ISP corresponding to the image acquisition equipment needs to be adjusted when judging that the first brightness value is larger than or equal to the preset brightness value threshold.
In this optional embodiment, optionally, obtaining a first luminance value corresponding to the target face area may include:
And converting the target face area from the RGB expression form into the YcbCr expression form, and calculating the average value of Y components of the target face area to be used as a first brightness value corresponding to the target face area.
In this optional embodiment, further, when it is determined that the first luminance value is not greater than or equal to the preset luminance value threshold, it is determined that the ISP corresponding to the image capturing device does not need to be adjusted, that is, the image capturing device is exposed normally, and this flow is ended.
Therefore, the optional implementation method can realize the judgment that the ISP needs to be adjusted under the condition that the image acquisition equipment is overexposed by acquiring the brightness value of the face image and comparing the brightness value with the preset brightness value, and further intercept the face image through the calibration result corresponding to the key point of the face before acquiring the brightness of the face image, thereby being capable of improving the determination efficiency and accuracy of the brightness value of the face image, and being beneficial to improving the judgment accuracy and reliability of whether the ISP needs to be adjusted.
In this embodiment of the present invention, as another optional implementation manner, determining, according to an image analysis parameter, whether an ISP corresponding to an image acquisition device needs to be adjusted includes:
When the image analysis parameters are white balance parameters of the face image, determining the average value of each channel in the RGB three channels of the target face area, judging whether the proportion distribution of all channels is matched with the predetermined proportion distribution according to all the average values, and determining that ISP corresponding to the image acquisition equipment needs to be adjusted when the judgment result is negative.
Therefore, the optional implementation mode can realize the judgment that the ISP needs to adjust by judging whether the distribution of the RGB three channels of the face image is reasonable.
In an embodiment of the present invention, as another optional implementation manner, determining, according to an image analysis parameter, whether an ISP corresponding to an image acquisition device needs to be adjusted includes:
When the image analysis parameters are focusing parameters of the face image, acquiring a target position of the target face area on the image acquisition equipment, judging whether the target position is in a predetermined position range, and determining that ISP corresponding to the image acquisition equipment needs to be adjusted when the judgment result is negative.
It can be seen that this alternative embodiment can implement the determination that the ISP needs to be adjusted by comparing the location where the acquired face image appears at the image capturing device with a predetermined location range.
In the embodiment of the invention, when the first brightness value is judged to be greater than or equal to the preset brightness value threshold value and/or when the proportion distribution of all channels is judged to be not matched with the predetermined proportion distribution and/or when the target position is judged not to be in the predetermined position range, the ISP is determined to be adjusted, so that the accuracy of the judgment of the ISP to be adjusted can be improved, the judgment modes of providing various ISP to be adjusted can be improved, and the judgment flexibility of the ISP to be adjusted is improved.
In the embodiment of the present invention, adjusting the ISP according to the image analysis parameter until the parameter of the ISP meets the preset condition may include:
when the first brightness value is judged to be greater than or equal to the preset brightness value threshold, the exposure parameter currently set by the ISP is obtained, and the ISP is adjusted according to the exposure parameter currently set by the ISP and the exposure parameter of the face image until the exposure parameter of the ISP is less than or equal to the preset exposure parameter, or
And when judging that the proportion distribution of all the channels is not matched with the predetermined proportion distribution, fixing the average value of the G channel of the target face image, and respectively adjusting the gain of the R channel and the gain of the B channel based on the R/G, G/B value so as to enable the proportion distribution of all the channels to be matched with the predetermined proportion distribution. Or alternatively
And when the target position is judged not to be in the predetermined position range, adjusting the ISP according to the target position until the target position is in the predetermined position range.
Therefore, according to the alternative implementation mode, the ISP is adjusted according to different parameters at different times, so that various parameters of the ISP meet the image acquisition requirements, and the image acquisition accuracy and efficiency are improved.
In an alternative embodiment, the ISP adaptive adjustment control method based on the face image may further include the following operations:
When the first brightness value is not larger than or equal to the preset brightness value threshold value, expanding the effective area of the target face area according to a preset expansion mode, and obtaining an expanded target face area, wherein the preset expansion mode is a mode set based on the central position of the target face area;
determining a second brightness value of a background area corresponding to the enlarged target face area, and calculating the inverse luminosity of the face image based on the first brightness value and the second brightness value;
judging whether the backlight degree is smaller than or equal to a preset backlight degree threshold value, and determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when judging that the backlight degree is smaller than or equal to the preset backlight degree threshold value.
In the alternative embodiment, the preset expansion mode is a mode set based on the central position of the target face area, specifically, the preset expansion mode is a rectangular image area formed by taking the central position of the target face area as the center, taking the short side of the first multiple (for example, 1 time) target face area as the first short side, and taking the long side of the second multiple (for example, 1 time) target face area as the first long side as the expanded target face area. For example, when the target face area is a rectangular image area with a short side of 10cm and a long side of 15cm, the enlarged target face area is still a rectangular image area with a center point of the target face area as a center point, the short side of 15cm and the long side of 20 cm.
In this optional embodiment, when the enlarged target face area (foreground image) is obtained, the target face area is removed from the face image by an image separation method to obtain a background area, where the image separation method may include one or more of a background difference method, a frame difference method, an optical flow field method, and an RPCA method, where the method for removing the foreground image by the image separation method is an existing method, and will not be described herein. The calculation method of the second luminance value of the background area is the same as the calculation method of the target face area, and will not be described here again.
In this alternative embodiment, the specific calculation formula of the inverse luminosity of the face image is as follows:
Wherein R is the inverse luminosity of the face image, Yf is the first brightness value corresponding to the target face region, and Yb is the second brightness value of the background region.
In this optional embodiment, further, when it is determined that the inverse luminosity is not less than or equal to the preset inverse luminosity threshold, it is determined that the ISP corresponding to the image acquisition device does not need to be adjusted, that is, the exposure of the image acquisition device is normal, and the current flow is ended.
Therefore, in the optional embodiment, when the brightness value of the face area is smaller, the brightness value of the background area corresponding to the enlarged face area is calculated, the inverse luminosity of the face image is obtained based on the two brightness values, and when the inverse luminosity of the face image is smaller, the ISP is determined to need to be adjusted, so that the judgment that the ISP needs to be adjusted under the condition that the exposure of the image acquisition equipment is insufficient is improved, the accuracy of determining that the ISP needs to be adjusted can be improved, the omnibearing dynamic adjustment of the ISP is facilitated, and the accuracy of the dynamic image acquired subsequently is facilitated.
In yet another alternative embodiment, the ISP adaptive adjustment control method based on the face image may further include the operations of:
When the inverse luminosity is not less than or equal to a preset inverse luminosity threshold value, judging whether the first brightness value is greater than or equal to a certain preset brightness value threshold value, wherein the certain preset brightness value threshold value is smaller than the preset brightness value threshold value;
and when the first brightness value is not larger than or equal to a certain preset brightness value threshold value, determining that ISP corresponding to the image acquisition equipment needs to be adjusted.
In this alternative embodiment, when it is determined that the first luminance value is greater than or equal to a certain preset luminance value threshold, it is determined that the ISP corresponding to the image capturing device does not need to be adjusted, that is, the exposure of the image capturing device is normal.
Therefore, in the alternative embodiment, when the backlight degree of the face image is judged to be larger, whether the brightness value of the face area is larger is continuously judged, and when the backlight degree of the face image is judged to be smaller, the ISP is determined to need to be adjusted, so that the accuracy of determining the underexposure of the image acquisition equipment is improved, namely the accuracy of judging the necessity of adjusting the ISP is improved, and the accuracy of omnibearing ISP dynamic adjustment is further improved.
In yet another alternative embodiment, the ISP adaptive adjustment control method based on the face image may further include the following operations before performing step 101:
Judging whether the ISP needs to be adjusted according to the current state of the ISP, and triggering and executing step 101 when judging that the ISP needs to be adjusted;
in this optional embodiment, optionally, determining whether the ISP needs to be adjusted according to the current state of the ISP includes:
reading the target moment currently displayed by the image processing system corresponding to the ISP, and obtaining the finishing moment corresponding to the ISP adjusted last time;
Calculating the interval time between the target time and the finishing time, judging whether the interval time is smaller than or equal to a predetermined interval time threshold, and determining that the ISP needs to be adjusted when the interval time is smaller than or equal to the interval time threshold.
In this optional embodiment, when it is determined that the interval duration is not less than or equal to the interval duration threshold, it is determined that the ISP does not need to be adjusted, and the total adjustment frequency of the ISP until the target time is cut off in the current operation process of the image processing system is set to zero, so that when it is determined that the ISP needs to be adjusted in the current operation process of the system, the calculation of the ineffective adjustment frequency is reduced, and further erroneous determination that the ISP needs to be adjusted is reduced.
In this alternative embodiment, the completion time corresponding to the last adjustment of the ISP is obtained from the adjustment information structure of the ISP.
It should be noted that this alternative embodiment may also occur simultaneously with step 101 or after step 101, preferably before step 101.
Therefore, before the face image is acquired, the optional embodiment judges whether the ISP needs to be adjusted according to the current state of the ISP, if so, the operation of acquiring the face image can be executed, the condition that the ISP is executed under the condition that various indexes (such as white balance and the like) of the image acquisition equipment are matched with the current environment without adjusting the ISP can be reduced, the condition that the ISP is wrongly adjusted to cause the image acquisition equipment to acquire the face image with poor quality is reduced, the power consumption of a system is reduced, and the service life of the system is prolonged.
In yet another alternative embodiment, after determining that the interval duration is less than or equal to the interval duration threshold, and before determining that the ISP needs to be adjusted, the method for controlling ISP adaptive adjustment based on the face image may further include the following operations:
Acquiring the total adjustment times of the ISP in a first preset time length, judging whether the total adjustment times are smaller than a preset adjustment times threshold, and triggering and executing the operation for determining the ISP to be adjusted when the total adjustment times are smaller than the preset adjustment times threshold, wherein the cut-off time of the first preset time length is the time of last adjustment of the ISP.
In this alternative embodiment, when it is determined that the total adjustment frequency is not less than the preset adjustment frequency threshold, it is determined that the ISP does not need to be adjusted, and the current flow is basically performed.
Therefore, in the optional embodiment, when the time for adjusting the ISP last time is short, the ISP is determined to be needed to be adjusted when the total adjustment times of the ISP in the running process of the image processing system are small, so that the accuracy of the judgment that the ISP needs to be adjusted can be improved, and the performance requirement of the ISP can be met and the complex environment is adapted by limiting the total adjustment times of the ISP in the running process of the system, so that the user experience is improved.
In yet another alternative embodiment, after adjusting the ISP according to the above image analysis parameter until the current parameter of the ISP meets the preset condition and before retriggering the execution of step 101, the ISP adaptive adjustment control method based on the face image may further include the following operations:
Judging whether the real-time display time of the image processing system corresponding to the ISP reaches the cut-off time of the second preset time length, and when the real-time display time reaches the cut-off time of the second preset time length, re-triggering and executing the step 101, wherein the starting time of the second preset time length is the time for determining that the ISP needs to be adjusted.
In this optional embodiment, when it is determined that the real-time display time does not reach the cutoff time of the second preset duration, the operation of executing the above determination on whether the real-time display time of the image processing system corresponding to the ISP reaches the cutoff time of the second preset duration is triggered. Therefore, the triggering accuracy of the operation of re-executing the face image acquisition can be improved by monitoring the real-time display time of the image processing system.
Therefore, in this optional embodiment, after the ISP adjustment is completed, whether the current time reaches the preset time is first determined, if so, the operation of acquiring the face image is re-executed, so that the requirement that a certain time is required from the writing of the parameters of the ISP to the validation can be met, the occurrence of the situation that the stability of the image processing system is possibly damaged by the subsequent direct reading of the image is reduced, and the running stability of the image processing system is further ensured.
Therefore, the ISP self-adaptive adjustment control method based on the face image described in the embodiment of the invention combines the ISP of the image acquisition device with the face related application bearing the face image quality evaluation model, inputs the acquired face image into the face image quality evaluation model for analysis, can evaluate the parameter setting of the ISP according to the image analysis parameter, namely the imaging quality of the ISP, when the ISP needs to be adjusted, adjusts the ISP according to the image analysis parameter and reacquires the face image to execute the adjustment operation of the same ISP, can realize the dynamic adjustment of the ISP, ensures that the ISP is always in a state matched with the face application, realizes the acquisition of the face image in real time and precision, is beneficial to ensuring that the face application acquires relatively stable high-quality face input data, thereby improving the effectiveness and the safety of face verification (such as access control face verification and the like), and fully utilizing the self-adjusting function of the prior image acquisition device on the premise of not increasing the cost according to the self-adaptive adjustment of the face imaging result of the face.
Example two
Referring to fig. 2, fig. 2 is a flow chart of another ISP adaptive adjustment control method based on face images according to an embodiment of the present invention. The method for controlling ISP adaptive adjustment based on face image described in fig. 2 is applicable to an image processing system, where the image processing system may be used to adjust ISP, and the image processing system is built in a terminal device capable of collecting face, where the terminal device includes a user terminal and/or an access control device. As shown in fig. 2, the ISP adaptive adjustment control method based on the face image may include the following operations:
201. and acquiring the face image acquired by the image acquisition equipment.
202. And determining the image parameters corresponding to the face image.
In the embodiment of the invention, the image parameters comprise at least one of the area of a face image, the position of the face image appearing in the image acquisition equipment and the face information of the face image, wherein the face information of the face image comprises the position of a left virtual pupil, the position of a right virtual pupil, the position of a left mouth corner of a virtual mouth, the position of a right mouth corner of the virtual mouth and the position of a virtual nose tip of the face image.
203. Judging whether the face image meets the preset ISP adjustment conditions according to the image parameters, triggering and executing step 204 when judging that the face image meets the ISP adjustment conditions, and triggering and executing step 201 when judging that the face image does not meet the ISP adjustment conditions, and ending the flow.
Therefore, after the face image is obtained, whether the face image meets the adjustment condition of the ISP is further judged, and when the face image meets the adjustment condition of the ISP, the subsequent operation is executed, so that the occurrence of the condition that the ISP adjustment is wrong due to the fact that the face image does not meet the adjustment condition of the ISP but is adjusted by the face image is reduced, the accuracy of the dynamic adjustment of the ISP is improved, the power consumption of an image processing system is reduced, and when the face image does not meet the adjustment condition of the ISP, the operation of obtaining the face image is triggered again, the image meeting the adjustment condition of the ISP is obtained, and further the dynamic adjustment of the ISP is facilitated.
204. Inputting the face image into a predetermined face image quality evaluation model for analysis, and obtaining an analysis result of the face image quality evaluation model as an image analysis parameter of the face image;
205. Judging whether the ISP corresponding to the image acquisition equipment needs to be adjusted according to the image analysis parameters, triggering and executing step 206 when judging that the ISP needs to be adjusted, and ending the flow when judging that the ISP does not need to be adjusted.
206. And adjusting the ISP according to the image analysis parameters until the parameters of the ISP meet preset conditions, and re-triggering the step 201.
In an embodiment of the present invention, as an optional implementation manner, determining whether a face image meets a predetermined ISP adjustment condition according to an image parameter includes:
And when the image parameter is the area of the face image, judging whether the area of the face image is larger than or equal to a predetermined area range, and when the judgment result is yes, determining that the face image meets the predetermined ISP adjustment condition.
Therefore, according to the alternative embodiment, the judgment that the face image meets the adjustment condition of the ISP can be realized by calculating the area of the acquired face image and comparing the area with the preset area range.
In this embodiment of the present invention, as another optional implementation manner, determining whether the face image meets the predetermined ISP adjustment condition according to the image parameter includes:
When the image parameter is the first position of the face image, acquiring a second position of the face image acquired last time, calculating the position offset of the first position and the second position, judging whether the position offset is smaller than or equal to a preset position offset threshold, and determining that the face image meets the preset ISP adjustment condition when the judgment result is yes.
In this alternative embodiment, optionally, calculating the position offset between the first position and the second position may include:
and calculating the intersection ratio of the first position and the second position as the position offset of the first position and the second position.
Therefore, according to the optional implementation mode, the judgment that the face image meets the ISP adjustment condition can be realized by calculating the position offset between the position of the face image acquired at this time and the position of the face image acquired last time in the image acquisition device, and the calculation accuracy and efficiency of the position offset between the positions of the two face images can be improved by calculating the intersection ratio of the positions of the two face images.
In an embodiment of the present invention, as another optional implementation manner, determining whether the face image meets the predetermined ISP adjustment condition according to the image parameter includes:
When the image parameter is the facial information of the face image, calculating a pupil abscissa mean value between the position of the left virtual pupil and the position of the right virtual pupil, and calculating a mouth angle abscissa mean value between the position of the left mouth angle and the position of the right mouth angle;
Calculating a first abscissa difference value between the pupil abscissa mean value and the abscissa of the position of the virtual nose tip, and calculating a second abscissa difference value between the mouth angle abscissa mean value and the abscissa of the position of the virtual nose tip;
and calculating a target horizontal coordinate difference value between the first horizontal coordinate difference value and the second horizontal coordinate difference value, judging whether the target horizontal coordinate difference value is smaller than or equal to a preset horizontal coordinate difference value range, and determining that the face image meets the preset ISP adjustment condition when the judgment result is yes.
In the alternative embodiment, the face information of the face image is obtained by determining a target calibration result matched with the face image from a predetermined calibration result set of the face key points, wherein the calibration result set of the face key points comprises a plurality of calibration results, such as a calibration result comprising 5 key points, a calibration result comprising 68 key points and a calibration result comprising 106 key points. The method selects the calibration results of 5 key points as target calibration results.
Therefore, according to the optional implementation mode, the positions of the left pupil, the right pupil, the left mouth corner, the right mouth corner and the nose tip in the face image are calculated, so that the judgment of the symmetry of the virtual five sense organs of the collected face image can be realized, and the judgment that the face image meets the adjustment condition of the ISP is realized, and the judgment accuracy that the face image meets the adjustment condition of the ISP is improved.
In the embodiment of the invention, it is to be noted that, when two or three of the above three face images meet the adjustment conditions of the ISP, the face image is determined to meet the adjustment conditions of the ISP, so that the accuracy of judging that the face image meets the adjustment conditions of the ISP can be improved, the accuracy of adjusting subsequent ISPs can be improved, and the flexibility and possibility of judging that the face image meets the adjustment conditions of the ISP can be improved by providing the adjustment means that the face images meet the adjustment conditions of the ISP.
In another optional embodiment, the ISP adaptive adjustment control method based on the face image may further include the operations of:
when judging that the face image does not meet the adjustment condition of the ISP, analyzing the factors that the face image does not meet the adjustment condition of the ISP according to the image parameters of the face image, and sending the factors to the image acquisition equipment so as to trigger the image acquisition equipment to acquire the face image again according to the factors. Among these factors, the five sense organs of the face image are incomplete, the brightness of the environment is darker, and the like.
Therefore, after the face image is judged not to meet the adjustment condition of the ISP, the optional embodiment further generates an image acquisition prompt, and the accuracy of acquiring the face image meeting the adjustment condition of the ISP is improved, so that the accuracy of dynamic adjustment of the ISP is improved.
In the embodiment of the present invention, please refer to the detailed description of step 101 to step 104 in the first embodiment for the related descriptions of step 201, step 204 and step 206, and the detailed description of the embodiment of the present invention is omitted.
Therefore, the ISP self-adaptive adjustment control method based on the face image described in the embodiment of the invention combines the ISP of the image acquisition device with the face related application bearing the face image quality evaluation model, inputs the acquired face image into the face image quality evaluation model for analysis, can evaluate the parameter setting of the ISP according to the image analysis parameter, namely the imaging quality of the ISP, when the ISP needs to be adjusted, adjusts the ISP according to the image analysis parameter, and reacquires the face image to execute the adjustment operation of the same ISP, thereby realizing the dynamic adjustment of the ISP, leading the ISP to be in a state matched with the face application all the time, realizing the acquisition of the real-time and accurate face image, being beneficial to ensuring the face application to acquire relatively stable high-quality face input data, thereby improving the effectiveness and the safety of face verification (such as access control face verification, etc.), and fully utilizing the self-adjusting function of the prior image acquisition device on the premise of not increasing the cost according to the self-adaptive adjustment of the face imaging result, and obviously improving the imaging effect of the prior image acquisition device. In addition, the method can also reduce the occurrence of errors in ISP adjustment caused by the fact that the face image does not meet the adjustment condition of the ISP and is used for adjusting the ISP, is beneficial to improving the accuracy of dynamic adjustment of the ISP and reducing the power consumption of an image processing system, is beneficial to acquiring images meeting the adjustment condition of the ISP and further beneficial to dynamic adjustment of the ISP, can also provide a judgment mode that various face images meet the adjustment condition of the ISP, and is beneficial to improving the judgment accuracy and flexibility that the face image meets the adjustment condition of the ISP and the adjustment accuracy of the subsequent ISP.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of an ISP adaptive adjustment control device based on a face image according to an embodiment of the present invention. The ISP adaptive adjustment control device based on the face image described in fig. 3 is suitable for use in an image processing system, where the image processing system may be used to adjust the ISP, and the image processing system is built in a terminal device that may collect the face, where the terminal device includes a user terminal and/or an access control device, etc. As shown in fig. 3, the ISP adaptive adjustment control device based on a face image may include an acquisition module 301, an analysis module 302, a first judgment module 303, and an adjustment module 304, where:
The acquiring module 301 is configured to acquire a face image acquired by the image acquisition device.
The analysis module 302 is configured to input the face image into a predetermined face image quality evaluation model for analysis.
The acquiring module 301 is further configured to acquire an analysis result of the face image quality evaluation model as an image analysis parameter of the face image;
a first judging module 303, configured to judge whether the ISP corresponding to the image capturing device needs to be adjusted according to the image analysis parameter.
The adjusting module 304 is configured to adjust the ISP according to the image analysis parameter when the first judging module 303 judges that the ISP needs to be adjusted, and trigger the acquiring module 301 to re-execute the operation of acquiring the face image acquired by the image acquiring device.
Therefore, the ISP self-adaptive adjustment control device based on the face image described in the embodiment of the invention combines the ISP of the image acquisition device with the face related application bearing the face image quality evaluation model, inputs the acquired face image into the face image quality evaluation model for analysis, can evaluate the parameter setting of the ISP according to the image analysis parameter, namely the imaging quality of the ISP, when the ISP needs to be adjusted, adjusts the ISP according to the image analysis parameter and reacquires the face image to execute the adjustment operation of the same ISP, can realize the dynamic adjustment of the ISP, ensures that the ISP is always in a state matched with the face application, realizes the acquisition of the face image in real time and precision, is beneficial to ensuring that the face application acquires relatively stable high-quality face input data, thereby improving the effectiveness and the safety of face verification (such as access control face verification and the like), and fully utilizing the self-adjusting function of the prior image acquisition device on the premise of not increasing the cost according to the self-adaptive adjustment of the face imaging result of the face.
In an optional embodiment, the image analysis parameter includes at least one of an exposure parameter of the face image, a white balance parameter of the face image, and a focus parameter of the face image;
the first judging module 303 may include a first judging sub-module or a second judging sub-module or a third judging sub-module, where the first judging sub-module includes an intercepting unit, an obtaining unit, a judging unit and a determining unit, and it should be noted that these sub-modules and units are not shown in the corresponding drawings, where:
and the intercepting unit is used for intercepting the face image based on the calibration result corresponding to the determined face key point to obtain a target face area when the image analysis parameter is the exposure parameter of the face image, wherein the area of the target face area is smaller than that of the face image.
And the acquisition unit is used for acquiring the first brightness value corresponding to the target face area.
And the judging unit is used for judging whether the first brightness value is larger than or equal to a preset brightness value threshold value.
A determining unit for determining that the ISP corresponding to the image acquisition device needs to be adjusted when the judging unit judges that the first brightness value is greater than or equal to the preset brightness value threshold value, or
A second judging sub-module for determining the average value of each of the RGB three channels of the target face region when the image analysis parameter is the white balance parameter of the face image, judging whether the proportional distribution of all channels is matched with the predetermined proportional distribution according to all the average values, and determining that the ISP corresponding to the image acquisition device needs to be adjusted when the judging result is no, or
And the third judging sub-module is used for acquiring the target position of the target face region in the image acquisition equipment when the image analysis parameter is the focusing parameter of the face image, judging whether the target position is in a predetermined position range, and determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when the judgment result is negative.
Therefore, the ISP self-adaptive adjustment control device based on the face image can also judge whether the distribution of three channels of RGB of the face image is reasonable or not and/or compare the position of the acquired face image in the image acquisition equipment with a predetermined position range by acquiring the brightness value of the face image and comparing the brightness value with a preset brightness value, so that the judgment that the ISP needs to be adjusted under the condition that the image acquisition equipment is overexposed can be realized, the judgment accuracy and the flexibility of the ISP needs to be adjusted can be improved by providing a plurality of determination modes that the ISP needs to be adjusted, and the face image can be further intercepted through the calibration result corresponding to the key points of the face before the brightness of the face image is acquired, thereby being beneficial to improving the judgment accuracy and the reliability of whether the ISP needs to be adjusted.
In another optional embodiment, the obtaining unit is further configured to, when the judging unit judges that the first luminance value is not greater than or equal to the preset luminance value threshold, expand the effective area of the target face area according to a preset expansion mode, and obtain an expanded target face area, where the preset expansion mode is a mode set based on a central position of the target face area.
And the determining unit is also used for determining a second brightness value of the background area corresponding to the enlarged target face area.
And the acquisition unit is also used for calculating the inverse luminosity of the face image based on the first brightness value and the second brightness value.
And the judging unit is used for judging whether the inverse luminosity is smaller than or equal to a preset inverse luminosity threshold value, and triggering the determining unit to execute the operation of determining that the ISP corresponding to the image acquisition equipment needs to be adjusted when judging that the inverse luminosity is smaller than or equal to the preset inverse luminosity threshold value.
Therefore, the ISP self-adaptive adjustment control device based on the face image can also be used for realizing the judgment of ISP adjustment under the condition of insufficient exposure of the image acquisition equipment by calculating the brightness value of the background area corresponding to the enlarged face area when the brightness value of the face area is smaller, acquiring the inverse luminosity of the face image based on the two brightness values and determining that the ISP needs to be adjusted when the inverse luminosity of the face image is smaller, so that the determination accuracy of the ISP needs to be adjusted can be improved, the omnibearing dynamic adjustment of the ISP is facilitated, and the accuracy of the dynamic image acquired subsequently is facilitated.
In still another alternative embodiment, the above-mentioned ISP adaptive adjustment control device based on a face image may further include a second determining module 305, where the ISP adaptive adjustment control device based on a face image may be as shown in fig. 4, and fig. 4 is a schematic structural diagram of another ISP adaptive adjustment control device based on a face image, where:
The second judging module 305 is configured to judge whether the ISP needs to be adjusted according to the current state of the ISP before the acquiring module 301 acquires the face image acquired by the image acquiring device, and trigger the acquiring module 301 to execute the operation of acquiring the face image acquired by the image acquiring device when the ISP needs to be adjusted.
In this alternative embodiment, as shown in fig. 4, optionally, the second determining module 305 may include a reading submodule 3051, an obtaining submodule 3052, a calculating submodule 3053, and a fourth determining submodule 3054, where:
and the reading submodule 3051 is used for reading the target moment currently displayed by the image processing system corresponding to the ISP.
And the acquiring submodule 3052 is used for acquiring the finishing moment corresponding to the ISP adjusted last time.
A calculating submodule 3053 for calculating an interval duration between the target time and the completion time.
A fourth judging sub-module 3054, configured to judge whether the interval duration is less than or equal to a predetermined interval duration threshold.
The obtaining submodule 3052 is further configured to determine that the ISP needs to be adjusted when the fourth judging submodule 3054 judges that the interval duration is less than or equal to the interval duration threshold.
Therefore, the implementation of the ISP adaptive adjustment control device based on the face image described in fig. 4 can also determine whether the ISP needs to be adjusted according to the current state of the ISP before the face image is acquired, if so, the operation of acquiring the face image can be performed, which can reduce the occurrence of the adjustment operation performed on the ISP without adjusting the ISP, that is, under the condition that the indexes (such as white balance, etc.) of the image acquisition device are matched with the current environment, thereby being beneficial to reducing the occurrence of the situation that the ISP performs incorrect adjustment to cause the image acquisition device to acquire the face image with poor quality, reducing the power consumption of the system, and improving the service life of the system.
In yet another alternative embodiment, as shown in fig. 4, the obtaining submodule 3052 is further configured to obtain, after the fourth judging submodule 3054 judges that the interval duration is less than or equal to the interval duration threshold and before determining that the ISP needs to be adjusted, a total adjustment number of the ISP within a first preset duration, where a deadline time of the first preset duration is a time of last adjustment of the ISP.
The fourth determining sub-module 3054 is further configured to determine whether the total adjustment frequency is smaller than a preset adjustment frequency threshold, and trigger the obtaining sub-module 3052 to perform the operation of determining that the ISP needs to be adjusted when determining that the total adjustment frequency is smaller than the preset adjustment frequency threshold.
Therefore, the ISP adaptive adjustment control device based on the face image described in fig. 4 can further determine that the ISP needs to be adjusted when the total adjustment times of the ISP in the current operation process of the image processing system are smaller when the time for adjusting the ISP last time is shorter, so that the accuracy of the ISP needs to be adjusted can be improved, and the performance requirement of the ISP can be met and the complex environment can be adapted by limiting the total adjustment times of the ISP in the current operation process of the system, so that the user experience is improved.
In yet another alternative embodiment, as shown in fig. 4, the above-mentioned ISP adaptive adjustment control device based on a face image may further include a determining module 306 and a third judging module 307, where:
A determining module 306, configured to determine, after the acquiring module 301 acquires the face image acquired by the image acquiring device and before the analyzing module 302 inputs the face image into the predetermined face image quality assessment model for analysis, image parameters corresponding to the face image, where the image parameters include at least one of an area of the face image, a position where the face image appears in the image acquiring device, and facial information of the face image, where the facial information of the face image includes a position of a left virtual pupil, a position of a right virtual pupil, a position of a left mouth corner of the virtual mouth, a position of a right mouth corner of the virtual mouth, and a position of a virtual nose tip of the face image.
A third judging module 307, configured to judge whether the face image meets the predetermined ISP adjustment condition according to the image parameter, and trigger the analyzing module 302 to perform an operation of inputting the face image into the predetermined face image quality evaluation model for analysis when it is judged that the face image meets the ISP adjustment condition.
Therefore, the implementation of the ISP adaptive adjustment control device based on the face image described in fig. 4 can further determine whether the face image satisfies the adjustment condition of the ISP after the face image is acquired, and execute the subsequent operation when the face image is determined to satisfy the adjustment condition of the ISP, so that the occurrence of errors in ISP adjustment caused by the fact that the face image does not satisfy the adjustment condition of the ISP but uses the ISP to adjust the ISP can be reduced, which is beneficial to improving the accuracy of dynamic adjustment of the ISP and reducing the power consumption of the image processing system, and when the face image is determined not to satisfy the adjustment condition of the ISP, the operation of acquiring the face image is retried, which is beneficial to acquiring the image satisfying the adjustment condition of the ISP, and further beneficial to dynamic adjustment of the ISP.
In yet another alternative embodiment, as shown in fig. 4, the ISP adaptive adjustment control device based on a face image may further include a fourth determining module 308, where:
A fourth judging module 308, configured to judge whether the real-time display time of the image processing system corresponding to the ISP reaches the expiration time of the second preset duration after the adjusting module 304 adjusts the ISP according to the image analysis parameter until the current parameter of the ISP meets the preset condition and before the triggering obtaining module 301 retriggers to perform the operation of obtaining the face image acquired by the image acquisition device, and when the real-time display time is judged to reach the expiration time of the second preset duration, trigger the obtaining module 301 to retrigger to perform the operation of obtaining the face image acquired by the image acquisition device, where the starting time of the second preset duration is a time when it is determined that the ISP needs to be adjusted.
Therefore, the ISP adaptive adjustment control device based on the face image described in fig. 4 can also determine whether the current time reaches the preset time after the ISP adjustment is completed, and if so, re-execute the operation of acquiring the face image, so as to meet the requirement that a certain time is required from writing the parameters of the ISP into the register to effect, thereby reducing the occurrence of the condition that the stability of the image processing system may be damaged when the subsequent direct image reading is performed, and further ensuring the running stability of the image processing system.
Example IV
Referring to fig. 5, fig. 5 shows another ISP adaptive adjustment control device based on a face image according to an embodiment of the present invention. The apparatus described in fig. 5 may be applied to an image processing system, where the image processing system may be used to adjust an ISP, and the image processing system is built in a terminal device that may collect a face, where the terminal device includes a user terminal and/or an access control device, etc. As shown in fig. 5, the ISP adaptive adjustment control device based on a face image may include:
a memory 501 in which executable program codes are stored;
a processor 502 coupled to the memory 501;
further, an input interface 503 and an output interface 504 coupled to the processor 502 may also be included;
the processor 502 invokes executable program codes stored in the memory 501, for executing the steps of the ISP adaptive adjustment control method based on face image described in the first or second embodiment.
Example five
The embodiment of the invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the ISP adaptive adjustment control method based on face images described in the first or second embodiment.
Example six
The embodiment of the invention discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to make a computer execute the steps of the ISP adaptive adjustment control method based on face image described in the first or second embodiment.
The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that the method and apparatus for ISP adaptive adjustment control based on face images disclosed in the embodiments of the present invention are only disclosed in the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, but not to limit the same, although the present invention is described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions described in the foregoing embodiments may be modified or some of the technical features may be equivalently replaced, and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.