Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a chip detection method is provided, which is described by taking an example that the method is applied to a terminal, and includes the following steps:
s110: and acquiring a chip image of the chip to be detected.
The chip to be detected is the chip which needs to be detected whether the chip is qualified or not. For example, the chip to be detected may be a SIM chip that needs to be detected as being qualified after production. The chip image of the chip to be detected is an image obtained by shooting the chip to be detected. Specifically, the terminal may receive a chip image of the chip to be detected, which is sent by a camera for shooting the chip to be detected.
S130: and generating a corresponding image moment according to the chip image.
Image moments are operators that describe image features. Specifically, the terminal generates an image moment of this chip image from the chip image.
S150: and generating an identification operator corresponding to the chip image according to the image moment.
The recognition operator is an operator which further embodies the image characteristics on the basis of the image moments. Specifically, the terminal generates an identification operator according to the image moment of the chip image, and the identification operator is the identification operator of the chip image.
S170: and if the recognition operator of the chip image is matched with the preset template recognition operator, generating a qualified detection result.
The preset template recognition operator is a preset recognition operator for reference comparison. For example, the template identifier may be the identifier corresponding to the image of a standard qualified chip. Specifically, the recognition operator of the chip image is matched with the preset template recognition operator, which means that the recognition operator of the chip image is consistent with the preset template recognition operator. It is understood that the condition that the matching is satisfied may be other conditions, for example, the matching between the recognition operator of the chip image and the preset template recognition operator may also mean that the difference between the recognition operator of the chip image and the template recognition operator is within a preset range.
S190: and if the recognition operator of the chip image is not matched with the preset template recognition operator, generating a detection unqualified result.
The recognition operator describes the image characteristics of the corresponding image, and the image characteristics can accurately reflect the characteristic information of the image; by comparing the recognition operator of the chip image with the template recognition operator, the chip to be detected corresponding to the chip image and the standard qualified chip corresponding to the template recognition operator can be compared and analyzed. If the recognition operator of the chip image is matched with the template recognition operator, the chip to be detected is the same as or similar to the standard qualified chip, the chip to be detected is qualified, and a qualified detection result is generated; otherwise, if not, the difference between the chip to be detected and the standard qualified chip is larger, the chip to be detected is unqualified, and the unqualified detection result is generated.
According to the chip detection method, the corresponding image moment is generated according to the chip image of the chip to be detected, the recognition operator corresponding to the chip image is generated according to the image moment, and the recognition operator is compared and analyzed with the preset template recognition operator to realize the detection of the chip to be detected. If the recognition operator of the chip image is matched with the template recognition operator, the chip image is qualified, the chip to be detected corresponding to the chip image is qualified, and a detection qualified result is generated; and if the recognition operator of the chip image is not matched with the template recognition operator and indicates that the chip image is unqualified, the chip to be detected corresponding to the chip image is unqualified, and a detection unqualified result is generated. Therefore, qualified detection is carried out through the recognition operator generated according to the image moment of the chip image, the anti-interference performance is strong, and the detection accuracy rate is high.
It is understood that in other embodiments, other methods may be used to test the qualification of the chip to be tested. For example, since the area characteristics of different types of chips are relatively stable and have the ability to distinguish, the area of the chip can be used for identification and detection. If the normal area of the chip is set to float between S1 and S2, the chip is identified as a qualified chip if the area of the chip is between S1 and S2; if not between S1-S2, the chip is not qualified.
In one embodiment, step S110 includes: receiving an initial image sent after the shooting of a camera; and extracting the outline of the initial image, and if the extraction is successful, taking the initial image as a chip image of the chip to be detected.
The camera is used for shooting a chip to be detected; in the actual use process, the camera can be placed at a fixed position for shooting, so that the initial image shot by the camera may or may not shoot the chip to be detected. By extracting the outline of the initial image, specifically extracting the outline of the chip, if the extraction is successful, namely extracting the outline, the initial image is an image obtained by shooting the chip to be detected, and the initial image can be used as the chip image of the chip to be detected. Therefore, the image of the chip to be detected in the chip image can be ensured, and the detection effectiveness is improved. Specifically, the terminal may perform contour extraction through findcontours () function.
In one embodiment, in step S110, after the step of receiving the initial image sent after the camera shooting and before the step of performing contour extraction on the initial image, the method further includes: the initial image is pre-processed. Correspondingly, the terminal extracts the outline of the preprocessed initial image.
Wherein the preprocessing includes a process of removing noise interference. For example, the preprocessing may be smoothing, filtering, or the like. The initial image is preprocessed, so that the accuracy of the initial image can be improved, and the accuracy of subsequent analysis and detection is improved.
The chip detection method can be used for detecting the qualification of the SIM chip, the SIM chip is placed on the conveyer belt, the conveyer belt is driven by the driving wheel to move, and the camera is used for shooting the SIM chip on the conveyer belt. In one embodiment, step S110 is followed by: and if the extraction is not successful, namely the outline is not extracted, controlling the driving wheel to drive the conveyor belt to move so as to convey the SIM chip. And if the contour extraction is unsuccessful, the camera does not shoot the chip to be detected. At the moment, the driving wheel is controlled to drive the conveyor belt to move so as to convey the SIM chip, so that the camera can shoot conveniently to detect the chip.
In one embodiment, the image moments include geometric moments and geometric center-to-center distances. The step S130 includes: carrying out threshold segmentation on the chip image to obtain a discrete function of a binary image; and performing Riemann integration on the discrete function of the binary image to obtain the geometric moment and the geometric center distance of the corresponding chip image.
The method comprises the steps of performing threshold segmentation on a chip image, specifically, counting gray values of the chip image to obtain a gray histogram, dividing pixel values of the image into two types of values, namely 0 and 1 according to the gray histogram and a set threshold, wherein the pixel value is 1 when the pixel value is greater than or equal to the set threshold, and the pixel value is 0 when the pixel value is smaller than the set threshold, so as to obtain a binary image. The gray histogram can be used to divide the pixel set and separate the background region from the target region, so as to achieve the purpose of image segmentation. For example, a grayscale histogram of the SIM chip is shown in fig. 2. The discrete function of the binarized image is the corresponding expression function of the binarized image. Through Riemann integration of the discrete function, the geometric moment and the geometric center distance can be obtained and used as the geometric moment and the geometric center distance of the corresponding chip image.
Specifically, assuming that the discrete function of the binarized image is f (x, y), the geometric moment m of order p + q of f (x, y) can be calculatedpqAnd the geometric central moment mupqThe definition is as follows:
wherein x and y are respectively an abscissa value and an ordinate value of the binarized image,andthe average value of the abscissa and the average value of the ordinate are respectively, and N and M are respectively the row and column sizes of the binary image.
In one embodiment, step S150 includes: calculating according to the geometric center distance to obtain HU moment; optimizing the HU moment according to the geometric center distance to obtain an improved HU moment; calculating to obtain eccentricity according to the geometric moment; and forming a characteristic vector by the improved HU moment and the eccentricity to obtain an identification operator of the chip image.
The improved HU moments including R1, R2, R3, R4, R5, R6, R7, R8, R9, and eccentricity is taken as an example, and the improved HU moments and eccentricity constitute feature vectors, specifically, feature vectors of composition [ R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, e ], as recognition operators. The improved HU moment is obtained by optimizing the HU moment, and on the basis, the eccentricity is combined to form an identification operator, so that the feature identification accuracy is high.
Specifically, the calculating of the HU moment according to the geometric center distance in step S150 includes: normalizing the geometric center distance to obtain a normalized center distance; the HU moments are linearly composed according to the normalized center distance.
Geometric center moment mu of chip imagepqWith only translational invariance and no rotational invariance. In order to make the chip image satisfy the rotation invariance and the proportion invariance, normalization processing can be carried out on the chip image to obtain a normalized center distance, and a formula of the normalized center distance is defined as follows:
further, the normalized central moment can be linearly composed of 7 HU moments with translational invariance, rotational invariance and proportional invariance, i.e., 7 image invariant moments, and the formula is as follows:
wherein,to7 HU moments, respectively.
In one embodiment, in step S150, the HU moments are optimized according to the geometric center-to-center distance to obtain improved HU moments, including: the improved HU moment is obtained by removing the geometric center distance of 0 order in the HU moment through ratio calculation.
E.g. mupqRepresenting the geometric center distance, the geometric center distance of 0 order is mu00By removing the scale factor mu00And obtaining a new uniform invariant moment, wherein the new uniform invariant moment can ignore the change caused by the area or the scaling of the target image, is only related to the geometric shape and is suitable for target elements with different area structures. So, obtain improving the HU square through optimizing the HU square, carry out the qualification based on improving the HU square and detect, can realize high-efficient discernment, and discern the correct rate height.
Specifically, the improved HU moment is obtained by removing the geometric center distance of 0 order in the HU moment through ratio calculation, and includes:
wherein R1, R2, R3, R4, R5, R6, R7, R8, R9 and R10 are respectively used for improving HU moment. Remove mu00But its translational, dimensional and rotational invariance is still satisfied.
In one embodiment, in step S150, calculating the eccentricity according to the geometric moment includes:
wherein e is the eccentricity, m20、m02And m11Can be based on a formulaAnd (4) obtaining.Eccentricity is the ratio of the maximum axis to the minimum axis of the image, satisfying geometric feature invariance. By adopting the eccentricity e, the recognition capability of HU moment on the chip contour is enhanced and improved.
For example, referring to fig. 3, a detailed flowchart of steps S130 and S150 in a detailed embodiment is shown.
In one embodiment, after step S170, the method further includes the step of: performing rectangle fitting on the qualified chip image to obtain four intersection point coordinates of a fitting rectangle; and calculating to obtain the center coordinate and the deflection angle of the fitting rectangle according to the intersection point coordinate.
The center coordinate is a coordinate of a center position of the fitted rectangle, and the deflection angle is an angle of the fitted rectangle with respect to a deflection position in a preset zero degree direction. The center coordinate and the deflection angle can reflect the position of the chip image, so that the chip image is positioned. Specifically, after the central coordinate and the deflection angle are obtained, a mounting position instruction can be generated according to the central coordinate and the deflection angle, and the mounting position instruction is used for controlling the chip mounter to mount the chip according to the central position and the deflection angle. The chip is positioned by adopting a rectangular fitting method, the positioning accuracy is high, and particularly the positioning accuracy is within 0.5 pixel and the rotation angle is within 0.10.
Referring to fig. 4, the specific process analysis of the positioning step is as follows: when performing the rectangular fitting, first, four vertices on the target area are determined. The coordinates of the four found vertexes are in a linear relation with the fitted rectangle, and the more accurate the four vertexes are, the higher the accuracy of the rectangle fitting is. Then, four vertexes are taken as boundaries to divide the edge points into four groups, and the number of pixel coordinate sets sampled equidistantly in each group is n1、n2、n3、n4And then the coordinate expression of each group of pixel points is as follows:
wherein, Xi(i＝1，2，3，4) Is the horizontal and vertical coordinates of four vertexes of the three-dimensional display, and x and y belong to different four groups respectively. According to the geometric characteristics of the rectangle, namely that the opposite sides are parallel and the adjacent sides are perpendicular, the equation of the straight line where the four sides of the rectangle are located is expressed as follows:
wherein, a, b, ci(i ═ 1,2,3,4) are parameters of the linear equation. The standard rectangle can be fitted by the shortest distance from the straight line where the four sides are located to the pixel point of each side, namely the deviation of the 4 equations is minimum, so that the edge of the outline of the chip can be accurately expressed. Because positive and negative deviations exist, the positive and negative deviations can be mutually offset through summation, and then the geometric characteristics of the rectangle are combined, namely the slopes of adjacent sides are mutually inverted and the slopes of opposite sides are equal, so that the fitting equation of the rectangle is expressed as follows:
in the formula n1、n2、n3、n4Corresponding to the number of points contained by the four sides of the target, and then respectively pairing a, b and c1、c2、c3、c4Calculating partial derivative to obtain parameters a and b and intercept c corresponding to each side1、c2、c3、c4Finally obtaining a linear equation of each edge, and solving to obtain four intersection points A (x)A,yA)，B(xB,yB)，C(xC,yC)，D(xD,yD) And the average value of the intersection coordinates is the center coordinate (x) of the chip image0,y0) The position parameters are as follows:
in addition, when an included angle between one side of the rectangle and the x axis is 90 degrees, it indicates that the chip to be detected does not deflect, and then the deflection angle of the chip to be detected is:
specifically, when a chip mounter is controlled by a central coordinate and a deflection angle to mount, when the deflection angle is smaller than 0 degree, the chip to be detected can be controlled to rotate anticlockwise to compensate; when the deflection angle is larger than 0 degree, the chip to be detected can be controlled to rotate clockwise for compensation.
It should be understood that although the various steps in the flowcharts of fig. 1, 3-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1 and 3-4 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
Referring to fig. 5, when the SIM chip is mounted, the driving wheel 9 and the driven wheel 7 act together to drive the synchronous belt 6 to move, the synchronous belt 6 drives the SIM plate 5 in the material clamping mechanism to move synchronously, and the SIM chip is identified and positioned by the vision system after being delivered to an accurate station. The hardware of the vision system generally consists of two cameras, namely the reference camera 2 and the recognition camera 10, and the software part can adopt OpenCV. The reference camera 2 is arranged on the suction head 1 and moves along the x-y direction, sucks the chip 4 through the suction nozzle 3 and moves to the upper part of the recognition camera 10 to shoot to obtain a chip image of the chip to be detected. And then, the OpenCV acquires a chip of the chip to be detected for execution, executes the chip detection method, and performs qualification detection on the SIM chip. Furthermore, the qualified chip can be positioned, and the center coordinate and the deflection angle can be obtained. Because the improved HU moment and eccentricity are used as the characteristic vectors, the SIM chips which rotate, translate and scale are identified, and then the rectangular fitting method is used for positioning, the SIM chips can be positioned with high precision on the basis of high-efficiency identification.
Referring to fig. 6, a comparison graph of performing eligibility detection on the chip to be detected by using the conventional HU moment as the identifier and performing eligibility detection on the chip to be detected by using the feature vector formed by the improved HU moment and the eccentricity as the identifier is shown. The identification performance of the algorithm is analyzed by calculating the relationship between the number of different chips and the correct identification rate, and the characteristic vector formed by improving the HU moment and the eccentricity is used as an identification operator to have better performance in the aspect of SIM chip identification.
In one embodiment, as shown in fig. 7, there is provided a chip detecting apparatus, including: an image acquisition module 710, an image moment calculation module 730, an identifier calculation module 750, a first result generation module 770, and a second result generation module 790, wherein:
the image obtaining module 710 is configured to obtain a chip image of a chip to be detected. The image moment calculation module 730 is configured to generate a corresponding image moment according to the chip image. The recognition operator calculation module 750 is configured to generate a recognition operator corresponding to the chip image according to the image moment. The first result generating module 770 is configured to generate a qualified detection result when the recognition operator of the chip image matches a preset template recognition operator. The second result generating module 790 is configured to generate a result that the detection is not qualified when the identifier of the chip image is not matched with the preset template identifier.
According to the chip detection device, the corresponding image moment is generated according to the chip image of the chip to be detected, the recognition operator corresponding to the chip image is generated according to the image moment, and the recognition operator and the preset template recognition operator are compared and analyzed to realize the detection of the chip to be detected. If the recognition operator of the chip image is matched with the template recognition operator, the chip image is qualified, the chip to be detected corresponding to the chip image is qualified, and a detection qualified result is generated; and if the recognition operator of the chip image is not matched with the template recognition operator and indicates that the chip image is unqualified, the chip to be detected corresponding to the chip image is unqualified, and a detection unqualified result is generated. Therefore, qualified detection is carried out through the recognition operator generated according to the image moment of the chip image, the anti-interference performance is strong, and the detection accuracy rate is high.
In one embodiment, the image acquisition module 710 receives an initial image sent after the camera takes a picture; and extracting the outline of the initial image, and if the extraction is successful, taking the initial image as a chip image of the chip to be detected. And extracting the outline of the initial image, and taking the initial image which is successfully extracted as a chip image of the chip to be detected. Therefore, the image of the chip to be detected in the chip image can be ensured, and the detection effectiveness is improved.
In one embodiment, the image moments include geometric moments and geometric center-to-center distances. The image moment calculation module 730 is used for performing threshold segmentation on the chip image to obtain a discrete function of the binarized image; and performing Riemann integration on the discrete function of the binary image to obtain the geometric moment and the geometric center distance of the corresponding chip image.
In one embodiment, the recognition operator calculation module 750 is configured to calculate the HU moments according to the geometric center-to-center distances; optimizing the HU moment according to the geometric center distance to obtain an improved HU moment; calculating to obtain eccentricity according to the geometric moment; and forming a characteristic vector by the improved HU moment and the eccentricity to obtain an identification operator of the chip image. The improved HU moment is obtained by optimizing the HU moment, and on the basis, the eccentricity is combined to form an identification operator, so that the feature identification accuracy is high.
In one embodiment, the chip detection apparatus further includes a positioning module, configured to perform rectangle fitting on the qualified chip image to obtain coordinates of four intersection points of a fitted rectangle; and calculating to obtain the center coordinate and the deflection angle of the fitting rectangle according to the intersection point coordinate. The chip is positioned by adopting a rectangular fitting method, and the positioning precision is high.
For the specific definition of the chip detection device, reference may be made to the above definition of the chip detection method, which is not described herein again. The modules in the chip detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a chip detection method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the aforementioned chip detection method when executing the computer program.
According to the computer equipment, the steps of the chip detection method are realized, and the accuracy of chip qualification detection can be improved in the same way.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the aforementioned chip detection method.
The computer readable storage medium realizes the steps of the chip detection method, and can improve the accuracy of chip qualification detection.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.