CN111524076A - Image processing method, electronic device, and computer-readable storage medium - Google Patents
Image processing method, electronic device, and computer-readable storage mediumDownload PDFInfo
- Publication number
- CN111524076A CN111524076ACN202010265232.5ACN202010265232ACN111524076ACN 111524076 ACN111524076 ACN 111524076ACN 202010265232 ACN202010265232 ACN 202010265232ACN 111524076 ACN111524076 ACN 111524076A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- processed
- hue
- component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明实施例涉及图像处理技术领域，特别涉及一种图像处理方法、电子设备和计算机可读存储介质。Embodiments of the present invention relate to the technical field of image processing, and in particular, to an image processing method, an electronic device, and a computer-readable storage medium.
背景技术Background technique
目前，绿幕抠图技术在电影行业扮演中极其重要的作用，通过绿幕技术能够准确分割出前后景物体，并通过后期的合成技术能够实现电影中的各种特效。在实际绿幕场景拍摄中，由于场景灯光布局及前景物体本身的影响，绿色成分很容易“溢出”到前景物体上，如：1)绿幕背景反光2)前景角色身穿白色衣物3)前景物体头发丝等毛发边缘4)人物身体轮廓及边缘等等。绿色成分的“溢出”导致成像后的前景物体局部偏色，为了克服这种“溢色”现象，现有许多色彩抑制方法被提出，现有主流方法大多为RGB通道抑制，主要原理为抑制G通道或B通道(蓝幕)的颜色成分，低降低绿色或蓝色成分的影响At present, green screen matting technology plays an extremely important role in the film industry. Through green screen technology, it can accurately segment foreground and background objects, and through post-compositing technology, various special effects in the film can be realized. In the actual green screen scene shooting, due to the influence of the scene lighting layout and the foreground object itself, the green component can easily "spill" to the foreground object, such as: 1) The green screen background reflects light 2) The foreground character is wearing white clothes 3) The foreground Object hair and other hair edges 4) Character body contours and edges and so on. The "spill" of the green component causes the partial color cast of the imaged foreground object. In order to overcome this "spill" phenomenon, many color suppression methods have been proposed. Most of the existing mainstream methods are RGB channel suppression, and the main principle is to suppress G Channel or B channel (blue screen) color component, low to reduce the impact of green or blue components
然而，发明人发现相关技术中至少存在如下问题：RGB通道抑制方法虽然能够有效的抑制溢色区域反射的背景色成分，但同时会影响一些非溢色区域的颜色。However, the inventor found that the related art has at least the following problems: although the RGB channel suppression method can effectively suppress the background color components reflected in the overflow area, it will affect the colors of some non-overflow areas at the same time.
发明内容SUMMARY OF THE INVENTION
本发明实施方式的目的在于提供一种图像处理方法、电子设备和计算机可读存储介质，使得可以有效的抑制溢色区域反射的背景色成分，同时不影响一些非溢色区域的颜色。The purpose of the embodiments of the present invention is to provide an image processing method, an electronic device and a computer-readable storage medium, which can effectively suppress the background color component reflected in the overflow area without affecting the colors of some non-overflow areas.
为解决上述技术问题，本发明的实施方式提供了一种图像处理方法，包括：确定待处理图像中的溢色区域，并确定所述溢色区域中的像素为预设色相的置信度；其中，所述预设色相为所述待处理图像中的背景色的色相；去除所述待处理图像中的所述背景色得到第一图像；根据所述置信度对所述第一图像和所述待处理图像进行线性混合，获取第二图像；对所述第二图像的亮度和饱和度进行修正，获取处理后的结果图像。In order to solve the above-mentioned technical problem, an embodiment of the present invention provides an image processing method, including: determining a color overflow area in an image to be processed, and determining the confidence level that the pixels in the color overflow area are a preset hue; wherein , the preset hue is the hue of the background color in the image to be processed; a first image is obtained by removing the background color in the image to be processed; the first image and the The images to be processed are linearly mixed to obtain a second image; the brightness and saturation of the second image are corrected to obtain a processed result image.
本发明的实施方式还提供了一种电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行上述的图像处理方法。Embodiments of the present invention also provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores data executable by the at least one processor The instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned image processing method.
本发明的实施方式还提供了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述的图像处理方法。Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned image processing method is implemented.
本发明实施方式相对于现有技术而言，确定待处理图像中的溢色区域，即对待处理图像中的溢色区域和非溢色区域进行了区分。通过确定待处理图像中的溢色区域中的像素为预设色相的置信度，其中预设色相为待处理图像中的背景色的色相，使得可以通过溢色区域中的像素的置信度得出该像素与背景色的色相的接近程度。通过去除待处理图像中的背景色得到第一图像，使得第一图像中的背景色成分可以大幅度降低。根据置信度对第一图像和待处理图像进行线性混合，获取第二图像，即结合溢色区域中的像素的色相与背景色的色相的接近程度，对去除背景色的第一图像和待处理图像即原始图像进行线性混合得到第二图像，使得在一定程度上第二图像相比于原始图像溢色区域反射的背景色成分可以被抑制。另外，由于去除待处理图像中的背景色会在一定程度上影响亮度和饱和度，因此，对第二图像的亮度和饱和度进行修正，获取处理后的结果图像，使得处理后的结果图像可以将因去除背景色影响的亮度和饱和度还原，从而可以在抑制溢色区域反射的背景色成分的同时不影响一些非溢色区域的颜色。Compared with the prior art, the embodiment of the present invention determines the overflow area in the image to be processed, that is, distinguishes the overflow area and the non-overflow area in the image to be processed. By determining the confidence that the pixels in the overflow area in the image to be processed are the preset hue, where the preset hue is the hue of the background color in the image to be processed, it can be obtained from the confidence of the pixels in the overflow area. How close this pixel is to the hue of the background color. The first image is obtained by removing the background color in the image to be processed, so that the background color component in the first image can be greatly reduced. Linearly mix the first image and the to-be-processed image according to the confidence level, and obtain a second image, that is, combine the degree of closeness between the hue of the pixels in the overflow area and the hue of the background color, and compare the first image with the background color removed and the to-be-processed image. The image, that is, the original image, is linearly mixed to obtain the second image, so that the background color component reflected by the second image compared with the color overflow area of the original image can be suppressed to a certain extent. In addition, since removing the background color in the image to be processed will affect the brightness and saturation to a certain extent, the brightness and saturation of the second image are corrected, and the processed result image is obtained, so that the processed result image can be Restore the brightness and saturation affected by the removal of the background color, so that the background color components reflected in the overflow area can be suppressed without affecting the color of some non-spill areas.
另外，所述根据所述溢色区域中的像素的HSL分量值和所述预设色相关联的工作区间，计算所述溢色区域中的像素为预设色相的置信度，包括：通过以下公式计算所述溢色区域中的像素为预设色相的置信度：In addition, the calculating, according to the HSL component value of the pixel in the overflow area and the working interval associated with the preset color, calculates the confidence that the pixel in the overflow area is the preset hue, including: by the following The formula calculates the confidence that the pixels in the overflow area are the preset hue:
其中，所述C为计算的置信度，所述H为像素的色相分量值，所述Lo，Li，Ro，Ri，分别为所述工作区间在色相环上的头端渐变开始值，头端渐变结束值，尾端渐变开始值，尾端渐变结束值。提供了一种计算置信度的具体公式，方便了准确的计算溢色区域中的像素为预设色相的置信度。Wherein, the C is the calculated confidence, the H is the hue component value of the pixel, and the Lo , Li , Ro , and Ri are respectively the beginning of the gradient at the beginning of the working interval on the hue circle. value, the end value of the head end gradient, the start value of the end end gradient, and the end value of the end end gradient. A specific formula for calculating the confidence is provided, which facilitates the accurate calculation of the confidence that the pixels in the overflow area are preset hues.
另外，所述色相估计值的获取方式如下：获取所述待处理图像中的背景区域的像素在HSL色彩空间下H分量值的平均值；将所述H分量值的平均值作为所述色相估计值。提供了一种色相估计值的获取方式，将背景区域的像素在HSL色彩空间下H分量值的平均值作为色相估计值，有利于考虑到背景区域的所有像素的H分量值，从而对背景色的色相值进行准确的估计，避免现有技术中使用背景色的色相经验值可能带来的偏差。In addition, the acquisition method of the hue estimation value is as follows: acquiring the average value of the H component value of the pixels of the background area in the image to be processed in the HSL color space; taking the average value of the H component value as the hue estimation value. Provides a way to obtain the estimated value of hue. The average value of the H component value of the pixels in the background area in the HSL color space is used as the estimated value of the hue. The hue value of the background color can be estimated accurately, and the deviation that may be caused by using the hue experience value of the background color in the prior art is avoided.
另外，在所述对所述第二图像的亮度和饱和度进行调整，获取处理后的结果图像之后，还包括：对所述待处理图像的背景区域进行色彩成分分析，确定溢出抑制估计值；根据所述溢出抑制估计值对所述待处理图像和所述结果图像进行线性融合，得到目标图像。考虑到实际场景中由于灯光材质不同背景色往往会发生变化，现有G通道溢出抑制方法未分析真实的背景色成分，容易导出溢出抑制不足或过度抑制。本发明实施方式通过对待处理图像的背景区域进行色彩成分分析确定溢出抑制估计值，根据溢出抑制估计值对待处理图像和结果图像进行线性融合，得到目标图像，有利于避免溢出抑制不足或过度抑制，从而更精确的抑制溢色区域反射的背景色成分。In addition, after adjusting the brightness and saturation of the second image and obtaining the processed result image, the method further includes: performing color component analysis on the background area of the to-be-processed image to determine the overflow suppression estimated value; The target image is obtained by linearly fusing the to-be-processed image and the result image according to the overflow suppression estimation value. Considering that the background color often changes due to different lighting materials in the actual scene, the existing G channel overflow suppression method does not analyze the real background color components, and it is easy to deduce that the overflow suppression is insufficient or excessive. The embodiment of the present invention determines the overflow suppression estimated value by performing color component analysis on the background area of the image to be processed, and performs linear fusion of the to-be-processed image and the result image according to the overflow suppression estimated value to obtain the target image, which is beneficial to avoid insufficient or excessive overflow suppression. Thereby, the background color component reflected in the overflow area can be suppressed more precisely.
另外，所述对所述待处理图像的背景区域进行色彩成分分析，确定溢出抑制估计值，包括：获取所述待处理图像中的背景区域的像素在HSL色彩空间下各分量值的平均值；其中，所述各分量值的平均值包括H分量值的平均值、S分量值的平均值和L分量值的平均值；根据所述HSL色彩空间下各分量值的平均值，计算所述溢出抑制估计值。提供了一种确定溢出抑制估计值的实现方式，通过获取待处理图像中的背景区域的像素的在HSL色彩空间下各分量值的平均值，有利于准确的对待处理图像的背景区域进行色彩成分分析，根据HSL色彩空间下各分量值的平均值，有利于合理的计算溢出抑制估计值。In addition, the performing color component analysis on the background area of the image to be processed to determine the overflow suppression estimated value includes: acquiring the average value of each component value of the pixels of the background area in the image to be processed in the HSL color space; Wherein, the average value of each component value includes the average value of H component value, the average value of S component value and the average value of L component value; the overflow is calculated according to the average value of each component value in the HSL color space Suppress the estimate. Provided is an implementation method for determining an estimated value of overflow suppression. By obtaining the average value of each component value in the HSL color space of the pixels of the background area in the image to be processed, it is beneficial to accurately determine the color components of the background area of the image to be processed. Analysis, according to the average value of each component value in the HSL color space, is conducive to a reasonable calculation of the overflow suppression estimate.
附图说明Description of drawings
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定。One or more embodiments are exemplified by the pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments.
图1是根据本发明第一实施方式中的图像处理方法的流程图；1 is a flowchart of an image processing method according to a first embodiment of the present invention;
图2是根据本发明第一实施方式中的像素的置信度与该像素的H分量值所处的区间之间的关系示意图；2 is a schematic diagram of the relationship between the confidence level of a pixel and the interval in which the H component value of the pixel is located according to the first embodiment of the present invention;
图3是根据本发明第二实施方式中的图像处理方法的流程图；3 is a flowchart of an image processing method according to a second embodiment of the present invention;
图4是根据本发明第三实施方式中的电子设备的结构示意图。FIG. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合附图对本发明的各实施方式进行详细的阐述。然而，本领域的普通技术人员可以理解，在本发明各实施方式中，为了使读者更好地理解本申请而提出了许多技术细节。但是，即使没有这些技术细节和基于以下各实施方式的种种变化和修改，也可以实现本申请所要求保护的技术方案。以下各个实施例的划分是为了描述方便，不应对本发明的具体实现方式构成任何限定，各个实施例在不矛盾的前提下可以相互结合相互引用。In order to make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those of ordinary skill in the art can appreciate that, in the various embodiments of the present invention, many technical details are set forth in order for the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be realized. The following divisions of the various embodiments are for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention, and the various embodiments may be combined with each other and referred to each other on the premise of not contradicting each other.
本发明的第一实施方式涉及一种图像处理方法。下面对本实施方式的实现细节进行具体的说明，以下内容仅为方便理解提供的实现细节，并非实施本方案的必须。本实施方式中的图像处理方法的流程图，如图1所示，具体包括：A first embodiment of the present invention relates to an image processing method. The implementation details of this embodiment will be specifically described below, and the following contents are only provided for the convenience of understanding, and are not necessary for implementing this solution. The flowchart of the image processing method in this embodiment, as shown in FIG. 1 , specifically includes:
步骤101：确定待处理图像中的溢色区域，并确定溢色区域中的像素为预设色相的置信度。Step 101: Determine the overflow area in the to-be-processed image, and determine the confidence level that the pixels in the overflow area are preset hues.
其中，预设色相为待处理图像中的背景色的色相，即待处理图像中的背景幕布的颜色的色相。比如，在具体实现中，若背景幕布为绿色幕布，则预设色相为绿色的色相，若背景幕布为蓝色幕布，则预设色相为蓝色的色相。The preset hue is the hue of the background color in the image to be processed, that is, the hue of the color of the background curtain in the image to be processed. For example, in a specific implementation, if the background curtain is a green curtain, the preset hue is a green hue, and if the background curtain is a blue curtain, the preset hue is a blue hue.
在一个例子中，确定待处理图像中的溢色区域的方式可以为：根据色相环确定预设色相关联的工作区间，获取待处理图像中的像素的色相，根据待处理图像中的像素的色相是否处于预设色相关联的工作区间，确定待处理图像中的溢色区域。比如，若像素的色相处于预设色相关联的工作区间，则该像素所在区域为溢色区域，否则为非溢色区域。以背景幕布为绿色幕布为例，根据色相环确定的绿色的色相关联的工作区间可以为[75°，165°]，在该工作区间内包括偏绿和绿对应的色相值，偏绿可以包括青绿、黄绿等。其中，绿对应的色相值的区间为[105°，135°]，其余为偏绿对应的色相值的区间。在具体实现中，绿色的色相关联的工作区间也可以表示为[75°，105°，135°，165°]。In an example, the method of determining the overflow area in the image to be processed may be: determining a working area associated with a preset color according to the hue circle, acquiring the hue of the pixel in the image to be processed, and obtaining the hue of the pixel in the image to be processed according to the Whether the hue is in the working range associated with the preset color determines the overflow area in the image to be processed. For example, if the hue of the pixel is in the working range associated with the preset color, the area where the pixel is located is an overflow area; otherwise, it is a non-spill area. Taking the background curtain as a green curtain as an example, the working range associated with the green color determined according to the hue circle can be [75°, 165°], and the working range includes the hue values corresponding to green and green. Including blue-green, yellow-green, etc. Among them, the interval of hue value corresponding to green is [105°, 135°], and the rest are the interval of hue value corresponding to greenish. In a specific implementation, the working interval associated with the green color can also be expressed as [75°, 105°, 135°, 165°].
在一个例子中，确定溢色区域中的像素为预设色相的置信度的方式可以为：首先，将待处理图像的像素的RGB分量值转换为HSL分量值；也就是对待处理图像进行HSL色彩空间转换得到待处理图像的像素的HSL分量值，由于RGB分量值与HSL分量值之间的转换属于现有技术，本实施方式对此不作展开描述。然后，根据溢色区域中的像素的HSL分量值和预设色相关联的工作区间，计算溢色区域中的像素为预设色相的置信度。其中，一个像素的置信度可以表征该像素与背景色的色相的接近程度，置信度的大小所在的区间为[0，1]。置信度为0表明该像素与背景色的色相毫无关联；置信度为1表明该像素与背景色的色相相同；置信度为(0，1)表明该像素与背景色的色相有关联但不相同，该像素与背景色的色相的越接近，置信度越大。可以理解的是，溢色区域中的像素的置信度的取值范围为(0，1]，溢色区域中的像素的置信度为0。比如，以背景幕布为绿色幕布为例，绿色的色相关联的工作区间可以为[75°，165°]，若像素的色相处于绿色的色相在[105°，135°]之间，则该像素的置信度为1。若像素的色相不在[75°，165°]之间，则该像素的置信度为0。若像素的色相在[75°，105°)或是(135°，165°]，则可以根据像素的色相与绿色的色相的接近程度，确定置信度。In one example, the method of determining the confidence that the pixels in the overflow area are preset hues may be: first, convert the RGB component values of the pixels of the image to be processed into HSL component values; The HSL component values of the pixels of the image to be processed are obtained by spatial conversion. Since the conversion between the RGB component values and the HSL component values belongs to the prior art, this embodiment will not describe this in detail. Then, according to the HSL component value of the pixel in the overflow area and the working interval associated with the preset color, the confidence level that the pixel in the overflow area is the preset hue is calculated. Among them, the confidence of a pixel can represent the closeness of the pixel to the hue of the background color, and the interval of the confidence is [0, 1]. A confidence level of 0 indicates that the pixel has nothing to do with the hue of the background color; a confidence level of 1 indicates that the pixel has the same hue as the background color; a confidence level of (0, 1) indicates that the pixel is associated with the hue of the background color but not. Similarly, the closer the hue of the pixel is to the background color, the greater the confidence. It can be understood that the value range of the confidence level of the pixels in the overflow area is (0, 1], and the confidence level of the pixels in the overflow area is 0. For example, taking the background curtain as a green curtain as an example, the green The working interval associated with color can be [75°, 165°], if the hue of the pixel is between [105°, 135°], the hue of the pixel is between [105°, 135°], then the confidence of the pixel is 1. If the hue of the pixel is not in [ 75°, 165°], the confidence of the pixel is 0. If the hue of the pixel is in [75°, 105°) or (135°, 165°], then the hue of the pixel can be compared with the hue of green according to the hue of the pixel. closeness to determine confidence.
在一个例子中，可以通过以下公式计算溢色区域中的像素为预设色相的置信度：In one example, the confidence that the pixels in the overflow area are of the preset hue can be calculated by the following formula:
其中，所述C为计算的置信度，所述H为像素的色相分量值，所述Lo，Li，Ro，Ri，分别为所述工作区间在色相环上的头端渐变开始值，头端渐变结束值，尾端渐变开始值，尾端渐变结束值。预设色相以绿色的色相为例，绿色的色相关联的工作区间可以表示为[75°，105°，135°，165°]。为便于理解，可以参考图2，图2展示了像素的置信度与该像素的H分量值所处的区间之间的关系。可以理解的是，溢色区域中的每一个像素均可以对应一个置信度。Wherein, the C is the calculated confidence, the H is the hue component value of the pixel, and the Lo , Li , Ro , and Ri are respectively the beginning of the gradient at the beginning of the working interval on the hue circle. value, the end value of the head end gradient, the start value of the end end gradient, and the end value of the end end gradient. The preset hue takes the hue of green as an example, and the working range associated with the green hue can be expressed as [75°, 105°, 135°, 165°]. For ease of understanding, reference may be made to FIG. 2 , which shows the relationship between the confidence of a pixel and the interval in which the value of the H component of the pixel is located. It can be understood that each pixel in the overflow area may correspond to a confidence level.
步骤102：去除待处理图像中的背景色得到第一图像。Step 102: Remove the background color in the image to be processed to obtain a first image.
比如说，待处理图像中的背景色为绿色幕布的颜色，则可以对除待处理图像的G通道进行0值填充，从而去除待处理图像中的绿色成分。再比如说，待处理图像中的背景色为蓝色幕布的颜色，则可以对除待处理图像的B通道进行0值填充，从而去除待处理图像中的蓝色成分。其中，第一图像可以为基于HSL色彩空间的图像。For example, if the background color in the image to be processed is the color of the green curtain, then the G channel other than the image to be processed can be filled with 0 value, thereby removing the green component in the image to be processed. For another example, if the background color in the to-be-processed image is the color of the blue curtain, the B channel except the to-be-processed image can be filled with 0 value, thereby removing the blue component in the to-be-processed image. The first image may be an image based on the HSL color space.
在一个例子中，待处理图像中的背景色为绿色幕布的颜色，可以先对待处理图像中的G通道进行0值填充，然后再对进行0值填充后的图像进行HSL色彩空间转换得到第一图像。In an example, the background color in the image to be processed is the color of the green curtain, the G channel in the image to be processed can be filled with 0 value first, and then the image after 0 value filling can be converted to HSL color space to obtain the first color space. image.
步骤103：根据置信度对第一图像和待处理图像进行线性混合，获取第二图像。Step 103: Linearly mix the first image and the to-be-processed image according to the confidence level to obtain a second image.
具体的说，可以根据溢色区域中的像素的置信度对第一图像中的像素值和待处理图像中的像素值进行线性混合，获取第二图像。可以理解的是，第一图像和待处理图像中各个像素的位置是相同的，因此可以获取第一图像的预设区域，该预设区域在第一图像中的相对位置与溢色区域在待处理图像中的相对位置相同。根据溢色区域中的像素的置信度，对第一图像中预设区域内的像素的像素值和待处理图像中溢色区域内的像素的像素值进行线性混合，得到第二图像。Specifically, the pixel values in the first image and the pixel values in the to-be-processed image may be linearly mixed according to the confidence of the pixels in the overflow area to obtain the second image. It can be understood that the positions of each pixel in the first image and the image to be processed are the same, so a preset area of the first image can be obtained, and the relative position of the preset area in the first image and the overflow area are different. The relative position in the processed image is the same. According to the confidence of the pixels in the overflow area, the pixel values of the pixels in the preset area in the first image and the pixel values of the pixels in the overflow area in the image to be processed are linearly mixed to obtain the second image.
在一个例子中，可以先对第一图像的色相和饱和度进行调整，得到第一调整图像。比如，可以分别获取第一图像的当前色相值和当前饱和度值，将第一图像的当前色相值减去预设色相值作为目标色相值，将当前饱和度值减去预设饱和度值作为目标饱和度值。然后将第一图像的色相和饱和度分别调整为上述的目标色相值和目标饱和度值，得到第一调整图像。其中，预设色相值和预设饱和度值可以根据实际需要进行设置，比如本实施方式中预设色相值可以设置为24°±10°，预设饱和度值可以设置为-30±10，然而在具体实现中并不以此为限。得到第一调整图像后，可以根据置信度通过以下公式对第一调整图像和待处理图像进行线性混合，获取第二图像：In one example, the hue and saturation of the first image may be adjusted first to obtain the first adjusted image. For example, the current hue value and the current saturation value of the first image may be obtained respectively, the current hue value of the first image minus the preset hue value may be used as the target hue value, and the current saturation value minus the preset saturation value may be used as the target hue value. Target saturation value. Then, the hue and saturation of the first image are adjusted to the above target hue value and target saturation value, respectively, to obtain a first adjusted image. The preset hue value and preset saturation value can be set according to actual needs. For example, in this embodiment, the preset hue value can be set to 24°±10°, and the preset saturation value can be set to -30±10. However, the specific implementation is not limited to this. After the first adjusted image is obtained, the first adjusted image and the to-be-processed image can be linearly mixed by the following formula according to the confidence to obtain the second image:
I2＝(1.0-C)*I+C*(I1_0)I2=(1.0-C)*I+C*(I1_0)
其中，I2为第二图像的像素值，C为置信度，I为待处理图像的像素值，I1_0为第一调整图像的像素值。线性混合可以理解为根据溢色区域中的像素的置信度，对待处理图像中的像素的像素值与第一调整图像中预设区域内的像素的像素值进行线性混合；其中，预设区域在第一调整图像中的相对位置与溢色区域在待处理图像中的相对位置相同。也就是说，本实施方式中只对待处理图像中的溢色区域的像素的像素值进行调整。Wherein, I2 is the pixel value of the second image, C is the confidence level, I is the pixel value of the image to be processed, and I1_0 is the pixel value of the first adjusted image. Linear mixing can be understood as linearly mixing the pixel value of the pixel in the image to be processed and the pixel value of the pixel in the preset area in the first adjustment image according to the confidence of the pixels in the overflow area; The relative position in the first adjusted image is the same as the relative position of the spill area in the image to be processed. That is to say, in this embodiment, only the pixel values of the pixels in the overflow area in the image to be processed are adjusted.
步骤104：对第二图像的亮度和饱和度进行修正，获取处理后的结果图像。Step 104: Correct the brightness and saturation of the second image, and obtain a processed result image.
在一个例子中，可以根据亮度和饱和度的经验值对第二图像的亮度和饱和度进行修正，获取处理后的结果图像。In one example, the brightness and saturation of the second image may be corrected according to the empirical values of brightness and saturation, to obtain a processed result image.
在另一个例子中，对第二图像的亮度和饱和度进行修正，获取处理后的结果图像的方式可以如下：In another example, the brightness and saturation of the second image are corrected, and the manner of obtaining the processed result image may be as follows:
首先，将预设的基于HSL色彩空间的背景色混合因子转换为基于RGB色彩空间的背景色混合因子；其中，基于HSL色彩空间的背景色混合因子包括：色相估计值H、亮度估计值L和饱和度估计值S，背景色混合因子可以表示为(H，S，L)。其中，亮度估计值L和饱和度估计值S可以根据实际需要进行设置，本实施方式中亮度估计值L可以设置为50±10，饱和度估计值S可以设置为50±10，然而在具体实现中并不以此为限。对基于HSL色彩空间的背景色混合因子(H，S，L)进行RGB色彩空间转换得到基于RGB色彩空间的背景色混合因子(Rb,Gb,Bb)。另外，由于HSL色彩空间与RGB色彩空间之间的转换为现有技术，因此，本实施方式对具体的转换过程不作具体描述。First, the preset background color mixing factor based on HSL color space is converted into a background color mixing factor based on RGB color space; wherein, the background color mixing factor based on HSL color space includes: hue estimated value H, luminance estimated value L and The saturation estimation value S, the background color mixing factor can be expressed as (H, S, L). The estimated brightness value L and the estimated value of saturation S can be set according to actual needs. In this embodiment, the estimated value of brightness L can be set to 50±10, and the estimated value of saturation S can be set to 50±10. However, in the specific implementation is not limited to this. Convert the background color mixing factors (H, S, L) based on HSL color space to RGB color space to obtain background color mixing factors (Rb , Gb , Bb ) based on RGB color space. In addition, since the conversion between the HSL color space and the RGB color space is in the prior art, the specific conversion process is not described in this embodiment.
在一个例子中，背景色混合因子(H，S，L)中的色相估计值H可以采用经验值，比如绿色幕布背景下，色相估计值H可以采用绿色的色相值，比如120°。In one example, the estimated hue value H in the background color mixing factor (H, S, L) may be an empirical value, for example, under a green curtain background, the estimated hue value H may be a green hue value, such as 120°.
在另一个例子中，背景色混合因子(H，S，L)中的色相估计值的获取方式如下：获取待处理图像中的背景区域的像素在HSL色彩空间下H分量值的平均值；将H分量值的平均值作为所述色相估计值。比如，可以先基于现有的分割技术进行前后景的分割，得到前景蒙版图像M，前后景的分割可采用传统的抠图技术，如：shared-matting，close-form matting等方法实现。然后，根据待处理图像和前景蒙版图像，对背景区域进行色彩成分分析，得到RGB色彩空间下背景区域的像素的RGB分量值的平均值，再将RGB分量值的平均值转换为在HSL色彩空间下的HSL分量值的平均值，然后将H分量值的平均值作为背景色混合因子(H，S，L)中的色相估计值。另外，在根据待处理图像和前景蒙版图像，对背景区域进行色彩成分分析时，可以先对待处理图像和前景蒙版图像进行下采样，得到具有预设分辨率的待处理图像和前景蒙版图像，然后根据具有预设分辨率的待处理图像和前景蒙版图像对背景区域进行色彩成分分析，从而获取待处理图像中的背景区域的像素在HSL色彩空间下H分量值的平均值。其中，下采样可以理解为对图像进行等比例缩小，预设分辨率可以较小，比如图像的较长边不超过320像素。先对待处理图像和前景蒙版图像进行下采样，有利于缩短执行时间。In another example, the acquisition method of the hue estimation value in the background color mixing factor (H, S, L) is as follows: acquiring the average value of the H component value of the pixels in the background area in the image to be processed in the HSL color space; The average value of the H component values serves as the hue estimation value. For example, the foreground and background images can be segmented based on the existing segmentation technology, and the foreground mask image M can be obtained. Then, according to the image to be processed and the foreground mask image, analyze the color components of the background area to obtain the average value of the RGB component values of the pixels in the background area in the RGB color space, and then convert the average value of the RGB component values to the HSL color. The average value of the HSL component values in the space, and then the average value of the H component values is used as the hue estimate value in the background color mixing factor (H, S, L). In addition, when performing color component analysis on the background area according to the image to be processed and the foreground mask image, the to-be-processed image and the foreground mask image can be down-sampled first to obtain the to-be-processed image and the foreground mask with a preset resolution image, and then perform color component analysis on the background area according to the to-be-processed image and the foreground mask image with a preset resolution, so as to obtain the average value of the H-component values of the pixels in the background area in the to-be-processed image in the HSL color space. The downsampling can be understood as scaling down the image in equal proportions, and the preset resolution can be smaller, for example, the longer side of the image does not exceed 320 pixels. Downsampling the to-be-processed image and the foreground mask image first is beneficial to shorten the execution time.
接着，获取基于RGB色彩空间的背景色混合因子的亮度和饱和度。比如，可以通过以下公式获取基于RGB色彩空间的背景色混合因子的亮度值L和饱和度值S：Next, obtain the brightness and saturation of the background color mixing factor based on the RGB color space. For example, the luminance value L and saturation value S of the background color mixing factor based on the RGB color space can be obtained by the following formulas:
L＝aRb+bGb+cBbL=aRb +bGb +cBb
S＝max(Rb,Gb,Bb)-min(Rb,Gb,Bb)S=max(Rb ,Gb ,Bb )-min(Rb ,Gb ,Bb )
其中，a+b+c＝1，a、b、c的具体取值可以根据实际需要进行设置，在一个例子中a、b、c的取值可以如下：a＝0.3,b＝0.59,c＝0.11，然而在具体实现中并不以此为限。Among them, a+b+c=1, the specific values of a, b, and c can be set according to actual needs. In an example, the values of a, b, and c can be as follows: a=0.3, b=0.59, c =0.11, however, it is not limited in the specific implementation.
然后，根据获取的亮度值和饱和度值分别对第二图像的亮度和饱和度进行修正，获取获取处理后的结果图像。比如，将第二图像的亮度和饱和度分别修正为获取的亮度值L和饱和度值S。Then, the brightness and saturation of the second image are respectively corrected according to the acquired brightness value and saturation value, and a result image after the acquisition and processing is acquired. For example, the brightness and saturation of the second image are corrected to the obtained brightness value L and saturation value S, respectively.
需要说明的是，本实施方式中的上述各示例均为为方便理解进行的举例说明，并不对本发明的技术方案构成限定。It should be noted that, the above examples in this embodiment are all examples for the convenience of understanding, and do not limit the technical solutions of the present invention.
与现有技术相比，本实施方式确定待处理图像中的溢色区域，即对待处理图像中的溢色区域和非溢色区域进行了区分。通过确定待处理图像中的溢色区域中的像素为预设色相的置信度，其中预设色相为待处理图像中的背景色的色相，使得可以通过溢色区域中的像素的置信度得出该像素与背景色的色相的接近程度。通过去除待处理图像中的背景色得到第一图像，使得第一图像中的背景色成分可以大幅度降低。根据置信度对第一图像和待处理图像进行线性混合，获取第二图像，即结合溢色区域中的像素的色相与背景色的色相的接近程度，对去除背景色的第一图像和待处理图像即原始图像进行线性混合得到第二图像，使得在一定程度上第二图像相比于原始图像溢色区域反射的背景色成分可以被抑制。另外，由于去除待处理图像中的背景色会在一定程度上影响亮度和饱和度，因此，对第二图像的亮度和饱和度进行修正，获取处理后的结果图像，使得处理后的结果图像可以将因去除背景色影响的亮度和饱和度还原，从而可以在抑制溢色区域反射的背景色成分的同时不影响一些非溢色区域的颜色。Compared with the prior art, this embodiment determines the overflow area in the image to be processed, that is, distinguishes the overflow area and the non-overflow area in the image to be processed. By determining the confidence that the pixels in the overflow area in the image to be processed are the preset hue, where the preset hue is the hue of the background color in the image to be processed, it can be obtained from the confidence of the pixels in the overflow area. How close this pixel is to the hue of the background color. The first image is obtained by removing the background color in the image to be processed, so that the background color component in the first image can be greatly reduced. Linearly mix the first image and the to-be-processed image according to the confidence level, and obtain a second image, that is, combine the degree of closeness between the hue of the pixels in the overflow area and the hue of the background color, and compare the first image with the background color removed and the to-be-processed image. The image, that is, the original image, is linearly mixed to obtain the second image, so that the background color component reflected by the second image compared with the color overflow area of the original image can be suppressed to a certain extent. In addition, since removing the background color in the image to be processed will affect the brightness and saturation to a certain extent, the brightness and saturation of the second image are corrected, and the processed result image is obtained, so that the processed result image can be Restore the brightness and saturation affected by the removal of the background color, so that the background color components reflected in the overflow area can be suppressed without affecting the color of some non-spill areas.
本发明的第二实施方式涉及一种图像处理方法。第二实施方式是对第一实施方式的进一步改进，本实施方式在得到结果图像后，还会对结果图像进行进一步处理得到目标图像，使得可以避免溢出抑制不足或过度抑制，从而更精确的抑制溢色区域反射的背景色成分。下面对本实施方式的实现细节进行具体的说明，以下内容仅为方便理解提供的实现细节，并非实施本方案的必须。本实施方式中的图像处理方法的流程图，如图2所示，具体包括：A second embodiment of the present invention relates to an image processing method. The second embodiment is a further improvement of the first embodiment. After the result image is obtained in this embodiment, the result image will be further processed to obtain the target image, so that insufficient or excessive suppression of overflow can be avoided, so that more accurate suppression can be achieved. The background color component of the spill area reflection. The implementation details of this embodiment will be specifically described below, and the following contents are only provided for the convenience of understanding, and are not necessary for implementing this solution. The flowchart of the image processing method in this embodiment, as shown in FIG. 2 , specifically includes:
步骤201：确定待处理图像中的溢色区域，并确定溢色区域中的像素为预设色相的置信度。Step 201: Determine the overflow area in the image to be processed, and determine the confidence level that the pixels in the overflow area are preset hues.
步骤202：去除待处理图像中的背景色得到第一图像。Step 202: Remove the background color in the image to be processed to obtain a first image.
步骤203：根据置信度对第一图像和待处理图像进行线性混合，获取第二图像。Step 203: Linearly mix the first image and the to-be-processed image according to the confidence level to obtain a second image.
步骤204：对第二图像的亮度和饱和度进行修正，获取处理后的结果图像。Step 204: Correct the brightness and saturation of the second image, and obtain a processed result image.
其中，步骤201至步骤204与第一实施方式中步骤101至步骤104大致相同，为避免重复在此不再一一赘述。Wherein,
步骤205：对待处理图像的背景区域进行色彩成分分析，确定溢出抑制估计值。Step 205: Perform color component analysis on the background area of the image to be processed to determine the overflow suppression estimated value.
具体的说，可以先获取待处理图像中的背景区域的像素的在HSL色彩空间下各分量值的平均值；其中，各分量值的平均值包括H分量值的平均值、S分量值的平均值和L分量值的平均值。然后根据HSL色彩空间下各分量值的平均值，计算溢出抑制估计值。Specifically, the average value of each component value in the HSL color space of the pixels in the background area in the image to be processed may be obtained first; wherein, the average value of each component value includes the average value of the H component value and the average value of the S component value. value and the average of the L component values. The overflow suppression estimate is then calculated based on the average value of each component value in the HSL color space.
在一个例子中，获取待处理图像中的背景区域的像素的在HSL色彩空间下各分量值的平均值的方式可以如下：获取待处理图像对应的前景蒙版图像，根据待处理图像和前景蒙版图像，在RGB色彩空间下进行背景区域的颜色统计得到背景区域的背景平均色
在一个例子中，根据HSL色彩空间下各分量值的平均值，计算溢出抑制估计值的方式可以为：通过如下公式计算溢出抑制估计值：In an example, according to the average value of each component value in the HSL color space, the method of calculating the overflow suppression estimated value may be: calculate the overflow suppression estimated value by the following formula:
其中，α为计算的溢出抑制估计值，
步骤206：根据溢出抑制估计值对待处理图像和结果图像进行线性融合，得到目标图像。Step 206: Perform linear fusion of the to-be-processed image and the result image according to the overflow suppression estimation value to obtain a target image.
具体的说，可以根据溢出抑制估计值对第一图像中的像素值和待处理图像中的像素值进行线性混合，获取目标图像。在具体实现中，可以对待处理图像、结果图像和溢出抑制估计值α，使用alpha融合方法，完成溢出抑制的自适应调整，并得目标图像。比如，可以根据如下公式进行线性融合：Specifically, the pixel value in the first image and the pixel value in the to-be-processed image can be linearly mixed according to the overflow suppression estimation value to obtain the target image. In the specific implementation, the image to be processed, the result image and the estimated value α of overflow suppression can be used to complete the adaptive adjustment of the overflow suppression by using the alpha fusion method, and the target image can be obtained. For example, linear fusion can be performed according to the following formula:
I4＝(1-α)I+αI3I4 =(1-α)I+αI3
其中，I4为目标图像的像素值、I为待处理图像的像素值、I3为结果图像的像素值，α为溢出抑制估计值。线性混合可以理解为对待处理图像和结果图像中处于相同位置的像素的像素值进行线性混合。Among them,I4 is the pixel value of the target image, I is the pixel value of the image to be processed,I3 is the pixel value of the result image, and α is the overflow suppression estimated value. Linear blending can be understood as a linear blending of pixel values of pixels in the same position in the image to be processed and the resulting image.
与现有技术相比，本实施方式中，考虑到实际场景中由于灯光材质不同背景色往往会发生变化，现有G通道溢出抑制方法未分析真实的背景色成分，容易导出溢出抑制不足或过度抑制。本发明实施方式通过对待处理图像的背景区域进行色彩成分分析确定溢出抑制估计值，根据溢出抑制估计值对待处理图像和结果图像进行线性融合，得到目标图像，有利于避免溢出抑制不足或过度抑制，从而更精确的抑制溢色区域反射的背景色成分。Compared with the prior art, in this embodiment, considering that the background color often changes due to different lighting materials in the actual scene, the existing G channel overflow suppression method does not analyze the real background color components, and it is easy to deduce that the overflow suppression is insufficient or excessive. inhibition. The embodiment of the present invention determines the overflow suppression estimated value by performing color component analysis on the background area of the image to be processed, and performs linear fusion of the to-be-processed image and the result image according to the overflow suppression estimated value to obtain the target image, which is beneficial to avoid insufficient or excessive overflow suppression. Thereby, the background color component reflected in the overflow area can be suppressed more precisely.
上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对算法中或者流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其算法和流程的核心设计都在该专利的保护范围内。The steps of the above various methods are divided only for the purpose of describing clearly. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as the same logical relationship is included, they are all within the protection scope of this patent. ;Adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of the algorithm and process are all within the scope of protection of this patent.
本发明第三实施方式涉及一种电子设备，如图3所示，包括至少一个处理器301；以及，与至少一个处理器301通信连接的存储器302；其中，存储器302存储有可被至少一个处理器301执行的指令，指令被至少一个处理器301执行，以使至少一个处理器301能够执行第一、或第二实施方式中的图像处理方法。The third embodiment of the present invention relates to an electronic device, as shown in FIG. 3 , comprising at least one
其中，存储器302和处理器301采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器301和存储器302的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器301处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器301。The
处理器301负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器302可以被用于存储处理器301在执行操作时所使用的数据。
本发明第四实施方式涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现上述方法实施例。A fourth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The above method embodiments are implemented when the computer program is executed by the processor.
即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。That is, those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device ( It may be a single chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.
本领域的普通技术人员可以理解，上述各实施方式是实现本发明的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本发明的精神和范围。Those skilled in the art can understand that the above-mentioned embodiments are specific examples for realizing the present invention, and in practical applications, various changes in form and details can be made without departing from the spirit and the spirit of the present invention. scope.
Claims (10)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265232.5ACN111524076B (en) | 2020-04-07 | 2020-04-07 | Image processing method, electronic device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265232.5ACN111524076B (en) | 2020-04-07 | 2020-04-07 | Image processing method, electronic device and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111524076Atrue CN111524076A (en) | 2020-08-11 |
| CN111524076B CN111524076B (en) | 2023-07-21 |
Family
ID=71901261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010265232.5AActiveCN111524076B (en) | 2020-04-07 | 2020-04-07 | Image processing method, electronic device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111524076B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487497A (en)* | 2021-06-18 | 2021-10-08 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
| CN113763496A (en)* | 2021-03-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Image coloring method, device and computer readable storage medium |
| CN114549372A (en)* | 2020-11-24 | 2022-05-27 | 浙江宇视科技有限公司 | Vehicle window image antireflection method, device, electronic device and storage medium |
| CN116546177A (en)* | 2023-05-17 | 2023-08-04 | 深圳市迈拓斯电子信息科技有限责任公司 | Method, system, terminal and storage medium for suppressing color in chroma keying |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH103549A (en)* | 1996-06-17 | 1998-01-06 | Hitachi Ltd | Pronunciation body identification support device |
| US6122441A (en)* | 1994-03-31 | 2000-09-19 | Canon Kabushiki Kaisha | Image processing apparatus and method |
| US20040041820A1 (en)* | 2002-08-30 | 2004-03-04 | Benoit Sevigny | Image processing |
| JP2004248020A (en)* | 2003-02-14 | 2004-09-02 | Fuji Photo Film Co Ltd | Image processor and image processing system |
| CN102005060A (en)* | 2010-12-08 | 2011-04-06 | 上海杰图软件技术有限公司 | Method and device for automatically removing selected images in pictures |
| CN102075666A (en)* | 2009-11-25 | 2011-05-25 | 惠普开发有限公司 | Method and device used for removing background colors from image |
| AU2012203836A1 (en)* | 2011-07-05 | 2013-01-24 | Jostens, Inc | System and method for yearbook creation |
| CN103177446A (en)* | 2013-03-13 | 2013-06-26 | 北京航空航天大学 | Image foreground matting method based on neighbourhood and non-neighbourhood smoothness prior |
| CN103581571A (en)* | 2013-11-22 | 2014-02-12 | 北京中科大洋科技发展股份有限公司 | Video image matting method based on three elements of color |
| CN105678724A (en)* | 2015-12-29 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Background replacing method and apparatus for images |
| CN107087123A (en)* | 2017-04-26 | 2017-08-22 | 杭州奥点科技股份有限公司 | It is a kind of that image space method is scratched based on the real-time high-definition that high in the clouds is handled |
| CN110210532A (en)* | 2019-05-15 | 2019-09-06 | 北京字节跳动网络技术有限公司 | Background colour generation method, device and electronic equipment |
| CN110703976A (en)* | 2019-08-28 | 2020-01-17 | 咪咕文化科技有限公司 | Clipping method, electronic device, and computer-readable storage medium |
- 2020
- 2020-04-07CNCN202010265232.5Apatent/CN111524076B/enactiveActive
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6122441A (en)* | 1994-03-31 | 2000-09-19 | Canon Kabushiki Kaisha | Image processing apparatus and method |
| JPH103549A (en)* | 1996-06-17 | 1998-01-06 | Hitachi Ltd | Pronunciation body identification support device |
| US20040041820A1 (en)* | 2002-08-30 | 2004-03-04 | Benoit Sevigny | Image processing |
| JP2004248020A (en)* | 2003-02-14 | 2004-09-02 | Fuji Photo Film Co Ltd | Image processor and image processing system |
| CN102075666A (en)* | 2009-11-25 | 2011-05-25 | 惠普开发有限公司 | Method and device used for removing background colors from image |
| CN102005060A (en)* | 2010-12-08 | 2011-04-06 | 上海杰图软件技术有限公司 | Method and device for automatically removing selected images in pictures |
| AU2012203836A1 (en)* | 2011-07-05 | 2013-01-24 | Jostens, Inc | System and method for yearbook creation |
| CN103177446A (en)* | 2013-03-13 | 2013-06-26 | 北京航空航天大学 | Image foreground matting method based on neighbourhood and non-neighbourhood smoothness prior |
| CN103581571A (en)* | 2013-11-22 | 2014-02-12 | 北京中科大洋科技发展股份有限公司 | Video image matting method based on three elements of color |
| CN105678724A (en)* | 2015-12-29 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Background replacing method and apparatus for images |
| CN107087123A (en)* | 2017-04-26 | 2017-08-22 | 杭州奥点科技股份有限公司 | It is a kind of that image space method is scratched based on the real-time high-definition that high in the clouds is handled |
| CN110210532A (en)* | 2019-05-15 | 2019-09-06 | 北京字节跳动网络技术有限公司 | Background colour generation method, device and electronic equipment |
| CN110703976A (en)* | 2019-08-28 | 2020-01-17 | 咪咕文化科技有限公司 | Clipping method, electronic device, and computer-readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 李娜等: "基于采样抠图和自适应颜色的图像合成算法", 《液晶与显示》* |
| 李闻等: "一种融合图像合成的抠图算法", 《计算机应用研究》* |
| 王春艳等: "Dirac Quasinormal Modes of Reissner-Nodstrom Black Hole Surrounded by Quintessence", 《COMMUNICATIONS IN THEORETICAL PHYSICS》* |
| 白宇: "对演播室图像质量的新认知――通过各工种合作呈现电视图像的高质量和艺术性", 《现代电视技术》* |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549372A (en)* | 2020-11-24 | 2022-05-27 | 浙江宇视科技有限公司 | Vehicle window image antireflection method, device, electronic device and storage medium |
| CN113763496A (en)* | 2021-03-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Image coloring method, device and computer readable storage medium |
| CN113763496B (en)* | 2021-03-19 | 2024-04-09 | 北京沃东天骏信息技术有限公司 | Method, apparatus and computer readable storage medium for image coloring |
| CN113487497A (en)* | 2021-06-18 | 2021-10-08 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
| CN116546177A (en)* | 2023-05-17 | 2023-08-04 | 深圳市迈拓斯电子信息科技有限责任公司 | Method, system, terminal and storage medium for suppressing color in chroma keying |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111524076B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111524076A (en) | Image processing method, electronic device, and computer-readable storage medium | |
| CN112752023B (en) | Image adjusting method and device, electronic equipment and storage medium | |
| US8290259B2 (en) | Device adaptively switching color emphasis processing for image | |
| CN109977949B (en) | Frame fine adjustment text positioning method and device, computer equipment and storage medium | |
| CN111861922A (en) | Method and device for adjusting color correction matrix and storage medium | |
| CN113573032B (en) | Image processing method and projection system | |
| CN106485720A (en) | Image processing method and device | |
| JP2009290661A (en) | Image processing apparatus, image processing method, image processing program and printer | |
| JP2003069846A (en) | Image processing program | |
| CN110392243B (en) | Method and apparatus for gamut mapping | |
| WO2021088639A1 (en) | Image brightness processing method and apparatus, and image processing method and apparatus | |
| JP2008306377A (en) | Color adjusting device, and color adjusting program | |
| KR20180021721A (en) | Color gamut mapping using brightness mapping based also on the brightness of the cusp color belonging to different constant- | |
| CN113592739B (en) | Lens shading correction method, device and storage medium | |
| WO2020093653A1 (en) | Color adjustment method, color adjustment device, electronic device and computer-readable storage medium | |
| CN116228563A (en) | Image defogging correction method and device based on dark channel | |
| JP2002271808A (en) | Program for correcting red-eye in picture, recording medium and red-eye correcting method | |
| WO2020037635A1 (en) | Color correction method and apparatus | |
| CN103761714A (en) | Color image enhancement method based on HIS color space | |
| CN110782400B (en) | Self-adaptive illumination uniformity realization method and device | |
| CN113409196B (en) | High-speed global chromatic aberration correction method for real-time video splicing | |
| KR20070090224A (en) | How to Process Electronic Color Image Saturation | |
| JP4862554B2 (en) | Image processing program and image processing apparatus | |
| JP2002281327A (en) | Device, method and program for image processing | |
| TWI531246B (en) | Color adjustment method and its system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |