CN107644437B - Color cast detection system and method based on blocks - Google Patents
Color cast detection system and method based on blocks Download PDFInfo
- Publication number
- CN107644437B CN107644437B CN201610586520.4A CN201610586520A CN107644437B CN 107644437 B CN107644437 B CN 107644437B CN 201610586520 A CN201610586520 A CN 201610586520A CN 107644437 B CN107644437 B CN 107644437B
- Authority
- CN
- China
- Prior art keywords
- image
- channel data
- color cast
- tile
- block
- 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.)
- Active
Links
Images
Abstract
The method reduces the influence of external environments such as light sources, noise and the like, improves the stability and the detection rate of an algorithm by adopting an automatic white balance technology, adopts a simple and practical self-adaptive image blocking method and a region detection method based on statistical probability, and realizes accurate and efficient color cast detection.
Description
Technical Field
The invention relates to a detection system and a method thereof, in particular to a color cast detection system and a method thereof based on blocks, which are used for detecting whether a color cast phenomenon exists in the imaging of a camera module and can effectively detect the color cast area of an image.
Background
The RGB color scheme is a color standard in the industry, and various colors are obtained by changing three color channels of red (R), green (G) and blue (B) and superimposing the three color channels on each other, where RGB represents colors of the three channels of red, green and blue, and the color standard almost includes all colors that can be perceived by human vision, and is one of the most widely used color systems at present.
At present, the demand of users for the camera module is higher and higher, and not only advanced technologies such as high pixel, large aperture, large field of view, optical anti-shake, fast focusing and the like are required, but also the quality requirements for the dirty and bad points, the brightness uniformity and the chromaticity uniformity in the module are more refined. Due to the fact that the technology development speed is gradually changed, the module imaging has uneven chromaticity due to the design reasons of the module chip and the production processes of manufacturing process, assembly, burning and the like, and the abnormal phenomena of red edge, red small area, red twill, green edge, green small area and the like of the image are embodied, so that the requirement of high quality of modules produced in batches on a production line is seriously influenced.
Disclosure of Invention
The invention aims to provide a color cast detection system and a color cast detection method based on blocks, which can automatically, quickly, accurately and efficiently detect the color cast area of an image and stably and accurately detect whether the imaging of a camera module has the color cast phenomenon in real time.
Another object of the present invention is to provide a color cast detection system and method based on block, which can reduce the influence of external environments such as light source and noise on the detection in the production process.
Another objective of the present invention is to provide a color cast detection system and method thereof, which can ensure the quality of modules produced in batch on a production line.
Another objective of the present invention is to provide a block-based color cast detection system, which includes at least one white balance module, and the white balance module processes the received RGB image by using an automatic white balance technique, so as to improve the stability and detection rate in the detection process.
Another object of the present invention is to provide a block-based color cast detection system, which comprises at least one image blocking module, which blocks an image, and is adaptive, simple and practical.
It is another object of the present invention to provide a block-based color cast detection system, which comprises at least one block threshold detection module, wherein the block threshold detection module can achieve accurate and efficient color cast detection.
Another objective of the present invention is to provide a block-based color cast detection method, which performs color cast detection by comparing red channel data, green channel data, and blue channel data at the same position of the RGB image, so as to reduce the influence of external environments such as light source and noise on detection in the production process.
Another object of the present invention is to provide a block-based color cast detection method, which employs an automatic white balance step, and can improve stability and detection rate in the detection process.
Another object of the present invention is to provide a block-based color cast detection method, which employs a region detection procedure based on statistical probability, and can achieve accurate and efficient color cast detection.
In order to achieve the above object, the present invention further provides a block-based color cast detection system, including: the image processing module processes the RGB image, the image detection module performs image color cast region detection on the image processed by the image processing module, and the detection result output module outputs the detection result of the image detection module.
In an embodiment, the image processing module includes at least one white balance module, at least one image ratio processing module, and at least one image binarization processing module, the white balance module performs automatic white balance processing on the RGB image received by the image receiving module, the image ratio processing module processes the RGB image after the white balance processing and obtains an image ratio, and the image binarization processing module performs image binarization processing on the RGB image.
In one embodiment, the white balance module processes the received RGB image using an automatic white balance technique.
In an embodiment, the white balance module performs white balance processing using the green channel data as a reference value.
In an embodiment, the image processing module further includes at least one image blocking module and at least one white pixel ratio processing module, the image blocking module blocks the RGB image into a plurality of block image areas, and the white pixel ratio processing module counts a ratio value of the number of white pixels of each block image area to the total number of pixels of each block image area.
In an embodiment, the image detection module includes at least one block threshold detection module, and the block threshold detection module performs image color cast region detection by using a region detection technique based on statistical probability.
In an embodiment, the block threshold detection module detects each block image by using each preset detection threshold after the white pixel ratio processing module counts a ratio of the number of white pixels of each block image region to the total number of pixels of each block image region, and if the block ratio is greater than the detection threshold, the block image region is determined as a color cast region, otherwise, the block image region is determined as a normal region.
According to another aspect of the present invention, there is also provided a block-based color cast detection method, including the steps of:
(a) receiving an RGB image shot by the camera module;
(b) carrying out image white balance processing;
(c) processing the image ratio;
(d) carrying out image binarization processing;
(e) image blocking;
(f) counting the white pixel ratio of each image block;
(g) block threshold detection; and
(h) and outputting a detection result.
In an embodiment, the step (b) performs white balance processing by using the G-channel data as a reference value.
In one embodiment, the step (b) further comprises the step (b 1): acquiring white balance gains of red channel data and blue channel data from a specified image area of the RGB image; and step (b 2): and acquiring gain images of the red channel and the blue channel after white balance.
In one embodiment, the RGB image is divided into a plurality of block image regions using the same size of block regions in the step (e).
In an embodiment, in the step (e), the edge area of each block image area is allowed to overlap, but the blocks may not overlap.
In an embodiment, the white pixel ratio of each image block in step (f) is a ratio of the number of white pixels of each block image area to the total number of pixels of the block image area.
In one embodiment, the step (g) is preceded by the steps of: a detection threshold is set in advance.
In an embodiment, in the step (g), the block threshold detection uses a preset detection threshold to detect each block image area.
In one embodiment, the step (g) further comprises the steps of: and comparing each block ratio value of each block image area, if the block ratio value is greater than a detection threshold value, judging the block image area as a color cast area, and if the block ratio value is less than the detection threshold value, judging the block image area as a normal area.
In an embodiment, to reduce the influence of external environments such as light sources and noise, the block-based color cast detection method further includes the following detection methods: if the image shows a red bias phenomenon, the red channel data at the same position of the REG image is larger than the green channel data and the blue channel data; if the image shows a greenish phenomenon, the green channel data at the same position of the REG image is larger than the red channel data and the blue channel data; if the image shows a blue bias phenomenon, the blue channel data at the same position of the REG image is larger than the red channel data and the green channel data; and if the image shows a yellow phenomenon, the sum of the red channel data and the green channel data at the same position of the REG image is larger than that of the blue channel data.
Drawings
FIG. 1 is a block diagram of a preferred embodiment of a tile-based color cast detection system according to the present invention.
Fig. 2 is a flow chart of a block-based color cast detection method according to the above preferred embodiment of the present invention.
Fig. 3 is a schematic diagram of image blocking according to the above preferred embodiment of the present invention.
Fig. 4 is a schematic diagram of the block detection result in the above preferred embodiment according to the present invention.
FIG. 5 is a diagram illustrating the corresponding color cast ratio in FIG. 4.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
Fig. 1 to 4 show a block-based color cast detection system and a method thereof according to a preferred embodiment of the present invention, the block-based color cast detection system is used for detecting whether a color cast phenomenon exists in an image of a camera module, and can effectively detect a color cast region of the image.
As shown in fig. 1, the block-based color cast detection system includes an image receiving module 10, an image processing module 20, an image detecting module 30 and a detection result output module 40. The image receiving module 10 receives an RGB image captured by a camera module, the image processing module 20 processes the image received by the image receiving module 10, the image detection module 30 performs image color cast region detection on the image processed by the image processing module 20, and the detection result output module 40 outputs the detection result of the image detection module 30 to the block-based color cast detection system.
Specifically, the image processing module 20 includes a white balance module 21, an image ratio processing module 22, an image binarization processing module 23, an image blocking module 24 and a white pixel ratio processing module 25. The white balance module 21 performs automatic white balance processing on the RGB image received by the image receiving module 10.
In the white balance module 21, an automatic white balance technique is used to process the received RGB image, thereby facilitating the detection of the image detection module 30. It can be understood by those skilled in the art that there are three CCD electronic coupling elements (charge-coupled devices, which are silicon chips for detecting light, and the change of semiconductor potential wells is generated and controlled by clock pulse voltage to realize solid-state electronic devices for storing and transferring charge information) inside the camera module, for respectively sensing blue, green and red lights, and the electronic amplification ratios of these three photosensitive circuits are the same under the preset condition, and are 1: 1: the relation of 1, the adjustment of the automatic white balance is that the proportional relation is changed according to the scene to be adjusted. For example, the proportional relationship between blue, green and red light of the scene to be adjusted is 2: 1: 1 (the blue light has a large proportion, the color temperature is high), then the proportion relationship after white balance adjustment is 1: 2: 2, the proportion of obvious blue reduces in the circuit magnification ratio after the adjustment, has increased the proportion of green and red, is adjusted the scenery like this and passes through white balance adjustment circuit to the image of shooing, and blue, green, red proportion just can be the same to be favorable to being adjusted the formation of image of scenery at the module of making a video recording, RGB image process promptly after white balance module 21's automatic processing, improve the stability of data processing among the testing process and image detection module 30's detection rate. It should be noted that, in the color cast detection system based on the block of the present invention, the white balance module 21 employs an automatic white balance technology, and compared with the prior art, the white balance detection system is firstly applied to the detection of whether the color cast phenomenon exists in the image imaged by the camera module. It should be noted that, because the G channel data in the RGB image imaged by the camera module accounts for about 60% of the pixel count of the entire image, the white balance module 21 performs white balance processing by using the G channel data as a reference value. In order to improve the data processing efficiency of each picture parameter in the detection process, the designated image area respectively obtains the white balance gains of the R channel data and the B channel data, and finally obtains the white balanced R channel gain image and the white balanced B channel gain image. It should be noted that, for example, through a contrast test, 40 8M color cast abnormal images are selected as the RGB images received by the image receiving module 10, and if the automatic white balance processing of the white balance module 21 is not used, the image detection module 30 can only detect 34 color cast abnormal images, and the detection rate is 85%; if the automatic white balance processing of the white balance module 21 is adopted, the image detection module 30 can identify 39 color cast images, and the detection rate reaches 97.5%. Therefore, the automatic white balance processing adopted by the white balance module 21 greatly improves the stability of data processing during the detection process and the detection rate of the image detection module 30.
It will be understood by those skilled in the art that the pixel number data involved in the automatic white balance processing of the white balance module 21 in the preferred embodiment and the parameter data in the comparative experiment are only examples, and the present invention is not limited thereto.
Further, after the RGB image received by the image receiving module 10 is subjected to the automatic white balance processing by the white balance module 21, the image ratio processing module 22 processes the RGB image and obtains an image ratio, in this process, red channel data, green channel data, and blue channel data of the same position in the processed image are involved. By processing and acquiring the image parameters of the image ratio processing module 22, a solution for detecting the color cast abnormal image, which is less affected by different external environments such as light sources and noises, can be obtained. For example, under the influence of external environmental factors such as light source and noise, the red bias detection scheme: if the image shows a red bias phenomenon, the red (R) channel data at the same position of the image is larger than the green (G) channel data and the blue (B) channel data; greenish detection protocol: if the image shows a greenish phenomenon, the green channel data at the same position of the image is larger than the red channel data and the blue channel data; for example, the bluing detection scheme: if the image shows a blue-biased phenomenon, the blue channel data at the same position of the image is larger than the red channel data and the green channel data; for example, the yellow bias detection scheme: if the image shows yellow, the sum of the red channel data and the green channel data at the same position of the image is larger than that of the blue channel data.
Further, the image binarization processing module 23 performs further processing on the RGB image, that is, binarization processing of the image. As will be understood by those skilled in the art, the binarization processing of the image is to set the gray scale of a point on the image to 0 or 255, that is, the whole image exhibits a distinct black-and-white effect. That is, a gray scale image with 256 brightness levels is selected by a proper threshold value to obtain a binary image which can still reflect the whole and local features of the image. In the digital image processing, the binary image is processed and analyzed, and the gray level image is firstly binarized to obtain the binary image, so that when the image detection module 30 is favorable for further detecting the image, the set property of the image is only related to the position of a point with a pixel value of 0 or 255, and the multi-level value of the pixel is not related, so that the detection process of the block-based color cast detection system is simple, and the data processing and compression amount is small. In addition, in order to obtain an ideal binary image, a non-overlapping region is generally defined by closed and connected boundaries. All pixels with the gray levels larger than or equal to the threshold are judged to belong to the specific object, the gray level of the pixels is 255 for representation, otherwise the pixels are excluded from the object area, the gray level is 0, and the pixels represent the background or the exceptional object area. If a particular object has a uniform gray level inside it and is in a uniform background with gray levels of other levels, a comparable segmentation effect can be obtained using thresholding. If the difference between the object and the background is not represented in gray scale (e.g., different texture), the difference can be converted into a gray scale difference, and then the image can be segmented using a threshold selection technique.
Further, the image blocking module 24 blocks the RGB image subjected to the binarization processing by the image binarization processing module 23. The image blocking module 24 blocks the RGB image by using an adaptive simple and practical image blocking method. As shown in fig. 3, in the preferred embodiment of the present invention, the RGB image 90 is partitioned into block image regions 90n, wherein the edge regions of the block image regions 90n are allowed to overlap, the height of each block image region 90n is recorded as Bh, and the width of each block image region 90n is recorded as Bw.
Further, after the image blocking by the image blocking module, the white pixel ratio processing module 25 counts a ratio value of the number of white pixels of each block image area 90n to the total number of pixels of each block image area 90 n. The ratio value here can also be defined as the color cast ratio p.
Further, the image detection module 30 includes a block threshold detection module 31, and the block threshold detection module 31 detects each block image 90n by using each preset detection threshold after the white pixel ratio processing module 25 counts a ratio of the number of white pixels of each block image area 90n to the total number of pixels of each block image area 90n, if the block ratio is greater than the detection threshold, the block image area 90n is determined as a color cast (NG) area, otherwise, the block image area 90n is determined as a normal (OK) area. For example, the values of the color cast ratio p of the two block image areas 90n at the lower right as shown in fig. 4 and 5, which are 0.48 and 0.86, are judged as NG areas, and the other block image areas are judged as OK areas. It should be noted that the block threshold detection module 31 of the image detection module 30 adopts a region detection method based on statistical probability, so as to realize accurate and efficient color cast detection.
It should be noted that the color cast detection system based on the blocks of the present invention can reduce the influence of external environments such as light source and noise on the detection of the color cast abnormal image, and improve the detection rate.
Further, the detection result output module 40 of the blocking-based color cast detection system outputs the detection result of the blocking threshold detection module 31 of the image detection module 30.
Therefore, based on the preferred embodiment of the present invention, a block-based color cast detection method is further disclosed, which is used for color cast detection of imaging of a camera module, and the block-based color cast detection method includes the following steps:
(a) receiving an RGB image shot by the camera module;
(b) carrying out image white balance processing;
(c) processing the image ratio;
(d) carrying out image binarization processing;
(e) image blocking;
(f) counting the white pixel ratio of each image block;
(g) block threshold detection; and
(h) and outputting a detection result.
Wherein, the step (b) adopts G channel data as a reference value to perform white balance processing.
It is worth mentioning that the step (b) further includes a step (b 1): acquiring white balance gains of R channel data and B channel data from a specified image area of the RGB image; and step (b 2): and acquiring the gain images of the R channel and the B channel after white balance.
It is worth mentioning that, as shown in fig. 3, the RGB image 90 is divided into a plurality of block image regions 90n by using the same size of block regions in the step (e). Wherein, the edge regions of the respective image regions 90n may overlap.
It should be noted that the white pixel ratio of each image block in the step (f) is a ratio of the number of white pixels of each block image area 90n to the total number of pixels of the block image area 90 n.
Wherein step (g) is preceded by the step of: a detection threshold is set in advance.
In the step (g), the block threshold detection is performed on each block image region 90n by using the preset detection threshold.
Wherein the step (g) further comprises the steps of: the block ratio values p of the block image areas 90n are compared, and if the block ratio values p are greater than a detection threshold, the block image areas 90n are determined as color cast (NG) areas, and if the block ratio values p are less than the detection threshold, the block image areas 90n are determined as normal (OK) areas.
It is worth mentioning that the block-based color cast detection method further includes a red cast detection method for reducing the influence of external environments such as light sources and noise: if the image shows a red bias phenomenon, the red (R) channel data at the same position of the REG image is larger than the green (G) channel data and the blue (B) channel data.
It is worth mentioning that the block-based color cast detection method further includes a green cast detection method: and if the image shows a greenish phenomenon, the green channel data at the same position of the REG image is larger than the red channel data and the blue channel data.
It is worth mentioning that the block-based color cast detection method further includes a blue cast detection method: and if the image shows a blue bias phenomenon, the blue channel data at the same position of the REG image is larger than the red channel data and the green channel data.
It is worth mentioning that the block-based color cast detection method further includes a yellow cast detection method: and if the image shows a yellow phenomenon, the sum of the red channel data and the green channel data at the same position of the REG image is larger than that of the blue channel data.
It will be understood by those skilled in the art that the above-listed steps of detecting the color cast abnormal image in the block-based color cast detection method are only examples in the preferred embodiment of the present invention, and other reasonable variations are possible, and the present invention is not limited thereto.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.
Claims (15)
1. A block-based color cast detection system, comprising: the image processing module comprises at least one white balance module, and the white balance module carries out automatic white balance processing on the RGB image received by the image receiving module.
2. The block-based color cast detection system according to claim 1, wherein the image processing module comprises at least one image ratio processing module and at least one image binarization processing module, the image ratio processing module processes the RGB image after the white balance processing and obtains red channel data, green channel data and blue channel data ratio of the image, and the image binarization processing module performs image binarization processing on the RGB image.
3. The tile-based color cast detection system of claim 2 wherein the white balance module performs white balance processing using green channel data as a reference value.
4. The block-based color cast detection system according to claim 2, wherein the image processing module further comprises at least one image blocking module for blocking the RGB image after the binarization processing by the image binarization processing module into a plurality of block image areas, and at least one white pixel ratio processing module for counting a ratio value of the number of white pixels in each block image area to the total number of pixels in each block image area.
5. The tile-based color cast detection system of claim 4 wherein the image detection module comprises at least one tile threshold detection module that employs a statistical probability-based region detection technique for image color cast region detection.
6. The tile-based color cast detection system according to claim 5, wherein the tile threshold detection module detects each tile image by using each preset detection threshold after the white pixel ratio processing module counts a ratio of the number of white pixels of each tile image area to the total number of pixels of each tile image area, and if the tile ratio is greater than the detection threshold, the tile image area is determined as a color cast area, otherwise the tile image area is determined as a normal area.
7. A color cast detection method based on blocks is characterized by comprising the following steps:
(a) receiving an RGB image shot by a camera module;
(b) carrying out image white balance processing;
(c) processing the RGB image after the white balance processing and acquiring the ratio of red channel data, green channel data and blue channel data of the image;
(d) carrying out image binarization processing;
(e) partitioning the RGB image subjected to binarization processing into a plurality of image areas;
(f) counting the white pixel ratio of each image block, wherein the white pixel ratio of each image block is a ratio value of the number of white pixels of each block image area to the total number of pixels of the block image area;
(g) after counting the white pixel ratio of each image block, detecting the block image area by using each preset detection threshold, if the block ratio value is greater than the detection threshold, judging the block image area as a color cast area, otherwise, judging the block image area as a normal area; and
(h) and outputting a detection result.
8. The tile-based color cast detecting method according to claim 7, wherein the white balance processing is performed in the step (b) using the G-channel data as a reference value.
9. The tile-based color cast detection method of claim 7 wherein said step (b) further comprises the step (b 1): acquiring white balance gains of red channel data and blue channel data from a specified image area of the RGB image; and step (b 2): and acquiring gain images of the red channel and the blue channel after white balance.
10. The tile-based color cast detection method according to claim 7, wherein the step (e) divides the RGB image into a plurality of tile image areas.
11. The tile-based color cast detection method according to claim 10, wherein in said step (e), edge regions of each of said tile image areas are allowed to overlap.
12. The tile-based color cast detection method of claim 7, wherein to reduce the effects of light sources and noise, the tile-based color cast detection method further comprises a red cast detection method: and if the image shows a red bias phenomenon, the red channel data at the same position of the RGB image is larger than the green channel data and the blue channel data.
13. The tile-based color cast detection method of claim 7, wherein to reduce the effects of light sources and noise, the tile-based color cast detection method further comprises a green cast detection method: and if the image shows a greenish phenomenon, the green channel data at the same position of the RGB image is larger than the red channel data and the blue channel data.
14. The tile-based color cast detection method of claim 7 wherein to reduce the effects of light sources and noise, the tile-based color cast detection method further comprises a blue cast detection method: and if the image shows a blue bias phenomenon, the blue channel data at the same position of the RGB image is larger than the red channel data and the green channel data.
15. The tile-based color cast detection method of claim 7, wherein to reduce the effects of light sources and noise, the tile-based color cast detection method further comprises a yellow cast detection method: if the image shows a yellow phenomenon, the sum of the red channel data and the green channel data at the same position of the RGB image is larger than that of the blue channel data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610586520.4A CN107644437B (en) | 2016-07-21 | 2016-07-21 | Color cast detection system and method based on blocks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610586520.4A CN107644437B (en) | 2016-07-21 | 2016-07-21 | Color cast detection system and method based on blocks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107644437A CN107644437A (en) | 2018-01-30 |
| CN107644437B true CN107644437B (en) | 2021-01-26 |
Family
ID=61109624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610586520.4A Active CN107644437B (en) | 2016-07-21 | 2016-07-21 | Color cast detection system and method based on blocks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107644437B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108810397B (en) * | 2018-04-23 | 2021-01-19 | 深圳和而泰数据资源与云技术有限公司 | Image color cast correction method and terminal equipment |
| CN108924545A (en) * | 2018-07-02 | 2018-11-30 | 昆山丘钛微电子科技有限公司 | The veiling glare detection device and detection method of camera module |
| CN111031307A (en) * | 2019-12-20 | 2020-04-17 | 昆山丘钛微电子科技有限公司 | Camera module detection method and device, electronic equipment and medium |
| CN115249272A (en) * | 2021-04-27 | 2022-10-28 | 青岛海尔电冰箱有限公司 | Method and equipment for detecting image color cast and refrigerator |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070159536A1 (en) * | 2006-01-11 | 2007-07-12 | Smedia Technology Corporation | White balance control method |
| CN101166285A (en) * | 2006-10-16 | 2008-04-23 | 展讯通信（上海）有限公司 | Automatic white balance method and device |
| CN101193316A (en) * | 2006-11-21 | 2008-06-04 | 安凯（广州）软件技术有限公司 | A self-adapted white balance correction method |
| CN102169585A (en) * | 2011-03-31 | 2011-08-31 | 汉王科技股份有限公司 | Method and device for detecting image color cast |
| CN102271260A (en) * | 2011-09-07 | 2011-12-07 | 天津天地伟业数码科技有限公司 | Method for adjusting white balance |
| CN102685513A (en) * | 2012-05-21 | 2012-09-19 | 信利光电(汕尾)有限公司 | White balance processing method and device |
| CN102750713A (en) * | 2012-07-18 | 2012-10-24 | 山东神思电子技术股份有限公司 | Image color shift detection method |
| CN103067734A (en) * | 2012-12-12 | 2013-04-24 | 成都三泰电子实业股份有限公司 | Video image color cast detecting method of video quality diagnostic system |
| CN103065334A (en) * | 2013-01-31 | 2013-04-24 | 金陵科技学院 | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space |
| CN103500457A (en) * | 2013-10-23 | 2014-01-08 | 武汉东智科技有限公司 | Method of color cast detection of video image |
| CN104796683A (en) * | 2014-01-22 | 2015-07-22 | 中兴通讯股份有限公司 | Image color calibration method and system |
-
2016
- 2016-07-21 CN CN201610586520.4A patent/CN107644437B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070159536A1 (en) * | 2006-01-11 | 2007-07-12 | Smedia Technology Corporation | White balance control method |
| CN101166285A (en) * | 2006-10-16 | 2008-04-23 | 展讯通信（上海）有限公司 | Automatic white balance method and device |
| CN101193316A (en) * | 2006-11-21 | 2008-06-04 | 安凯（广州）软件技术有限公司 | A self-adapted white balance correction method |
| CN102169585A (en) * | 2011-03-31 | 2011-08-31 | 汉王科技股份有限公司 | Method and device for detecting image color cast |
| CN102271260A (en) * | 2011-09-07 | 2011-12-07 | 天津天地伟业数码科技有限公司 | Method for adjusting white balance |
| CN102685513A (en) * | 2012-05-21 | 2012-09-19 | 信利光电(汕尾)有限公司 | White balance processing method and device |
| CN102750713A (en) * | 2012-07-18 | 2012-10-24 | 山东神思电子技术股份有限公司 | Image color shift detection method |
| CN103067734A (en) * | 2012-12-12 | 2013-04-24 | 成都三泰电子实业股份有限公司 | Video image color cast detecting method of video quality diagnostic system |
| CN103065334A (en) * | 2013-01-31 | 2013-04-24 | 金陵科技学院 | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space |
| CN103500457A (en) * | 2013-10-23 | 2014-01-08 | 武汉东智科技有限公司 | Method of color cast detection of video image |
| CN104796683A (en) * | 2014-01-22 | 2015-07-22 | 中兴通讯股份有限公司 | Image color calibration method and system |
Non-Patent Citations (3)
| Title |
|---|
| "基于图像偏色检测的自动白平衡算法研究";巢琳 等;《移动通信》;20150831(第8期);第80-83页 * |
| "基于图像分析的偏色检测及颜色校正方法";徐晓昭 等;《测控技术》;20080531;第27卷(第5期);第10-21页 * |
| "让你拍的照片永不偏色";老庄;《个人图书馆》;20120902;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107644437A (en) | 2018-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019148912A1 (en) | Image processing method, apparatus, electronic device and storage medium | |
| EP2775719B1 (en) | Image processing device, image pickup apparatus, and storage medium storing image processing program | |
| US8077228B2 (en) | Processing of sensor values in imaging systems | |
| CN107644437B (en) | Color cast detection system and method based on blocks | |
| US20150092079A1 (en) | Imaging systems and methods for generating motion-compensated high-dynamic-range images | |
| US9007488B2 (en) | Systems and methods for generating interpolated high-dynamic-range images | |
| KR101441786B1 (en) | Subject determination apparatus, subject determination method and recording medium storing program thereof | |
| CN107395991B (en) | Image synthesis method, image synthesis device, computer-readable storage medium and computer equipment | |
| CN103139492B (en) | Camera head, image capture method and the system of supervision | |
| US7158687B2 (en) | Image combination device | |
| US10567723B2 (en) | System and method for detecting light sources in a multi-illuminated environment using a composite RGB-IR sensor | |
| CN107682611B (en) | Focusing method and device, computer readable storage medium and electronic equipment | |
| US9860456B1 (en) | Bayer-clear image fusion for dual camera | |
| JP2010219683A (en) | Image processing device, image processing method, and program | |
| CN111970501A (en) | Pure color scene AE color processing method and device, electronic equipment and storage medium | |
| US9113121B2 (en) | Method for white balance adjustment of images | |
| CN109937382A (en) | Imaging device and imaging method | |
| JP2008067158A (en) | Electronic equipment, method for processing information and program | |
| JP2006229626A (en) | Defective pixel detecting method | |
| CN112950509B (en) | Image processing method and device and electronic equipment | |
| US8804025B2 (en) | Signal processing device and imaging device | |
| WO2022032666A1 (en) | Image processing method and related apparatus | |
| CN114170153A (en) | Wafer defect detection method and device, electronic equipment and storage medium | |
| JP2020047170A (en) | Image recognition apparatus, neural network model, imaging apparatus, and image recognition method | |
| US9025046B2 (en) | Method for white balance adjustment |
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 |