Image color correction method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of image processing, and discloses an image color correction method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting an RGB image, and carrying out the preprocessing of the RGB image; constructing a three-dimensional mapping table based on the preprocessed RGB image, mapping the RGB image, and calculating a mapping coordinate of the RGB image; and based on the mapping coordinates and the three-dimensional mapping table, performing color correction on the RGB image and outputting the corrected RGB image. According to the color correction method disclosed by the invention, the color cast condition of the image can be well improved, the algorithm complexity is low, the required computing resources are few, the color correction can be carried out on the endoscope image in real time, and the accuracy and efficiency of clinical diagnosis are improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image color correction method, device, electronic equipment and storage medium. Background Art

[0002] Endoscope is a commonly used medical device with important clinical application value. The quality of its image affects the clinical use effect of the endoscope. Existing color correction methods, such as those based on polynomial regression or deep learning, can improve the image color cast problem, but the polynomial regression method is highly complex and has poor robustness. Although the deep learning method has good robustness, it is highly complex and consumes a lot of resources. It is difficult to process images in real time and cannot meet clinical diagnosis requirements. Summary of the invention

[0003] In view of this, the present invention provides an image color correction method, device, electronic device and storage medium to solve the problem of how to quickly and accurately correct the image color in real time.

[0004] In a first aspect, the present invention provides an image color correction method, the method comprising:

[0005] Input an RGB image and preprocess the RGB image;

[0006] Constructing a three-dimensional mapping table based on the preprocessed RGB image, mapping the RGB image, and calculating the mapping coordinates of the RGB image;

[0007] Based on the mapping coordinates and the three-dimensional mapping table, color correction is performed on the RGB image and a corrected RGB image is output.

[0008] Beneficial effects: By inputting the RGB image into the image processing software, the input RGB image is preprocessed in the image processing software; for example, the image size is adjusted to meet the requirements of subsequent processing, the image is cropped to remove unnecessary parts, and denoising is performed to reduce noise interference in the image. Then, the color characteristics and distribution of the preprocessed RGB image are used to construct a three-dimensional mapping table of the RGB image, and the three dimensions of the three-dimensional mapping table correspond to the pixel values ​​of the three RGB channels of the input image respectively; further, the pixel position to be mapped in the preprocessed RGB image is extracted, and the mapping coordinates of the RGB image are obtained by pixel value calculation; the corresponding corrected pixel value is obtained in the three-dimensional mapping table according to the mapping coordinate, and then the corrected RGB image is output. The color correction method disclosed in the present invention can well improve the color cast of the image, and the algorithm complexity is low, the required computing resources are small, and the color correction of the endoscopic image can be performed in real time, thereby improving the accuracy and efficiency of clinical diagnosis.

[0009] In an optional implementation, the calculating the mapping coordinates of the RGB image includes:

[0010] Calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, and the calculation formula is:

[0011] r1 = round(r×(leng-1))

[0012] g1 = round(g × (leng - 1))

[0013] b1 = round(b×(leng-1))

[0014] xbel=leng×leng×b1+leng×g1+r1+1

[0015] Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table.

[0016] In an optional implementation, the preprocessing of the RGB image includes:

[0017] The RGB image is subjected to color adjustment processing to obtain an RGB image of a target color.

[0018] In an optional implementation, the color correction of the RGB image based on the mapping coordinates and the three-dimensional mapping table and outputting the corrected RGB image includes:

[0019] Searching the three-dimensional mapping table for a mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image;

[0020] The RGB image is color corrected according to the mapped pixel value at each pixel position and a corrected RGB image is output.

[0021] In an optional implementation, the expression for searching the mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image in the three-dimensional mapping table is:

[0022] [r2,g2,b2]=3DLUT(xbel)

[0023] Among them, r2, g2, and b2 are the pixel values ​​of the three channels after mapping at each pixel position in the RGB image; 3DLUT is a three-dimensional mapping table; and xbel is the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image.

[0024] In an optional implementation, the size of the three-dimensional mapping table includes 16×16×16, 32×32×32 or 64×64×64.

[0025] In a second aspect, the present invention further provides an image color correction device, comprising:

[0026] A preprocessing module, used for inputting an RGB image and preprocessing the RGB image;

[0027] A calculation module, used to construct a three-dimensional mapping table based on the preprocessed RGB image, map the RGB image, and calculate the mapping coordinates of the RGB image;

[0028] A correction module is used to perform color correction on the RGB image based on the mapping coordinates and the three-dimensional mapping table and output a corrected RGB image.

[0029] In an optional implementation, the calculation module includes:

[0030] The calculation unit is used to calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, and the calculation formula is:

[0031] r1 = round(r×(leng-1))

[0032] g1 = round(g × (leng - 1))

[0033] b1 = round(b×(leng-1))

[0034] xbel=leng×leng×b1+leng×g1+r1+1

[0035] Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table.

[0036] In a third aspect, the present invention further provides an electronic device, comprising: a memory, a processor, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0037] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the above-mentioned image color correction method.

[0038] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the storage medium stores at least one executable instruction, and when the executable instruction is executed on an electronic device / image color correction device, the electronic device / image color correction device executes the above-mentioned image color correction method.

[0039] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 is a flow chart of an image color correction method provided by an embodiment of the present invention;

[0042] Figure 2 is a rendering of a human oral cavity image before processing in an embodiment of the present invention;

[0043] Figure 3 is a diagram showing the effect of a human oral cavity image after processing in an embodiment of the present invention;

[0044] Figure 4 is a schematic structural diagram of an embodiment of an image color correction device provided by an embodiment of the present invention;

[0045] Figure 5 It is a schematic diagram of the structure of an embodiment of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0047] The following describes a specific embodiment of an image color correction method of the present invention. Figure 1 It is a flowchart of an image color correction method provided by an embodiment of the present invention. This specification provides method operation steps such as the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in the order of the method shown in the embodiment or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment). Specifically, Figure 1 As shown, the method may include the following steps:

[0048] Step S100, inputting an RGB image and preprocessing the RGB image;

[0049] Step S200: construct a three-dimensional mapping table based on the preprocessed RGB image, map the RGB image, and calculate the mapping coordinates of the RGB image;

[0050] Step S300: Based on the mapping coordinates and the three-dimensional mapping table, color correction is performed on the RGB image and the corrected RGB image is output.

[0051] In this embodiment, by inputting the RGB image into the image processing software, the input RGB image is preprocessed in the image processing software; for example, the image size is adjusted to meet the requirements of subsequent processing, the image is cropped to remove unnecessary parts, and denoising is performed to reduce noise interference in the image. Then, the color characteristics and distribution of the preprocessed RGB image are used to construct a three-dimensional mapping table of the RGB image, and the three dimensions of the three-dimensional mapping table correspond to the pixel values ​​of the three RGB channels of the input image. Further, the pixel position to be mapped in the preprocessed RGB image is extracted, and the mapping coordinates of the RGB image are obtained by pixel value calculation; the corresponding corrected pixel value is obtained in the three-dimensional mapping table according to the mapping coordinates, and then the corrected RGB image is output. The color correction method disclosed in the present invention can well improve the color cast of the image, and the algorithm complexity is low, the required computing resources are small, and the color correction of the endoscopic image can be performed in real time, thereby improving the accuracy and efficiency of clinical diagnosis.

[0052] like Figure 2 , Figure 3 As shown in the figure, the human oral cavity image collected by the endoscope has uneven brightness and darker surroundings before processing, and unclear details. After being processed by the image color correction method of the present invention, the image brightness is more uniform and brighter around the image, with clearer details and colors closer to the standard. This helps doctors make diagnoses and improves the accuracy and efficiency of clinical diagnosis.

[0053] In one embodiment, step S100 includes: performing color adjustment on the RGB image to obtain an RGB image of a target color.

[0054] In this embodiment, the RGB image can be input into image processing software, such as 3DLUTCreator and image-adaptive-3dlut, etc.; by performing color adjustment on the input RGB image in the image processing software, by adjusting various parameters such as hue, saturation, brightness, contrast, etc., the overall color performance of the image can be changed, and the color of different brightness areas can be finely adjusted using the curve tool. In the process of continuous trial and adjustment, the desired color effect can be achieved, thereby correcting the color deviation of the image.

[0055] In step S200, the preprocessed RGB image is analyzed in detail to extract features related to color distribution, brightness change, texture, etc. The pixel values ​​of the three RGB channels are used as the three coordinate axes of the three-dimensional space. In the three-dimensional space, the color value of each pixel corresponds to a specific point; the color points in the three-dimensional space are sampled, the sampling density and interval are determined, and then the sampling points are gridded to form a regular three-dimensional grid structure. For each grid node, the corresponding relationship with the target three-dimensional mapping table is calculated according to the color characteristics of the surrounding pixels. The three-dimensional mapping table generated initially is optimized to remove noise and abnormal values ​​in the three-dimensional mapping table; and it is adjusted according to the actual effect to ensure the accuracy and effectiveness of the three-dimensional mapping table. Among them, the size of the three-dimensional mapping table includes 16×16×16, 32×32×32 or 64×64×64. 16×16×16 means that for each color channel (R, G, B), there are 16 discrete value levels, that is, a total of 16×16×16=4096 possible color combinations are mapped to specific output color values. Similarly, 32×32×32 has 32768 color combinations, and 64×64×64 has 262144 color combinations. The larger the size of the three-dimensional mapping table, the more delicate and accurate the color transition that can be represented, but it will also take up more resources and computing time. The size of the three-dimensional mapping table can be selected according to actual needs.

[0056] In one embodiment, step S200 includes: calculating the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, and the calculation formula is:

[0057] r1 = round(r×(leng-1))

[0058] g1 = round(g × (leng - 1))

[0059] b1 = round(b×(leng-1))

[0060] xbel=leng×leng×b1+leng×g1+r1+1

[0061] Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table, that is, 16, 32, or 64.

[0062] By using the round() function to calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, we can avoid the uncertainty and error caused by decimal precision problems, and make subsequent operations on the mapping coordinates clearer and more explicit.

[0063] In one embodiment, step S300 includes: searching the three-dimensional mapping table for the mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image; performing color correction on the RGB image according to the mapping pixel value of each pixel position and outputting the corrected RGB image. Further, the expression for searching the three-dimensional mapping table for the mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image is:

[0064] [r2,g2,b2]=3DLUT(xbel)

[0065] Among them, r2, g2, and b2 are the pixel values ​​of the three channels after mapping at each pixel position in the RGB image; 3DLUT is a three-dimensional mapping table; and xbel is the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image.

[0066] In this embodiment, according to the constructed three-dimensional mapping table and the calculated mapping coordinates, for each pixel in the RGB image, the three-dimensional mapping table is searched to find the mapping pixel value corresponding to the mapping coordinates of each pixel position; after finding the mapping pixel value corresponding to each pixel position in the three-dimensional mapping table, the pixel value of the pixel in the input RGB image is replaced with the found mapping pixel value to achieve color correction of the input RGB image. For example, when the color level of the RGB image is 64, the generated three-dimensional mapping table is a two-dimensional matrix of 262144×3, that is, the matrix has 262144 rows and 3 columns per row; if the mapping coordinates of the pixel values ​​of the three channels of a certain pixel position in the RGB image are calculated to be xbel=57, then 3DLUT(57) means taking the 57th row of the two-dimensional matrix, and the 57th row has 3 columns, which respectively represent r, g, and b values, so as to obtain the pixel value after color correction; then the color correction operation is performed on each pixel in the input RGB image, and finally the corrected RGB image is obtained.

[0067] Second, as Figure 4 As shown, the present invention also provides an image color correction device, comprising:

[0068] The preprocessing module 100 is used to input an RGB image and preprocess the RGB image;

[0069] The calculation module 200 is used to construct a three-dimensional mapping table based on the preprocessed RGB image, map the RGB image, and calculate the mapping coordinates of the RGB image; the size of the three-dimensional mapping table includes 16×16×16, 32×32×32 or 64×64×64;

[0070] The correction module 300 is used to perform color correction on the RGB image based on the mapping coordinates and the three-dimensional mapping table and output the corrected RGB image.

[0071] In one embodiment, the pre-processing module 100 includes:

[0072] The processing unit is used to perform color adjustment on the RGB image to obtain an RGB image of a target color.

[0073] In one embodiment, the computing module 200 includes:

[0074] The calculation unit is used to calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image. The calculation formula is:

[0075] r1 = round(r×(leng-1))

[0076] g1 = round(g × (leng - 1))

[0077] b1 = round(b×(leng-1))

[0078] xbel=leng×leng×b1+leng×g1+r1+1

[0079] Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table.

[0080] In one embodiment, the correction module 300 includes:

[0081] The search unit is used to search the mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image in the three-dimensional mapping table; the expression is:

[0082] [r2,g2,b2]=3DLUT(xbel)

[0083] Among them, r2, g2, and b2 are the pixel values ​​of the three channels after mapping at each pixel position in the RGB image; 3DLUT is a three-dimensional mapping table; xbel is the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image;

[0084] The correction unit is used to perform color correction on the RGB image according to the mapped pixel value of each pixel position and output the corrected RGB image.

[0085] In a third aspect, the present invention further provides an electronic device comprising: a memory, a processor, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the above-mentioned image color correction method.

[0086] like Figure 5 As shown, the electronic device may include: a processor (processor) 502 , a communication interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 .

[0087] The processor 502, the communication interface 504, and the memory 506 communicate with each other via a communication bus 508. The communication interface 504 is used to communicate with other devices such as a client or other server network elements. The processor 502 is used to execute a program 510, which can specifically execute the relevant steps in the above-mentioned method for image color correction.

[0088] Specifically, the program 510 may include program code including computer-executable instructions.

[0089] The processor 502 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0090] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0091] The program 510 can be specifically called by the processor 502 to enable the electronic device to execute the relevant steps in the above-mentioned embodiment of the method for image color correction.

[0092] It can be understood by those skilled in the art that Figure 5 The structure shown is only for illustration and does not limit the structure of the above-mentioned device. Figure 5 More or fewer components as shown, or with Figure 5 Different configurations are shown.

[0093] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction runs on an electronic device / image color correction device, the electronic device / image color correction device executes the above-mentioned image color correction method.

[0094] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0095] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0096] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0097] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for image color correction, characterized in that: The method comprises: Input an RGB image and preprocess the RGB image; Constructing a three-dimensional mapping table based on the preprocessed RGB image, mapping the RGB image, and calculating the mapping coordinates of the RGB image; Based on the mapping coordinates and the three-dimensional mapping table, color correction is performed on the RGB image and a corrected RGB image is output.

2. The image color correction method according to claim 1, characterized in that: The calculating the mapping coordinates of the RGB image comprises: Calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, and the calculation formula is: r1 = round(r×(leng-1)) g1 = round(g × (leng - 1)) b1 = round(b×(leng-1)) xbel=leng×leng×b1+leng×g1+r1+1 Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table.

3. The image color correction method according to claim 1, characterized in that: The preprocessing of the RGB image comprises: The RGB image is subjected to color adjustment processing to obtain an RGB image of a target color.

4. The image color correction method according to claim 1, characterized in that: The color correction of the RGB image based on the mapping coordinates and the three-dimensional mapping table and outputting the corrected RGB image comprises: Searching the three-dimensional mapping table for a mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image; The RGB image is color corrected according to the mapped pixel value at each pixel position and a corrected RGB image is output.

5. The image color correction method according to claim 4, characterized in that: The expression for searching the mapping pixel value corresponding to the mapping coordinates of each pixel position in the RGB image in the three-dimensional mapping table is: [r2,g2,b2]=3DLUT(xbel) Among them, r2, g2, and b2 are the pixel values ​​of the three channels after mapping at each pixel position in the RGB image; 3DLUT is a three-dimensional mapping table; and xbel is the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image.

6. The image color correction method according to claim 1, characterized in that: The size of the three-dimensional mapping table includes 16×16×16, 32×32×32 or 64×64×64.

7. An image color correction device, characterized in that: include: A preprocessing module, used for inputting an RGB image and preprocessing the RGB image; A calculation module, used to construct a three-dimensional mapping table based on the preprocessed RGB image, map the RGB image, and calculate the mapping coordinates of the RGB image; A correction module is used to perform color correction on the RGB image based on the mapping coordinates and the three-dimensional mapping table and output a corrected RGB image.

8. The image color correction device according to claim 7, characterized in that: The computing module comprises: The calculation unit is used to calculate the mapping coordinates of the pixel values ​​of the three channels at each pixel position in the RGB image, and the calculation formula is: r1 = round(r×(leng-1)) g1 = round(g × (leng - 1)) b1 = round(b×(leng-1)) xbel=leng×leng×b1+leng×g1+r1+1 Among them, r, g, and b are the input pixel values ​​of the three channels of each pixel position in the RGB image; r1, g1, and b1 are the output pixel values ​​of the three channels of each pixel position in the RGB image; the round() function is rounded to the nearest integer; xbel is the mapping coordinate of the pixel values ​​of the three channels of each pixel position in the RGB image; leng is the side length of the three-dimensional mapping table.

9. An electronic device, characterized in that: include: A memory, a processor, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the image color correction method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction. When the executable instruction is executed on the electronic device / image color correction device, the electronic device / image color correction device executes the image color correction method according to any one of claims 1 to 6.

Images