Endoscopic markers, endoscopic image correction methods, and endoscopes

Abstract

This invention relates to the field of image processing technology, and discloses an endoscope marker, an endoscope image correction method, and an endoscope. The method includes: if a preset calibration command is detected, acquiring at least one endoscope image obtained by an endoscope imaging system acquiring an endoscope marker; performing region segmentation on the endoscope image to obtain a target marker box region corresponding to the endoscope marker; calculating a first correction parameter based on the difference between the channel values ​​of each channel of a first pixel contained in the first marker region; calculating a second correction parameter based on the difference between the actual channel value and the nominal channel value of a second pixel corresponding to a preset color block in the second marker region; using the first correction parameter and the second correction parameter as imaging parameters of the endoscope; simultaneously determining the ambient light source information for color temperature correction using the first correction parameter and determining the endoscope's color difference information using the second correction parameter, thereby improving the realism of the image.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, specifically to endoscopic markers, endoscopic image correction methods, and endoscopes. Background Technology

[0002] An endoscope is an optical instrument consisting of a cold light source lens, fiber optic cable, image transmission system, and screen display system. It is typically inserted into the body through natural openings or small incisions. During use, the doctor manually guides the endoscope to the area to be examined, allowing direct visualization of changes and facilitating necessary diagnosis and treatment in conjunction with surgical instruments. The quality of endoscopic imaging directly impacts the doctor's experience, the accuracy and efficiency of the examination, and also reflects the level of development of endoscopic technology.

[0003] Medical endoscopes typically consist of a main unit and interchangeable endoscopes. Many similar endoscopes do not support local storage of key optical parameters such as color temperature. This results in significant inconsistencies in color representation (especially color temperature / white balance) in the images acquired by different endoscopes of the same model due to their inherent minor optical differences. This inconsistency reduces the comparability of images when multiple endoscopes are used interchangeably and the diagnostic experience of doctors, which is a pain point that urgently needs to be addressed in existing technologies.

[0004] In view of this, there is an urgent need to propose an endoscopic image correction method to solve the problem of inconsistent color representation in endoscopic images caused by optical differences in the endoscope. Summary of the Invention

[0005] In view of this, the present invention provides an endoscope marker, an endoscope image correction method, and an endoscope to solve the problem of inconsistent color representation in endoscope images caused by optical differences in the endoscope body.

[0006] In a first aspect, the present invention provides an endoscope marker, which is fitted onto the endoscope body of an endoscope imaging system. The endoscope marker is used to perform color correction and color temperature correction on the acquired endoscope images. The bottom of the endoscope marker is provided with a color temperature correction area and a color difference correction area. The color temperature correction area is used to correct the white balance parameters of the endoscope, and the color difference correction area is used to correct the color difference parameters of the endoscope. It includes at least one preset color block for characterizing the target tissue, and the preset color block has a preset color. The surface of the endoscope marker is a uniform matte surface.

[0007] In one optional implementation, the color difference correction area includes at least one of a first preset color block, a second preset color block, a third preset color block, and a fourth preset color block; the color of the first preset color block is the color of deoxyhemoglobin; the color of the second preset color block is the color of bright red hemoglobin; the color of the third preset color block is the color of bright red submucosal blood vessels; and the color of the fourth preset color block is the color of pink moist mucosa.

[0008] In one optional embodiment, the optical characteristics of the endoscopic marker surface are matte diffuse reflection, with a gloss level ≤3Gu at 60° and a reflectivity deviation ≤5% at a reflection angle of 0-80°.

[0009] Secondly, the present invention provides an endoscopic image correction method. The endoscope includes an endoscopic camera system, an image processing system, an illumination system, and endoscopic markers. The endoscopic camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters. The endoscopic markers include a color temperature correction region and a color difference correction region. The color difference correction region includes at least one preset color patch for characterizing the target tissue. The endoscopic image correction method includes: if a preset calibration command is detected, acquiring at least one endoscopic image obtained by the endoscopic camera system acquiring the endoscopic markers; performing region segmentation on the endoscopic image to obtain target marker frame regions corresponding to the endoscopic markers; wherein the target marker frame regions include a first marker region corresponding to the color temperature correction region and a second marker region corresponding to the color difference correction region; calculating a first correction parameter based on the difference between the channel values ​​of each channel of the first pixel contained in the first marker region; calculating a second correction parameter based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color patch in the second marker region; and using the first correction parameter and the second correction parameter as imaging parameters of the endoscope.

[0010] In one optional implementation, a second correction parameter is calculated based on the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked region, including: obtaining the preset nominal LAB value corresponding to each preset color block; extracting the actual LAB value of each preset color block in the endoscopic image; calculating the color difference deviation degree corresponding to the preset color block based on the difference between the actual LAB value and the preset nominal LAB value; and calculating the second correction parameter based on the actual LAB value, the preset nominal LAB value, and the color difference deviation degree corresponding to each preset color block.

[0011] In one optional implementation, a second correction parameter is calculated based on the actual LAB value, the preset nominal LAB value, and the color difference deviation corresponding to each preset color block, including: calculating the color difference weight vector of each preset color block based on the actual LAB value, the preset nominal LAB value, and the color difference deviation; and calculating the second correction parameter based on the color difference weight vector, the actual LAB value, the preset nominal LAB value, and the preset weighted CCM matrix.

[0012] In one optional implementation, a first correction parameter is calculated based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked region, including: extracting the pixel values ​​of each preset channel in the first marked region; calculating the average value of the pixel values ​​corresponding to each preset channel; and using one preset channel as a reference channel, calculating the difference between the average value of other preset channels and the average value of the reference channel as the first correction parameter.

[0013] In one optional implementation, the endoscopic image correction method further includes: obtaining a first correction parameter corresponding to each endoscopic image; and averaging the first correction parameters to obtain the final first correction parameter.

[0014] In one optional implementation, the endoscopic images are segmented into regions, including: obtaining a Y-domain image sequence corresponding to the endoscopic images; Based on the contrast of each pixel in the Y-domain image sequence, the endoscopic image is segmented to obtain the target Y-domain pixels with actual contrast greater than the preset contrast. The target bounding box region is obtained from the image acquired by the endoscope based on the position of the target Y-domain pixel.

[0015] Thirdly, the present invention provides an endoscope, which includes an endoscope camera system, an image processing system, an illumination system, and an endoscope marker as described in any of the above embodiments; the endoscope camera system and the image processing system are communicatively connected, the illumination system operates according to preset light power parameters, and the image processing system is used to execute the endoscope image correction method as described in any of the above embodiments.

[0016] This invention provides an endoscopic marker, an endoscopic image correction method, and an endoscope. The endoscope includes an endoscopic camera system, an image processing system, an illumination system, and an endoscopic marker. The endoscopic camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters. The endoscopic marker includes a color temperature correction region and a color difference correction region. The color difference correction region includes at least one preset color patch for characterizing the target tissue. The endoscopic image correction method includes: if a preset calibration command is detected, acquiring at least one endoscopic image obtained by the endoscopic camera system acquiring the endoscopic marker; performing region segmentation on the endoscopic image to obtain a target marker frame region corresponding to the endoscopic marker; wherein, the target marker frame region includes a first marker corresponding to the color temperature correction region. The first calibration method calculates a first calibration parameter based on the difference between the channel values ​​of each channel of the first pixel contained in the first calibration region; the second calibration parameter is calculated based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second calibration region; the first calibration parameter and the second calibration parameter are used as the imaging parameters of the endoscope. The above endoscope image correction method can simultaneously determine the first calibration parameter and the second calibration parameter through a single preset calibration command. The first calibration parameter can be used to determine the ambient light source information for color temperature correction, and the second calibration parameter can be used to determine the color difference information of the endoscope. This method can effectively solve the problem of color temperature and color inconsistency caused by lens differences between multiple devices and improve the realism of the image. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an endoscope marker according to an embodiment of the present invention; Figure 2 This is a structural diagram of an endoscope marker according to an embodiment of the present invention; Figure 3 This is a schematic diagram of another endoscopic marker according to an embodiment of the present invention; Figure 4 This is a structural diagram of another endoscopic marker according to an embodiment of the present invention; Figure 5 This is a flowchart of an endoscopic image correction method according to an embodiment of the present invention; Figure 6This is a structural block diagram of an optional endoscope according to an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] In a first aspect, the present invention provides an endoscopic marker; exemplarily, Figure 1 This is a schematic diagram of an endoscope marker according to an embodiment of the present invention. Figure 2 This is a structural diagram of an endoscopic marker according to an embodiment of the present invention, such as... Figure 1 , Figure 2 As shown, an endoscope marker is fitted onto the endoscope body of the endoscope imaging system. The endoscope marker is used for color and color temperature correction of the acquired endoscope images. The bottom of the endoscope marker has a color temperature correction area 100 and a color difference correction area 200. The color temperature correction area 100 is used to correct the endoscope's white balance parameters, and the color difference correction area 200 is used to correct the endoscope's color difference parameters. It includes at least one preset color patch for characterizing the target tissue, with a pre-set preset color. The surface of the endoscope marker is a uniform matte surface. Its optical characteristics include at least one of the following: matte diffuse reflection, gloss ≤3Gu at 60°, and reflectivity deviation ≤5% at a reflection angle of 0-80°. This surface is a high-precision uniform matte surface that is almost non-reflective, completely diffuse, and has almost the same brightness from any angle, effectively reducing ambient light reflection interference and improving calibration accuracy.

[0021] Endoscopes in related technologies have the problem that the endoscope itself does not support the local storage of key optical parameters (such as color temperature); this problem causes that even different endoscopes of the same model have significant inconsistencies in color performance (especially color temperature / white balance) due to their inherent slight optical differences. This inconsistency reduces the comparability of images when multiple endoscopes are used alternately and the diagnostic experience of doctors.

[0022] To address the aforementioned issues, in this embodiment, an endoscope marker is fitted onto the endoscope body of the endoscope imaging system. During endoscope use, color difference correction and color temperature correction can be performed simultaneously by capturing an image of the endoscope marker. Specifically, in the captured endoscope image, the optical characteristics of the endoscope marker itself provide highly stable diffuse reflection, allowing ambient light information to be captured based on the color temperature correction area 100 within the endoscope marker. Furthermore, the color difference correction area 200 within the endoscope marker includes at least one preset color block for characterizing the target tissue. This preset color block has a pre-set color, allowing lens color difference correction of the endoscope lens based on the color difference between the preset color block and the actual color of the endoscope image. This effectively solves the color inconsistency problem caused by lens differences and changes in ambient light between multiple devices, improving the realism of image colors.

[0023] In one embodiment, the endoscope includes an endoscope camera system, an image processing system, an illumination system, and endoscope markers. The endoscope camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters. The endoscope markers include a color temperature correction area and a color difference correction area, and the color difference correction area includes at least one preset color patch for characterizing the target tissue. When a preset command is triggered, the illumination system operates according to the preset light power, and the image processing system acquires at least one endoscope image obtained by the endoscope camera system from the endoscope markers through the communication connection with the endoscope camera system. Further, ambient light source information is captured based on the color temperature correction area 100 in the endoscope markers. Simultaneously, the endoscope lens is chromatic aberration corrected based on the color difference between the preset color of the preset color patch and the actual color of the endoscope image. By simultaneously performing chromatic aberration correction and color temperature correction on the endoscope through a single image of the endoscope markers, the problem of color inconsistency caused by lens differences and changes in ambient light sources among multiple devices can be effectively solved, improving the realism of image colors.

[0024] For example, the endoscope markers are adapted to the visible light imaging band of the endoscope (400-700nm) and the spectral response characteristics of the medical endoscope lens. The reflectivity of the preset color blocks matches the spectral characteristics of human mucosa / blood. The endoscope markers meet the requirements of diffuse reflection without specular reflection and fluorescence to avoid ultraviolet interference from the endoscope's cold light source. In addition, the endoscope markers meet the requirements of matte low gloss to adapt to close-range endoscopic imaging.

[0025] For example, the endoscope marker material can be printable / injection moldable medical-grade silicone or medical-grade ABS / PC plastic, and can withstand 500 or more wipings with medical alcohol without fading or peeling.

[0026] For example, the endoscopic markers are free of fluorescent whitening agents and do not emit fluorescence under 365nm ultraviolet light, in order to avoid interference from the ultraviolet components of the endoscopic cold light source with imaging.

[0027] For example, the color difference correction area 200 may include multiple preset color blocks for characterizing target tissues, which may include hemoglobin, lipids, hydrated tissues, etc.; the multiple preset color blocks for characterizing target tissues are set in a way that combines clinical histological features to correct visual presentation deviations of blood and tissue colors, suppress excessive reflectivity in other specific tissues (specific tissues may include, for example, fat) and / or provide color baseline support for judging tissue health status (such as oxidation level, inflammation or ischemic signs).

[0028] Specifically, taking the use of a medical bronchoscope as an example, the color difference correction area 200 of the endoscope marker is set to match the color characteristics of deoxyhemoglobin (dark red), hemoglobin (bright red), submucosal blood vessels (true red), and moist mucosa (pink). In view of this, as an exemplary embodiment, the color difference correction area 200 includes at least one of a first preset color block, a second preset color block, a third preset color block, and a fourth preset color block; the color of the first preset color block is the color of deoxyhemoglobin; the color of the second preset color block is the color of hemoglobin (bright red); the color of the third preset color block is the color of submucosal blood vessels (true red); and the color of the fourth preset color block is the color of moist mucosa (pink).

[0029] In the above embodiment, the color difference correction area 200 in the endoscopic marker includes at least one of a first preset color block, a second preset color block, a third preset color block, and a fourth preset color block; the color of the first preset color block is the color of deoxyhemoglobin; the color of the second preset color block is the color of bright red hemoglobin; the color of the third preset color block is the color of true red submucosal blood vessels; and the color of the fourth preset color block is the color of pink moist mucosa. Therefore, lens color difference correction can be performed on the endoscopic lens individually or jointly based on at least the first color difference between the actual endoscopic image of the first preset color block and the color of deoxyhemoglobin, the second color difference between the actual endoscopic image of the second preset color block and the color of bright red hemoglobin, the third color difference between the actual endoscopic image of the third preset color block and the color of true red submucosal blood vessels, and the fourth color difference between the actual endoscopic image of the fourth preset color block and the color of pink moist mucosa. This can effectively solve the problem of color inconsistency between multiple devices caused by lens differences and changes in ambient light, and improve the realism of image colors.

[0030] For example, the nominal LAB value of the preset color block is the preset LAB value; wherein, the preset LAB value may be the LAB value corresponding to the endoscope image acquired when the illumination system of the endoscope is working according to the preset light power parameters.

[0031] For example, the actual RGB value of the preset color block is the nominal RGB value.

[0032] In one embodiment, Figure 3 This is a schematic diagram of another endoscopic marker according to an embodiment of the present invention. Figure 4 This is a structural diagram of another endoscopic marker according to an embodiment of the present invention; as shown Figure 3 , Figure 4 As shown, the color difference correction area 200 includes a first preset color block 210, a second preset color block 220, a third preset color block 230, and a fourth preset color block 240; the color of the first preset color block 210 is the color of deoxyhemoglobin; the color of the second preset color block 220 is the color of bright red hemoglobin; the color of the third preset color block 230 is the color of bright red submucosal blood vessels; and the color of the fourth preset color block 240 is the color of pink moist mucosa.

[0033] In this embodiment, the color of the first preset color block 210 is the color of deoxyhemoglobin to adapt to venous blood / hypoxic mucosa and serves as a dark tone correction anchor point.

[0034] For example, the preset LAB values ​​for the deoxyhemoglobin color of the first preset color patch 210 are L=22.1, A=35.7, and B=14.3. For example, the deoxyhemoglobin color of the first preset color block 210 is a nominal RGB value, specifically R=99, G=34, B=40, to match the spectral characteristics of human deoxyhemoglobin, which has strong absorption in the blue-green band and weak absorption in the red band.

[0035] In this embodiment, the second preset color block 220 is the bright red color of hemoglobin to match venous blood / hypoxic mucosa, serving as the red-toned main correction anchor point.

[0036] For example, the preset LAB values ​​for the hemoglobin red color of the second preset color block 220 are L=45.2, A=74.8, and B=52.6. For example, the hemoglobin red color of the second preset color block 220 is the nominal RGB value, specifically R=211, G=31, B=41, so as to restore the bright red transparency of arterial blood through the high proportion of red channel and the extremely low proportion of green and blue channel.

[0037] In this embodiment, the third preset color block 230 is a bright red color for submucosal blood vessels, which is adapted to submucosal blood vessels and is a pure red correction anchor point.

[0038] For example, the preset LAB values ​​of the submucosal blood vessel bright red color of the third preset color block 230 are L=38.5, A=52.1, and B=32.8.

[0039] For example, the submucosal blood vessel positive red color of the third preset color block 230 is the nominal RGB value, specifically R=167, G=43, B=54, in order to suppress yellow band reflection, enhance red band reflection, correct the yellow bias of blood vessels in endoscopic imaging, and serve as a pure red correction anchor point to solve lens channel crosstalk.

[0040] In this embodiment, the color of the fourth preset color block 240 is a moist mucosal pink, which is adapted to the endoscopic background mucosa and serves as the main anchor point of the background base color.

[0041] For example, the fourth preset LAB value of the wet mucous membrane pink color of the fourth preset color block 240 is L=79.1, A=23.8, and B=14.6.

[0042] For example, the fourth preset color patch 240, wet mucosa pink, has a nominal RGB value, specifically R=240, G=182, B=179, to simulate the spectral characteristics of wet mucosa without absorption peaks through medium continuous reflectance across the entire band, covering the mainstream background color of endoscopy and providing a benchmark for light-colored color correction.

[0043] As an exemplary embodiment, the first preset color block 210, the second preset color block 220, the third preset color block 230, and the fourth preset color block 240 are arranged in an array at the bottom of the endoscope marker, and the array center of the first preset color block 210, the second preset color block 220, the third preset color block 230, and the fourth preset color block 240 is the geometric center of the endoscope marker; the side length or diameter of the first preset color block 210, the second preset color block 220, the third preset color block 230, and the fourth preset color block 240 is within 3-5mm, and the spacing between the first preset color block 210, the second preset color block 220, the third preset color block 230, and the fourth preset color block 240 is greater than or equal to 1mm.

[0044] In this embodiment, the side length or diameter of the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 in the color difference correction area 200 of the endoscope marker is within 3-5mm, and the spacing between the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 is greater than or equal to 1mm, so as to meet the geometric size requirements of the endoscope marker.

[0045] In one embodiment, the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 of the color difference correction area 200 in the endoscope marker are squares, and the side lengths of the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 are any values ​​in the range of [3mm, 5mm], which satisfies the geometric size requirements of the endoscope marker.

[0046] In one embodiment, the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 of the color difference correction area 200 in the endoscope marker are circular, and the diameters of the first preset color block 210, the second preset color block 220, the third preset color block 230 and the fourth preset color block 240 are any values ​​in the range of [3mm, 5mm], which satisfies the geometric size requirements of the endoscope marker.

[0047] Secondly, according to an embodiment of the present invention, an embodiment of an endoscopic image correction method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0048] In one embodiment, the endoscope includes an endoscope camera system, an image processing system, an illumination system, and endoscope markers. The endoscope camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters. The endoscope markers include a color temperature correction area and a color difference correction area. The color difference correction area includes at least one preset color patch for characterizing the target tissue.

[0049] For example, the endoscope also includes an illumination system that is communicatively connected to an image processing system. When the illumination system receives an illumination command transmitted by the image processing system, it operates according to preset light power parameters.

[0050] As a possible implementation, the color temperature correction region of the endoscopic marker is used to provide a highly neutral and stable diffuse reference.

[0051] As a possible implementation, the color correction module of the endoscopic marker includes a preset color block for characterizing the target tissue. The nominal color of the preset color block is a preset color that conforms to industry color standards and specifications for the target tissue as it appears in the endoscope.

[0052] As a possible implementation, the color correction module of the endoscopic marker includes multiple preset color blocks for characterizing target tissues; wherein, the target tissues may include hemoglobin, lipids, hydrated tissues, etc.; the nominal color of the preset color blocks is the preset color of the target tissue as it appears in the endoscope in accordance with industry color standards; the setting method of multiple preset color blocks characterizing target tissues, the preset color block design combined with clinical histological characteristics, can correct the visual presentation deviation of blood and tissue colors, suppress excessive reflectivity areas of other specific tissues (specific tissues may include, for example, fat) and / or provide color baseline support for judging tissue health status (such as oxidation level, signs of inflammation or ischemia).

[0053] As a possible implementation, the color correction module for endoscopic markers includes four preset color patches for characterizing the target tissue.

[0054] This embodiment provides an endoscopic image correction method. Figure 5 This is a flowchart of an endoscopic image correction method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: Step S101: If a preset calibration command is detected, acquire at least one endoscopic image obtained by the endoscopic camera system from the endoscopic markers.

[0055] For example, the preset calibration command can be a color calibration command; wherein, the color calibration command can be triggered by the operator operating the endoscope system or can be triggered automatically by the endoscope system.

[0056] As a possible implementation, the preset calibration command could be a white balance command.

[0057] For example, if a preset calibration command is detected, the image processing unit controls the lighting system to operate according to preset light power parameters through communication with the endoscope camera system and the lighting system, and acquires an image captured by the endoscope camera system under the preset light power parameters, which includes at least the endoscope markers, as the endoscope acquisition image.

[0058] For example, endoscopic images can be captured by an endoscopic camera system before the procedure.

[0059] For example, images acquired by the endoscope may be in the form of RAW images.

[0060] As a possible implementation, in order to overcome the noise effect that may be caused by a single frame of endoscopic image acquisition, in this invention, multiple images obtained by the endoscopic camera system from endoscopic markers can be acquired as endoscopic images.

[0061] As a possible implementation, N consecutive endoscopic images can be captured to overcome noise; where N is a positive integer.

[0062] As a possible implementation, five consecutive frames of endoscopic images can be captured to overcome noise.

[0063] Step S102: Perform region segmentation on the endoscope-acquired image to obtain the target marker box region corresponding to the endoscope marker; wherein, the target marker box region includes a first marker region corresponding to the color temperature correction region and a second marker region corresponding to the color difference correction region.

[0064] After obtaining the endoscope-acquired image, the endoscope-acquired image is segmented to obtain the target marker box region corresponding to the endoscope marker; the target marker box region includes the first marker region corresponding to the color temperature correction region and the second marker region corresponding to the color difference correction region.

[0065] In this invention, the difference between the endoscope marker and its surrounding environment is usually large. The target marker box area corresponding to the endoscope marker is represented in the image as having a specific shape distinction and / or a relatively obvious edge distinction from the environment where the endoscope is located. Therefore, in one embodiment, the region segmentation of the endoscope-acquired image can be achieved by edge detection to obtain the target marker box area corresponding to the endoscope marker.

[0066] Specifically, as a possible implementation, the target bounding box region corresponding to the endoscope marker is presented in the image with relatively high contrast. The endoscope-acquired image in the Y-domain of the YUV space has sufficient brightness information. The region segmentation of the endoscope-acquired image can be achieved by detecting the bounding box on the Y-domain image based on the contrast information, thereby obtaining the target bounding box region.

[0067] As a possible implementation, the target bounding box region corresponding to the endoscopic marker appears to have a specific shape in the image. The region of the endoscopic image can be segmented by image segmentation methods such as shape matching or edge detection to obtain the target bounding box region.

[0068] For example, the target bounding box region obtained by region segmentation is denoted as R.

[0069] After obtaining the target marking box region, the target marking box region is further divided into a first marking region corresponding to the color temperature correction region and a second marking region corresponding to the color difference correction region; the specific division method of the first marking region and the second marking region can refer to the content disclosed in the above embodiments, and will not be repeated here.

[0070] For example, the first labeled region obtained after region segmentation is denoted as R. wb The second marked region is denoted as R. cc .

[0071] For example, after obtaining the second marked area, for the second marked area including multiple preset color blocks, the second marked area can be further divided into regions to obtain each preset color block; the method for dividing the second marked area can refer to the content disclosed in the above embodiments, and will not be repeated here.

[0072] Step S103: Calculate the first correction parameter based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked region.

[0073] As mentioned above, the color temperature correction area is used to provide a highly neutral and stable diffuse reflection reference, and the lighting system operates according to preset light power parameters, so the ambient light source of the endoscope remains unchanged. Therefore, in this invention, the first correction parameter is calculated based on the difference between the channel values ​​of each channel of the first pixel contained in the first marking area. The ambient light source information provided by the lighting system can be captured through the first correction parameter to perform color temperature correction on the endoscope to adapt to the ambient light source information.

[0074] In one embodiment, when calculating the first correction parameter based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked region, any one of the channels in the first marked region can be used as a reference channel, and the first correction parameter can be calculated by the difference between the other channels and the reference channel, so that when the endoscope obtains an endoscopic image using the first correction parameter, the white area appears as a neutral color.

[0075] In one embodiment, for acquiring multiple endoscopic images obtained by the endoscopic camera system from endoscopic markers, a first correction parameter can be calculated for each endoscopic image, and the first correction parameter can be averaged to obtain the final first correction parameter.

[0076] In one embodiment, when acquiring multiple endoscopic images obtained by the endoscopic camera system from endoscopic markers, if there is a case where the channel value corresponding to other channels in the endoscopic images other than the reference channel is zero when calculating the first correction parameter, the endoscopic images with a channel value of zero corresponding to the reference channel are discarded.

[0077] The first correction parameter is calculated based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked area. This parameter can be used to correct the color temperature of the endoscope based on the highly neutral and stable diffuse reflection reference provided by the endoscope marker. When the endoscope image is subsequently corrected using the first correction parameter, the illumination system always operates according to the preset light power parameter. Since the first correction parameter captures the ambient light source information provided by the illumination system, the endoscope can be color-corrected to adapt to the ambient light source information.

[0078] Step S104: Calculate the second correction parameter based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked area.

[0079] In this invention, the endoscope is simultaneously corrected for color temperature and color difference based on the color correction module of the endoscope markers in the images acquired by the endoscope.

[0080] As described above, the color correction module of the endoscope marker includes at least one preset color block for characterizing the target tissue. The nominal color of the preset color block is the preset color of the target tissue as it appears in the endoscope in accordance with industry color standards. Therefore, in this embodiment, the second correction parameter is calculated based on the nominal channel value of the second pixel corresponding to the preset color block, using the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marker area as a reference.

[0081] In one embodiment, for a single preset color block, a second correction parameter can be calculated based on the channel value difference between the actual channel value and the nominal channel value of the preset color block.

[0082] In one embodiment, for multiple preset color blocks, the color difference deviation can first be calculated based on the channel value difference between the actual channel value and the nominal channel value of the preset color block. Then, based on the color difference deviation, each preset color block is assigned a corresponding weight vector according to the severity of the color difference. Finally, with the optimization goal of relatively balanced channel values ​​of each preset color block, optimization is performed based on the weight vector, the actual channel value and the nominal channel value of each preset color block, and the optimization result is used as the second correction parameter.

[0083] In one embodiment, for multiple preset color blocks, the color difference deviation can first be calculated based on the channel value difference between the actual channel value and the nominal channel value of the preset color block. Then, based on the color difference deviation, each preset color block is assigned a corresponding weight vector according to the severity of the color difference. Finally, with the goal of minimizing the sum of the errors between the actual channel value and the nominal channel value of all preset color blocks, optimization is performed based on the weight vector, the actual channel value and the nominal channel value of each preset color block, and the optimization result is used as the second correction parameter.

[0084] The method described above, which calculates the second correction parameter based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked area, can reflect the lens chromatic aberration during endoscopic imaging by showing the difference between the standard nominal value provided by the preset color block and the actual value of the preset color block. Color correction of the endoscope based on the second correction parameter can improve the influence of lens chromatic aberration and enhance the realism of image colors.

[0085] Step S105: Use the first correction parameter and the second correction parameter as the imaging parameters of the endoscope.

[0086] This invention provides an endoscopic image correction method. The endoscope includes an endoscopic camera system, an image processing system, an illumination system, and endoscopic markers. The endoscopic camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters. The endoscopic markers include a color temperature correction region and a color difference correction region. The color difference correction region includes at least one preset color patch for characterizing the target tissue. The endoscopic image correction method includes: if a preset calibration command is detected, acquiring at least one endoscopic image obtained by the endoscopic camera system acquiring the endoscopic markers; performing region segmentation on the endoscopic image to obtain a target marker frame region corresponding to the endoscopic markers; wherein the target marker frame region includes a first marker region corresponding to the color temperature correction region and a color difference correction region. The correction area corresponds to a second marked area; a first correction parameter is calculated based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked area; a second correction parameter is calculated based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked area; the first correction parameter and the second correction parameter are used as the imaging parameters of the endoscope; the above endoscope image correction method can simultaneously determine the first correction parameter and the second correction parameter through a preset calibration command, and can simultaneously determine the ambient light source information for color temperature correction through the first correction parameter and determine the color difference information of the endoscope through the second correction parameter, which can effectively solve the problem of color temperature and color inconsistency caused by lens differences between multiple devices and improve the realism of the image.

[0087] As an exemplary embodiment, the second correction parameter is calculated based on the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked region, including: obtaining the preset nominal LAB value corresponding to each preset color block; extracting the actual LAB value of each preset color block in the endoscopic image; calculating the color difference deviation corresponding to the preset color block based on the difference between the actual LAB value and the preset nominal LAB value; and calculating the second correction parameter based on the actual LAB value, the preset nominal LAB value, and the color difference deviation corresponding to each preset color block.

[0088] In one embodiment, after obtaining the endoscope-acquired images, the RAW image format of the endoscope-acquired images is converted to obtain the LAB values ​​of the pixels constituting each endoscope-acquired image.

[0089] Furthermore, in this embodiment, a second correction parameter is calculated based on the difference between the actual LAB value corresponding to each preset color block and the preset nominal LAB value, so as to perform color difference correction on the endoscope through the second correction parameter.

[0090] In one embodiment, the endoscopic markers include a color temperature correction region and a color difference correction region. The color difference correction region includes a preset color block for characterizing the target tissue. When calculating the second correction parameter based on the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marker region, the preset nominal LAB value corresponding to the preset color block is first obtained, and the actual LAB value is extracted from the endoscopic image. The second correction parameter is further determined based on the difference between the actual LAB value and the preset nominal LAB value.

[0091] As a possible implementation, the lightness difference, saturation difference, and hue difference between the actual LAB value and the preset nominal LAB value can be calculated based on the actual LAB value and the preset nominal LAB value. Furthermore, the color difference deviation value can be calculated based on the lightness difference, saturation difference, and hue difference, thereby determining the second correction parameter based on the color difference deviation value.

[0092] For example, the color difference deviation value can be calculated using equation (1):

[0093] In equation (1), This indicates the difference in brightness between the measured and nominal LAB values. This indicates the difference in saturation between the measured and nominal LAB values. This indicates the difference between the measured and nominal LAB values. These represent the weighting parameters, which can be predefined.

[0094] Furthermore, a second correction parameter is calculated based on the color difference deviation value.

[0095] As a possible implementation, after obtaining the color difference deviation value, the endoscope corrects the image acquired by the endoscope using the second correction parameter calculated from the color difference deviation value, and the difference between the actual LAB value obtained by correction and the preset nominal LAB value is less than the preset difference.

[0096] In one embodiment, the endoscopic markers include a color temperature correction region and a color difference correction region. The color difference correction region includes at least one preset color block for characterizing the target tissue. When calculating the second correction parameter based on the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marker region, the preset nominal LAB value corresponding to each preset color block is first obtained, and the actual LAB value of each preset color block is extracted from the endoscopic image. Furthermore, a weight vector is determined based on the difference between the actual LAB value and the preset nominal LAB value, and finally, a relatively balanced second correction parameter is fitted based on the weight vector.

[0097] In view of this, as an exemplary embodiment, the second correction parameter is calculated based on the actual LAB value, the preset nominal LAB value, and the color difference deviation corresponding to each preset color block, including: calculating the color difference weight vector of each preset color block based on the actual LAB value, the preset nominal LAB value, and the color difference deviation; and calculating the second correction parameter based on the color difference weight vector, the actual LAB value, the preset nominal LAB value, and the preset weighted CCM matrix.

[0098] In this embodiment, the color difference deviation of each preset color block can be calculated first using formula (1), and denoted as E1 to Ek respectively.

[0099] Furthermore, a weight vector is assigned to each preset color block based on the severity of the color difference; wherein, the severity of the color difference is inversely proportional to the value of the weight vector.

[0100] For example, the weight vector of each preset color block can be calculated using equation (2):

[0101] In equation (2), wk represents the weight vector corresponding to the k-th preset color block, and Ek represents the color difference deviation corresponding to the k-th preset color block. To prevent division by zero.

[0102] Furthermore, the second correction parameter is calculated based on the color difference weight vector, the actual LAB value corresponding to each preset color block, the preset nominal LAB value, and the preset weighted CCM matrix.

[0103] For example, the second correction parameter can be calculated using equation (3):

[0104] In equation (3), Indicates the second correction parameter. This represents the matrix of actual LAB values. This represents the preset nominal LAB value matrix.

[0105] .

[0106] As an exemplary embodiment, the calculation of the first correction parameter based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked region includes: extracting the pixel values ​​of each preset channel in the first marked region; calculating the average value of the pixel values ​​corresponding to each preset channel; and using one preset channel as a reference channel, calculating the difference between the average value of other preset channels and the average value of the reference channel as the first correction parameter.

[0107] In this embodiment, the preset channels are R channel, G channel, and B channel. That is, within the first marked area Rwb of the RAW format endoscopic image, the pixel values ​​of the pixels in the preset channels R channel, G channel, and B channel are extracted respectively.

[0108] For example, RAW format endoscopic images are represented in data as a Bayer array; since the G channel in the Bayer array includes Gr and Gb channels, the pixel values ​​in the Gr and Gb channels are taken as the pixel values ​​of the G channel.

[0109] Furthermore, the average value of each channel is calculated separately, and the average value of all R channel pixels is denoted as . It equals all The average value of all pixels (at their position in the Bayer array). The average value of the channel pixels (pixel values ​​within the Gr and Gb channels) is denoted as The average value of all B-channel pixels is denoted as .

[0110] Finally, using a preset channel as the reference channel, the difference between the average value of other preset channels and the average value of the reference channel is calculated as the first correction parameter.

[0111] For example, since the pixels in the G channel are closer to the colors perceived by the visual senses, the gain of the G channel is calculated as a reference channel to obtain the first correction parameter.

[0112] Specifically, the gain of the R channel relative to the G channel can be calculated using equation (4):

[0113] In equation (4), This indicates the gain of the R channel. This represents the average value of the R channel pixels. This represents the average value of all G-channel pixels.

[0114] Specifically, the gain of channel B relative to channel G can be calculated using equation (5):

[0115] In equation (5), This indicates the gain of channel B. This represents the average value of the B channel pixels. This represents the average value of all G-channel pixels.

[0116] In one embodiment, when acquiring an endoscopic image obtained by the endoscopic imaging system from endoscopic markers, if the image obtained from the current endoscopic image is... or If the value is zero, discard the current endoscopic image and acquire at least one new image obtained from the endoscopic markers by the endoscopic camera system, continuing until the value obtained from the current endoscopic image is zero. and Not zero.

[0117] In one embodiment, when acquiring N endoscopic images obtained by the endoscopic imaging system from endoscopic markers, the first correction parameters obtained from each endoscopic image can be averaged to obtain the final first correction parameter; wherein, N is a positive integer greater than 1. Specifically, as an exemplary embodiment, the endoscopic image correction method further includes: acquiring the first correction parameters corresponding to each endoscopic image; and averaging the first correction parameters to obtain the final first correction parameter.

[0118] Specifically, the first correction parameter can be obtained by calculating the multi-frame average gain of the R channel relative to the G channel in all endoscopic images using equation (6):

[0119] In equation (6), This represents the average gain across multiple frames for the R channel. The gain of the R channel is calculated from the i-th endoscopic image.

[0120] The final first correction parameter can be obtained by calculating the multi-frame average gain of the B channel relative to the G channel in all endoscopic images using equation (7):

[0121] In equation (7), This represents the multi-frame average gain of channel B. The gain of channel B is calculated from the i-th endoscopic image.

[0122] In one embodiment, when acquiring N endoscopic images obtained by the endoscopic imaging system from endoscopic markers, if the images obtained from the current endoscopic images are... or If the value is zero, the currently acquired endoscopic image is discarded, based on... and For non-zero endoscope-acquired images, the gain of the R channel relative to the G channel and the gain of the B channel relative to the G channel of each image are calculated. Further, the multi-frame average gain of the R channel relative to the G channel and the multi-frame average gain of the B channel relative to the G channel of each image are calculated as the first correction parameter.

[0123] As an exemplary embodiment, region segmentation of an endoscope-acquired image includes: obtaining a Y-domain image sequence corresponding to the endoscope-acquired image; performing region segmentation of the endoscope-acquired image based on the contrast of each pixel in the Y-domain image sequence to obtain target Y-domain pixels with actual contrast greater than a preset contrast; and obtaining a target bounding box region in the endoscope-acquired image based on the position of the target Y-domain pixels.

[0124] In this embodiment, for RAW format endoscopic images, the Y-domain image sequence corresponding to the endoscopic images is first obtained; for example, the Y-domain image sequence can be determined by obtaining the Y component from the RAW format endoscopic images through de-mosaicing and RGB to YUV conversion.

[0125] Furthermore, based on the contrast of each pixel in the Y-domain image sequence, the endoscopic image is segmented to obtain target Y-domain pixels with actual contrast greater than the preset contrast. Finally, the target bounding box region R is obtained from the image acquired by the endoscope based on the position of the target Y-domain pixel.

[0126] For example, the target bounding box region R can be represented by equation (8):

[0127] In equation (8), R represents the target bounding box region. This represents the coordinates of pixels within the target bounding box region. The position of the target Y-domain pixels can be determined, where w and h are the pixels corresponding to the width and height of the target bounding box area, depending on the endoscope resolution.

[0128] In one embodiment, a bounding box detection algorithm can be used to segment regions of images acquired by an endoscope. Specifically, as an exemplary embodiment, segmenting regions of images acquired by an endoscope further includes: obtaining a Y-domain image sequence corresponding to the endoscope image; inputting the Y-domain image sequence into a pre-trained bounding box region detection model, and using the bounding box region detection model to segment the Y-domain image sequence based on the shape of the target marked region to obtain the target marked region; wherein, the bounding box region detection model is trained based on a preset Y-domain image and preset position information; the preset Y-domain image contains a preset bounding box region, and the preset position information is used to represent the position information of the preset bounding box region in the Y-domain image; during the model training process, the preset Y-domain image is input into the pre-constructed preset detection model, and the model parameters of the preset detection model are continuously adjusted until the actual position information of the training marked region output by the preset detection model and the actual difference information of the preset position information satisfy the preset difference information.

[0129] Thirdly, the present invention provides an endoscope, the endoscope including an endoscope camera system, an image processing system, and an endoscope marker as described in any of the above embodiments; the endoscope camera system and the image processing system are communicatively connected, and the illumination system operates according to preset light power parameters; the image processing system is used to execute the endoscope image correction method as described in any of the above embodiments.

[0130] For example, the image processing system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory is used to store computer programs; and the processor is used to execute the methods of any of the above embodiments by running the computer programs stored in the memory.

[0131] Figure 6 This is a structural block diagram of an optional endoscope according to an embodiment of this application, such as... Figure 6 As shown, it includes a processor 10, a communication interface 20, a memory 30, and a communication bus 40. The processor 10, communication interface 20, and memory 30 communicate with each other via the communication bus 40. Memory 30 is used to store computer programs; When the processor 10 executes a computer program stored in the memory 30, it implements the method as described in any of the above embodiments.

[0132] Optionally, in this embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0133] The communication interface is used for communication between the aforementioned computer equipment and other devices.

[0134] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0135] The processor mentioned above can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0136] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0137] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. The device that implements any of the methods in the above embodiments can be a terminal device, such as a smartphone (e.g., an Android phone, an iOS phone), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, the terminal device may also include components that are more... Figure 6 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0138] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0139] As an exemplary embodiment, this application also provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the method steps of any one of the embodiments in this application at runtime.

[0140] Optionally, in this embodiment, the storage medium described above can be used to execute program code for the method steps of the embodiments of this application.

[0141] Optionally, in this embodiment, the storage medium may be located on at least one of the network devices in the network shown in the above embodiment.

[0142] Optionally, in this embodiment, the storage medium is configured to store methods for performing the above embodiments.

[0143] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated in this embodiment.

[0144] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0145] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0146] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods in the above embodiments.

[0147] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0148] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the solution provided in this embodiment, depending on actual needs.

[0149] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0150] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0151] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An endoscopic marker, characterized in that, The endoscope marker is fitted onto the endoscope body of the endoscope camera system. The endoscope marker is used to perform color correction and color temperature correction on the acquired endoscope images. The endoscope marker has a color temperature correction area and a color difference correction area at its bottom. The color temperature correction area is used to correct the white balance parameters of the endoscope, and the color difference correction area is used to correct the color difference parameters of the endoscope. It includes at least one preset color block for characterizing the target tissue. The preset color block has a preset color. The surface of the endoscope marker is a uniform matte surface.

2. The endoscopic marker as described in claim 1, characterized in that, The color difference correction area includes at least one of a first preset color block, a second preset color block, a third preset color block, and a fourth preset color block arranged in an array at the center of the endoscope marker; The color of the first preset color block is the color of deoxyhemoglobin; The second preset color block is the bright red color of hemoglobin; The third preset color block is the bright red color of submucosal blood vessels; The fourth preset color block is a moist mucous membrane pink color.

3. The endoscopic marker as described in claim 2, characterized in that, The optical characteristics of the surface of the endoscope marker are matte diffuse reflection, gloss ≤3Gu at 60°, and reflectivity deviation ≤5% at a reflection angle of 0-80°.

4. An endoscopic image correction method, characterized in that, The endoscope includes an endoscope camera system, an image processing system, an illumination system, and endoscope markers. The endoscope camera system and the image processing system are communicatively connected. The illumination system operates according to preset light power parameters. The endoscope markers include a color temperature correction area and a color difference correction area. The color difference correction area includes at least one preset color patch for characterizing the target tissue. The endoscopic image correction method includes: If a preset calibration command is detected, at least one endoscopic image acquired by the endoscopic camera system from the endoscopic markers is obtained. The image acquired by the endoscope is segmented to obtain the target marker box region corresponding to the endoscope marker; wherein, the target marker box region includes a first marker region corresponding to the color temperature correction region and a second marker region corresponding to the color difference correction region; The first correction parameter is calculated based on the difference between the channel values ​​of each channel of the first pixel contained in the first marked region; The second correction parameter is calculated based on the difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked area. The first correction parameter and the second correction parameter are used as the imaging parameters of the endoscope.

5. The endoscopic image correction method as described in claim 4, characterized in that, The second correction parameter is calculated based on the channel value difference between the actual channel value and the nominal channel value of the second pixel corresponding to the preset color block in the second marked area, including: Obtain the preset nominal LAB value corresponding to each preset color block; Extract the actual LAB value of each preset color block from the image acquired by the endoscope; The color difference deviation degree corresponding to the preset color block is calculated based on the difference between the actual LAB value and the preset nominal LAB value; The second correction parameter is calculated based on the actual LAB value corresponding to each preset color block, the preset nominal LAB value, and the color difference deviation.

6. The endoscopic image correction method as described in claim 5, characterized in that, The calculation of the second correction parameter based on the actual LAB value corresponding to each preset color block, the preset nominal LAB value, and the color difference deviation includes: The color difference weight vector of each preset color block is calculated based on the actual LAB value corresponding to each preset color block, the preset nominal LAB value and the color difference deviation. The second correction parameter is calculated based on the color difference weight vector, the actual LAB value corresponding to each preset color block, the preset nominal LAB value, and the preset weighted CCM matrix.

7. The endoscopic image correction method as described in claim 4, characterized in that, The calculation of the first correction parameter based on the differences between the channel values ​​of each channel of the first pixel contained in the first marked region includes: In the first marked area, the pixel values ​​of each preset channel are extracted respectively; Calculate the average value of the pixel values ​​corresponding to each preset channel; Using one of the preset channels as a reference channel, the difference between the average value of the other preset channels and the average value of the reference channel is calculated as the first correction parameter.

8. The endoscopic image correction method as described in any one of claims 4 or 6, characterized in that, The endoscopic image correction method further includes: Obtain the first correction parameter corresponding to each of the endoscopic images acquired; The first correction parameter is averaged and used as the final first correction parameter.

9. The endoscopic image correction method as described in claim 4, characterized in that, The process of segmenting the images acquired by the endoscope includes: Obtain the Y-domain image sequence corresponding to the images acquired by the endoscope; Based on the contrast of each pixel in the Y-domain image sequence, the endoscopic image is segmented to obtain target Y-domain pixels with actual contrast greater than the preset contrast. The target marker box region is obtained from the image acquired by the endoscope based on the position of the target Y-domain pixel.

10. An endoscope, characterized in that, The endoscope includes an endoscope camera system, an image processing system, an illumination system, and an endoscope marker as described in any one of claims 1 to 3; the endoscope camera system and the image processing system are communicatively connected, the illumination system operates according to preset light power parameters, and the image processing system is used to execute the endoscope image correction method as described in any one of claims 4 to 9.

Images