A Confocal Endoscope Video Image Enhancement Method Based on Principal Component Analysis

Abstract

The present invention discloses a confocal endoscope video image enhancement method based on principal component analysis, comprising the following steps: extracting an effective region of the endoscopic image; dividing the effective region into a plurality of sub-regions, with the sub-regions overlapping each other; calculating the principal components of the sub-region image data based on the time series; calculating the correction factor of the sub-image region; combining the correction factors of the sub-image regions; and reconstructing the endoscopic image through the correction factor to obtain an enhanced reconstructed image. This method can adaptively calculate the correction factor according to the local region characteristics of the image based on the video stream, thereby removing the honeycomb structure existing in the confocal endoscope scanning system and improving the imaging quality of the reconstructed image.

Description

Technical Field

[0001] The invention belongs to the technical field of optical fiber bundle image processing, in particular to a confocal endoscope video image enhancement method based on principal component analysis. Background Art

[0002] Fluorescence confocal endoscopic imaging technology is a technology that combines fiber optic endoscopy technology with confocal scanning microscopy. It can perform non-invasive tissue examination on living tissue and is widely used in the field of medical imaging.

[0003] Fluorescence confocal endoscopic imaging technology uses a confocal scanning system to achieve imaging through a fiber bundle containing multiple optical fibers. Fiber bundles play an important role in endoscopic imaging and provide a way to visualize the cellular level for the diagnosis of a series of diseases in vivo. Typically, a fiber bundle contains a large number of fiber cores (usually up to 30,000), which can transmit and acquire optical signals simultaneously. However, the core spacing (i.e., cladding) causes information loss between fibers, and the distribution structure of the fibers appears in the acquired image, presenting a honeycomb periodic structure, affecting the readability of the image. Usually, a reference image is used to calculate the correction parameters of the image at the beginning, and a fixed correction coefficient is used to correct the image. However, during long-term use, due to external forces and other reasons, the position of the fiber interface end face of the confocal scanning system will change slightly, defocus will occur in some areas of the image, and the position and intensity of the honeycomb pattern will change. This makes it necessary to use a self-learning algorithm that can calculate the correction parameters in real time during use to eliminate the confocal honeycomb artifacts.

[0004] In the current processing method ("Optical fiber bundle image processing method and device. Publication number: CN107678153A Publication date: 2018.02.09 Application number: 201710959003.1"), before the confocal scanning system is started, the correction parameters are calculated using the reference image, and the image is corrected according to the correction parameters. The operation is relatively complicated, and after long-term use, the honeycomb pattern will reappear due to the displacement of the interface end face. Summary of the invention

[0005] The purpose of the present invention is to address the problems existing in the above-mentioned prior art and provide a confocal endoscopic video image enhancement method based on principal component analysis, which performs local analysis on the image based on time sequence and removes the image honeycomb structure.

[0006] The technical solution to achieve the purpose of the present invention is: a confocal endoscope video image enhancement method based on principal component analysis, the method comprising the following steps:

[0007] Extracting effective areas of endoscopic images;

[0008] Divide the effective region into a number of sub-regions, with the sub-regions overlapping each other;

[0009] Calculate the principal components of the sub-region image data based on the time series;

[0010] Calculate the correction factor for the sub-image region;

[0011] Combine the correction factors of the sub-image regions;

[0012] Reconstruct the endoscopic image with the correction factor to obtain an enhanced reconstructed image.

[0013] Furthermore, the extraction of the effective region of the endoscopic image specifically includes:

[0014] Set a threshold σ;

[0015] For each endoscopic image , based on the threshold σ, segment to obtain the corresponding mask ;

[0016] Perform an AND operation on all the masks and obtain the largest connected component of the masks;

[0017] Perform morphological dilation processing on the operation result to obtain the mask Mask of the effective region.

[0018] Furthermore, the division of the effective region into a number of sub-regions specifically includes:

[0019] According to the preset sub-region width wd and sub-region overlap size overlap, divide the effective region of the endoscopic image P with width w and height h into N small square sub-regions, where the number of small regions divided in the width direction is and the number of small regions divided in the height direction is :

[0020]

[0021]

[0022]

[0023] The starting position , , and width , height of the i-th small square sub-region image are:

[0024]

[0025]

[0026]

[0027]

[0028]

[0029]

[0030] According to the mask of the effective area, each small square sub-region i contains valid pixel points, and the small square sub-regions with a preset number of valid pixel points are screened out to form a region set R to be analyzed;

[0031] Extract the sequence numbers of all valid pixel points in each sub-region i in the region set R relative to the starting position of the sub-region, and form a position sequence .

[0032] Furthermore, calculating the principal component of the sub-region image data based on the time series specifically includes:

[0033] For the t-th endoscopic image, according to the position sequence of the sub-region, obtain the pixel values at the corresponding positions, and form a vector with a length of ;

[0034] In the time domain, perform PCA analysis on the data of the sub-region:

[0035] (1) Data preprocessing, normalize and take the logarithm of the original data at each moment of the same sub-region i:

[0036]

[0037] In the formula, represents the preprocessing result corresponding to the sub-region i of the t-th endoscopic image, is a fixed value of a minimum value, used to avoid the logarithm term being zero;

[0038] (2) Obtain the average value of the data of the sub-region over a period of time :

[0039]

[0040] In the formula, represents the total number of endoscopic images;

[0041] (3) Calculate the covariance matrix :

[0042]

[0043] (4) Obtain the covariance matrix Take the eigenvalues and the eigenvectors e:

[0044]

[0045]

[0046] where represents the j-th eigenvector obtained after decomposing the matrix of the i-th sub-region, represents the j-th eigenvalue obtained after decomposing the matrix of the i-th sub-region, j = 1, 2,..., , represents the number of eigenvectors or eigenvalues;

[0047] (5) Extract the principal component weights :

[0048] .

[0049] Further, the calculation of the correction factor for the sub-image region specifically includes:

[0050] Perform mean-shift clustering analysis on the minimum value in all to extract the clustering center ;

[0051] Represent the interference effect of artifacts on the small-region image as:

[0052]

[0053] According to the position serial number of the data in the region Convert into the fiber optic influence coefficient , and the calculation formula is:

[0054] .

[0055] Further, the merging of the correction factors for the sub-image regions specifically includes:

[0056] Calculate the shortest distance from the points in the overlapping region to the boundary of the sub-region image : :

[0057]

[0058] where represents the points in the overlapping region;

[0059] Calculate the sub-region image of the weight parameter :

[0060]

[0061]

[0062] Calculate the total weight parameter of the overlapping region :

[0063]

[0064] Calculate the final correction factor for each overlapping region:

[0065] .

[0066] Furthermore, reconstructing the endoscopic image through the correction factor to obtain an enhanced reconstructed image specifically includes:

[0067] Correct the original endoscopic image using the correction factor:

[0068]

[0069] In the formula, represents the corresponding corrected endoscopic image;

[0070] Obtain the maximum and minimum values of the endoscopic image and perform normalization processing on .

[0071] On the other hand, a confocal endoscopic video image enhancement system based on principal component analysis is provided. The system includes:

[0072] The first module is used to extract the effective region of the endoscopic image;

[0073] The second module is used to divide the effective region into several sub-regions, and the sub-regions overlap each other;

[0074] The third module is used to calculate the principal components of the sub-region image data based on the time series;

[0075] The fourth module is used to calculate the correction factor of the sub-image region;

[0076] The fifth module is used to merge the correction factors of the overlapping regions of the sub-image regions;

[0077] The sixth module is used to reconstruct the endoscopic image through the correction factor to obtain an enhanced reconstructed image.

[0078] On the other hand, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the confocal endoscope video image enhancement method based on principal component analysis is implemented.

[0079] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the confocal endoscope video image enhancement method based on principal component analysis is implemented.

[0080] Compared with the prior art, the remarkable advantages of the present invention are as follows:

[0081] (1) This method can automatically calculate the influence of fiber loss based on the video stream and correct the image accordingly. It does not require initial light intensity calibration of the fiber bundle, and the processing effect of this method on honeycombing will be enhanced as the video duration increases.

[0082] (2) This method can adaptively calculate the correction factor based on the local region features of the image from the video stream, so as to remove the honeycomb structure in the confocal endoscopic scanning system and improve the imaging quality of the reconstructed image.

[0083] (3) Compared with the neural network method, this method does not require training with labeled images, has strong interpretability, relatively simple calculation, and high efficiency.

[0084] The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 is a flowchart of a confocal endoscope video image enhancement method based on principal component analysis in an embodiment.

[0086] Figure 2 is a reference image of a video stream obtained in an embodiment.

[0087] Figure 3 is a valid region mask image obtained according to the video stream in an embodiment.

[0088] Figure 4 is a schematic diagram of dividing sub-regions according to the mask image in an embodiment, where Figure 4 in (a) is a schematic diagram of dividing the valid region into several sub-regions, Figure 4 in (b) is a schematic diagram of the relative position coordinates of pixel points in one of the sub-regions, Figure 4 in (c) is a schematic diagram of the brightness of pixel points in the sub-region, Figure 4 in (d) is a position sequence formed according to the sub-region coordinate position and brightness Schematic diagram of the luminance value vector ; Figure 4 In the small square area in (b) of, in the order from top to bottom and from left to right, the coordinates of each small square are (1,0), (1,1), (2,0), (2,1), (2,2), (2,3), (3,0), (3,1), (3,2), (3,3), (3,4), (3,5), (4,0), (4,1), (4,2), (4,3), (4,4), (4,5), (4,6), (5,0), (5,1), (5,2), (5,3), (5,4), (5,5), (5,6), (6,0), (6,1), (6,2), (6,3), (6,4), (6,5), (6,6), (7,0), (7,1), (7,2), (7,3), (7,4), (7,5), (7,6), (8,0), (8,1), (8,2), (8,3), (8,4), (8,5), (8,6), (9,0), (9,1), (9,2), (9,3), (9,4), (9,5), (9,6), (9,7), (10,0), (10,1), (10,2), (10,3), (10,4), (10,5), (10,6), (10,7), (10,8), (10,9), (10,10), (11,0), (11,1), (11,2), (11,3), (11,4), (11,5), (11,6), (11,7), (11,8), (11,9), (11,10), (11,11).

[0089] Figure 5 is the sub-region image in an embodiment, where Figure 5 (a) to (c) in are the images of a sub-region at different times.

[0090] Figure 6 is the corrected image obtained by principal component analysis of the sub-region in an embodiment.

[0091] Figure 7 is the overall correction parameter coefficient image in an embodiment.

[0092] Figure 8 is the image obtained by correcting Figure 1 in an embodiment. Specific embodiments

[0093] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0094] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present invention, then such directional indications are only used to explain the relative positional relationship, movement conditions, etc. between components in a certain specific posture (as shown in the attached drawings). If this specific posture changes, then the directional indications will also change accordingly.

[0095] In addition, if there are descriptions such as "first", "second", etc. involved in the embodiments of the present invention, then such descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0096] In one embodiment, in combination with Figure 1 , a confocal endoscope video image enhancement method based on principal component analysis is provided. The method includes the following steps:

[0097] S01, extracting the effective region of the endoscopic image;

[0098] S02, dividing the effective region into several sub-regions, and the sub-regions overlap with each other;

[0099] S03, calculating the principal components of the sub-region image data based on the time series;

[0100] S04, calculating the correction factor of the sub-image region;

[0101] S05, combining the correction factors of the sub-image regions;

[0102] S06, reconstructing the endoscopic image through the correction factor to obtain an enhanced reconstructed image;

[0103] S07, putting the newly captured image into the time-series image queue to be analyzed, and repeating step S03 every other period of time.

[0104] Here, the confocal endoscope scans the laser to the end face of the fiber bundle through a galvanometer. The laser is transmitted through the optical fiber to the object surface, and the fluorescence signal generated by the biological tissue is collected through the optical fiber to generate an image. The scanning range of the galvanometer is generally rectangular, while the cross-section of the fiber bundle is circular. The real effective region of the image only exists within the effective cross-section of the light beam (such as Figure 2As shown in the figure, in order to reduce the computational complexity and the interference of image information in irrelevant regions, it is first necessary to extract the effective region of the image. Since there is no fluorescence signal return in the invalid region, the brightness value of its points on the image is basically zero.

[0105] Furthermore, in one of the embodiments, the method for extracting the effective region of the endoscopic image described in S01 specifically includes:

[0106] S011, setting a threshold σ;

[0107] S012, for each endoscopic image , based on the threshold σ, segmenting to obtain the corresponding mask ;

[0108] S013, performing an AND operation on all masks;

[0109] S014, performing morphological processing (erosion operation) on the operation result to eliminate the influence of small holes and obtain the mask Mask of the effective region (as Figure 3 shown).

[0110] Furthermore, in one of the embodiments, the method for dividing the effective region into several sub-regions described in S02 specifically includes:

[0111] S021, according to the preset sub-region width wd and sub-region overlap size overlap, dividing the effective region of the endoscopic image P with width w and height h into N small square sub-regions, where in the width direction, it is divided into small regions, and in the height direction, it is divided into small regions:

[0112]

[0113]

[0114]

[0115] The starting position , , and width , height of the i-th small square sub-region image

[0116]

[0117]

[0118]

[0119]

[0120]

[0121]

[0122] S022. According to the mask of the effective area, each small square sub-region i contains effective pixel points, and the small square sub-regions with a preset number of effective pixel points are screened out (as Figure 4 shown), and a region set R to be analyzed is formed;

[0123] S023. Extract the sequence numbers of all effective pixel points in each sub-region i in the region set R relative to the starting position of the sub-region, and form a position sequence .

[0124] Furthermore, in one embodiment, the principal component algorithm is a method of data dimensionality reduction, which maps high-dimensional data into a low-dimensional space so that the variance between the coordinates of points in the low-dimensional space on the new coordinate axes (principal components) is as large as possible. PCA is widely used in data analysis in all walks of life and can be used for image data compression and feature dimensionality reduction of neural networks. In the present invention, the honeycomb influence coefficient can be approximately obtained by performing principal component analysis in the time domain.

[0125] Calculating the principal component of the sub-region image data based on the time series in S03 specifically includes:

[0126] For the t-th endoscopic image, convert the sub-image region data into a one-dimensional vector, and the process is as Figure 3 shown. According to the position sequence of the sub-region, read the pixel values at the corresponding positions and form a vector with a length of , where Metrix2Vector represents the operation of matrix to vector;

[0127] Metrix2Vector(Mi,Pvi)

[0128] Perform PCA analysis on the data of the sub-region in the time domain:

[0129] (1) Data preprocessing: Normalize and take the logarithm of the original data at each moment of the same sub-region i:

[0130]

[0131] In the formula, represents the preprocessing result corresponding to the sub-region i of the t-th endoscopic image, is a fixed value of a minimum value (1e-6) to avoid the logarithm term being zero;

[0132] (2) Obtain the data average value of the sub-region within a period of time :

[0133]

[0134] In the formula, represents the total number of endoscopic images;

[0135] (3) Calculate the covariance matrix :

[0136]

[0137] (4) Perform singular value SVD decomposition on the covariance matrix to obtain eigenvalues ( ) and eigenvectors :

[0138]

[0139]

[0140] (5) Select the vector with the largest eigenvalue as the principal component, and calculate the principal component weight of each sub-region image :

[0141] .

[0142] Further, in one of the embodiments, the calculating the correction factor of the sub-image region in S04 specifically includes:

[0143] The influence of artifacts on the small-region image can be expressed as follows:

[0144]

[0145] Wherein, is the original signal, is the influence of honeycomb artifacts. Since each region is small, in most of the time-series images (such as Figure 5 shown), can be approximately a constant distribution in space. Since the size of the sub-region is larger than the size of a single optical fiber, the signal has basically no loss at the center of the optical fiber. Therefore the maximum value of the coefficient for signal transmission within the region is 1, then:

[0146]

[0147]

[0148] When the pixel values in a small area are approximately a constant distribution, the processed data and the interference effect relationship can be expressed as:

[0149]

[0150] Therefore the minimum value of and the principal component will be relatively concentrated. Using the mean-shift clustering algorithm, the clustering center is extracted, then the vector of the interference effect can be expressed as:

[0151]

[0152] The calculated As Figure 6 shown, according to the serial number of the data in the region the Fi vector can be converted into an interference effect matrix :

[0153] i, )

[0154] is converted into the optical fiber influence coefficient, i.e., the correction coefficient The correction coefficient can be obtained through the following calculation:

[0155] .

[0156] Furthermore, in one of the embodiments, the correction factor for merging the sub-image regions in S05 is specifically: merging the correction factors of the overlapping regions of the sub-image regions (since there will be overlapping parts between each sub-region and other sub-regions, the calculation of the correction coefficient of the overlapping region needs to be mixed and superimposed based on the weight, and the farther away from the region boundary, the greater the weight), specifically including:

[0157] S051, calculate the closest distance from the points in the overlapping region to the boundary of the sub-region image

[0158]

[0159] In the formula, represents the coordinates of the point in the overlapping region relative to the origin of the i-th sub-region;

[0160] S052, calculate the weight parameter of the sub-region image :​

[0161]

[0162]

[0163] S053, Set the total image parameter weight Q to zero:

[0164]

[0165] where x and y are the coordinates of the pixel point relative to the origin of the entire image area.

[0166] S054, The number of weights of the sub-region Perform superposition calculation to calculate the total weight parameter of the overlapping region :

[0167]

[0168] S055, Calculate the final correction factor for each overlapping region:

[0169] .

[0170] Furthermore, in one embodiment, the step of reconstructing the endoscopic image by the correction factor in S06 to obtain an enhanced reconstructed image specifically includes:

[0171] S061, After calculating the overall correction factor (as Figure 7 shown), use the correction factor to correct the original endoscopic image:

[0172]

[0173] In the formula, represents the corresponding corrected endoscopic image;

[0174] S062, Obtain the maximum and minimum values of the endoscopic image and perform normalization on to ensure the consistency of the image brightness before and after correction. The final processed image result is as Figure 8 shown.

[0175] Furthermore, in one embodiment, S07 specifically includes:

[0176] S071, Form a queue for image analysis. Adopt the first-in, first-out strategy, put the newly captured image into the queue to be analyzed, and dequeue the image that was put into the queue first.

[0177] S072. When the number of newly entered images exceeds half, repeat step S03 to recalculate the calibration parameter C of the images so that it can adapt to the influence caused by the change of honeycomb artifacts.

[0178] In one embodiment, a confocal endoscope video image enhancement system based on principal component analysis is provided. The system includes:

[0179] A first module for extracting the effective region of the endoscopic image;

[0180] A second module for dividing the effective region into a plurality of sub-regions, and the sub-regions overlap with each other;

[0181] A third module for calculating the principal components of the sub-region image data based on the time series;

[0182] A fourth module for calculating the correction factor of the sub-image region;

[0183] A fifth module for combining the correction factors of the overlapping regions of the sub-image regions;

[0184] A sixth module for reconstructing the endoscopic image through the correction factor to obtain an enhanced reconstructed image.

[0185] For the specific limitations of the confocal endoscope video image enhancement system based on principal component analysis, reference can be made to the limitations of the confocal endoscope video image enhancement method based on principal component analysis in the above text, which will not be elaborated here. Each module in the above confocal endoscope video image enhancement system based on principal component analysis can be implemented in whole or in part by software, hardware and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0186] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it realizes:

[0187] Extracting the effective region of the endoscopic image;

[0188] Dividing the effective region into a plurality of sub-regions, and the sub-regions overlap with each other;

[0189] Calculating the principal components of the sub-region image data based on the time series;

[0190] Calculating the correction factor of the sub-image region;

[0191] Combining the correction factors of the sub-image regions;

[0192] Reconstruct the endoscopic image by the correction factor to obtain an enhanced reconstructed image.

[0193] For the specific limitations of each step, reference can be made to the limitations of the confocal endoscope video image enhancement method based on principal component analysis in the above text, which will not be elaborated here.

[0194] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it realizes:

[0195] Extract the effective region of the endoscopic image;

[0196] Divide the effective region into several sub-regions, and the sub-regions overlap each other;

[0197] Calculate the principal components of the sub-region image data based on the time series;

[0198] Calculate the correction factor of the sub-image region;

[0199] Merge the correction factors of the sub-image regions;

[0200] Reconstruct the endoscopic image by the correction factor to obtain an enhanced reconstructed image.

[0201] For the specific limitations of each step, reference can be made to the limitations of the confocal endoscope video image enhancement method based on principal component analysis in the above text, which will not be elaborated here.

[0202] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A confocal endoscope video image enhancement method based on principal component analysis, characterized in that, The method includes the following steps: Extract the effective region of the endoscopic image; Divide the effective region into a number of sub-regions, and the sub-regions overlap with each other; Calculate the principal components of the sub-region image data based on the time series; Calculate the correction factor of the sub-image region; Merge the correction factors of the sub-image regions; Reconstruct the endoscopic image with the correction factor to obtain an enhanced reconstructed image; The dividing the effective region into a number of sub-regions specifically includes: According to the preset sub-region width wd and sub-region overlap size overlap, the effective region of the endoscopic image P with width w and height h is divided into N small square sub-regions, where in the width direction, it is divided into small regions, and in the height direction, it is divided into small regions: ； ； ； The image of the i-th small square sub-region starting position , and width , height are as follows: ； ； ； ； ； ； According to the mask of the valid area, each small square sub-region i contains valid pixel points, and small square sub-regions with a preset number of valid pixel points are screened out to form a region set R to be analyzed; Extract the sequence numbers of all valid pixel points in each sub-region i in the region set R relative to the starting position of the sub-region, and form a position sequence from small to large ; The calculating the principal components of the sub-region image data based on the time series specifically includes: For the t-th endoscopic image, according to the position sequence of the sub-regions , obtain the pixel values at the corresponding positions, and form a vector with a length of ; Perform PCA analysis on the data of the sub-region in the time domain: (1) Data preprocessing, normalize and take the logarithm of the original data at each moment of the same sub-region i; ； In the formula, represents the preprocessing result corresponding to the sub-region i of the t-th endoscopic image, is a fixed value of a minimum value, which is used to avoid the logarithmic term being zero; (2)Calculate the data average value of the sub-region within a period of time : ； In the formula, represents the total number of endoscopic images; (3) Calculate the covariance matrix : ； (4) Obtain the covariance matrix Obtain the eigenvalues And the eigenvector e: ； ； In the formula, represents the j-th eigenvector obtained after decomposing the matrix of the i-th sub-region, represents the j-th eigenvalue obtained after decomposing the matrix of the i-th sub-region, where j = 1, 2,..., , represents the number of eigenvectors or eigenvalues; Extract the principal component weights : 。 2. The method for enhancing a confocal endoscope video image based on principal component analysis according to claim 1, wherein The extracting the effective region of the endoscopic image specifically includes: Set a threshold σ; For each endoscopic image , a corresponding mask is segmented based on the threshold σ ; Perform an AND operation on all masks and obtain the largest connected domain of the masks; Perform morphological dilation processing on the operation result to obtain the mask Mask of the effective region.

3. The method for enhancing a confocal endoscope video image based on principal component analysis according to claim 1, wherein The calculating the correction factor of the sub-image region specifically includes: For all the minimum value in perform mean-shift clustering analysis to extract the cluster centers ; The interference effect of artifacts on small-region images is expressed as: ； According to the position serial number of the data within the area Convert into the optical fiber influence coefficient , and the calculation formula is: 。 4. The confocal endoscope video image enhancement method based on principal component analysis according to claim 3, characterized in that, The merging the correction factors of the sub-image regions specifically includes: Calculate the shortest distance from the points in the overlapping area to the boundary of the sub-region image :​ ； In the formula, represents the points in the overlapping region; Calculating the weight parameter of the sub-region image as follows : ； ； Calculate the total weight parameter of the overlapping region : ； Calculate the final correction factor of each overlapping region: 。 5. The method for enhancing a confocal endoscope video image based on principal component analysis according to claim 4, wherein The reconstructing the endoscopic image with the correction factor to obtain an enhanced reconstructed image specifically includes: Correct the original endoscopic image with the correction factor; ； In the formula, represents the corresponding corrected endoscopic image; Obtain the maximum and minimum values of the endoscopic image and perform normalization on ​ 6. A confocal endoscope video image enhancement system based on the method according to any one of claims 1 to 5, characterized in that The system includes: A first module for extracting the effective region of the endoscopic image; A second module for dividing the effective region into a number of sub-regions, and the sub-regions overlap with each other; A third module for calculating the principal components of the sub-region image data based on the time series; A fourth module for calculating the correction factor of the sub-image region; A fifth module for merging the correction factors of the overlapping regions of the sub-image regions; A sixth module for reconstructing the endoscopic image with the correction factor to obtain an enhanced reconstructed image.

7. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 5.

Images