CN119946270A - Endoscopic lossless image compression and transmission method based on adaptive algorithm - Google Patents

Abstract

The invention relates to an endoscope lossless image compression and transmission method based on a self-adaptive algorithm, which relates to the technical field of endoscopes, wherein an endoscope is inserted into a patient, an image is transmitted to a display screen through a camera in the endoscope, the endoscope image is preprocessed, the preprocessed endoscope image is subjected to feature extraction, key features of the endoscope image are extracted for subsequent compression and transmission processes, a lossless compression algorithm is selected according to the extracted endoscope image features, a compression ratio is dynamically adjusted, compressed image data is transmitted as a continuous data stream according to the adjusted compression ratio, and data loss in the transmission process is processed by using a flow control and error correction technology.

Description

Endoscope lossless image compression and transmission method based on self-adaptive algorithm

Technical Field

The invention relates to the technical field of endoscopes, in particular to an endoscope lossless image compression and transmission method based on an adaptive algorithm.

Background

Endoscope technology is one of the important means in modern medical diagnosis and treatment, and can enter the human body through a natural duct or a small incision of the human body to observe and operate. The endoscope image has important significance in the field of medical imaging and plays a vital role in clinical diagnosis and treatment.

However, endoscopic images typically have high resolution and a large amount of detail, resulting in a large amount of data for the image, which presents difficulties for image transmission and storage.

The endoscope lossless image compression and transmission method based on the self-adaptive algorithm dynamically adjusts the compression ratio and transmission parameters according to the characteristics and requirements of images, and achieves better image quality and higher compression efficiency.

Disclosure of Invention

Aiming at the technical problems in the prior art, the invention provides an endoscope lossless image compression and transmission method based on an adaptive algorithm, and solves the problems in the background art by adjusting compression ratio and transmission parameters.

The technical scheme for solving the technical problems is as follows, the endoscope lossless image compression and transmission method based on the self-adaptive algorithm specifically comprises the following steps:

Step 101, inserting an endoscope into a patient, transmitting an image to a display screen through a camera in the endoscope, and preprocessing the image of the endoscope;

102, extracting features of the preprocessed endoscope image, and extracting key features of the endoscope image for subsequent compression and transmission processes;

Step 103, selecting a lossless compression algorithm according to the extracted endoscope image characteristics, and dynamically adjusting the compression ratio;

Step 104, transmitting the compressed image data as a continuous data stream according to the adjusted compression ratio, and using flow control and error correction technology to handle the data loss in the transmission process.

In a preferred embodiment, the preprocessing of the endoscopic image, including denoising and enhancing operations, to enhance the effect of subsequent compression and transmission, comprises the following specific steps:

Step A1, denoising, namely, carrying out mean value filtering on an endoscope image by taking pixels (x, y) as the center for the image I (x, y) by adjusting the size of a filtering window, wherein the specific calculation formula is as follows:

Wherein, Representing denoised image pixel values, I (x, y) representing original image pixel values, S _xy representing a filter window centered around (x, y), η representing the number of pixels within the window;

And A2, enhancing, namely expanding the gray dynamic range of the image by redistributing pixel gray levels through histogram equalization so as to improve the contrast of the image, wherein the specific calculation formula is as follows:

Where I' (x, y) represents the enhanced image pixel value, N _i represents the number of pixels with gray level I in the original image, L represents the number of gray levels, and M and N represent the width and height of the image, respectively.

In a preferred embodiment, the extraction of key features of the endoscopic image, including texture, edge and color features, will be used in the subsequent compression and transmission process, as follows:

And B1, extracting texture features by calculating a gray level co-occurrence matrix, and calculating the gray level co-occurrence matrix according to gray level relations and gray level quantity L among different pixel points in an image, wherein the specific calculation formula is as follows:

Wherein P (i, j) represents the number of pixels of gray level i adjacent to pixels of gray level j in the gray level co-occurrence matrix, n _ij represents the number of pixels of gray level i adjacent to pixels of gray level j, and L represents the number of gray levels;

And B2, extracting edge characteristics of the endoscope image by a Canny edge detection algorithm, and calculating gradients in the horizontal and vertical directions by using a Sobel operator, wherein a specific calculation formula is as follows:

Wherein Gradient (x, y) represents the Gradient intensity at coordinates (x, y) in the image, gradient _x (x, y) and Gradient _y (x, y) represent the gradients in the horizontal and vertical directions, respectively;

And B3, color histogram, namely dividing the color space of the image into different areas, and counting the number of pixels in each area, wherein the specific calculation formula is as follows:

wherein Histogram (c) represents the number of pixels of color cc in the color Histogram, delta function represents whether the determination condition is satisfied, I (x, y) represents the original image pixel value, c represents a specific color, and M and N represent the width and height of the image, respectively.

In a preferred embodiment, the edge feature is extracted by a Canny edge detection algorithm using the steps of:

step B201, noise suppression, namely smoothing the image by using a Gaussian filter to reduce noise influence;

Step B202, calculating gradients, namely calculating gradients of the smoothed image, and finding the gradient strength and the gradient direction of each pixel point in the image, wherein a specific calculation formula is as follows:

wherein Gradient _x (x, y) and Gradient _y (x, y) represent gradients in the horizontal and vertical directions, respectively, w _i,j represents the weight of the Sobe l operator, and I (x+i, y+j) represents the image pixel gray values of I pixels in the horizontal direction and j pixels in the vertical direction from the point (x, y);

step B203, performing non-maximum suppression on each pixel point in the gradient direction so as to reserve a local maximum point on the edge;

Step B204, double-threshold detection, namely dividing edge pixels into three types of strong edges, weak edges and non-edges according to two thresholds, wherein when the gradient value of the pixels is larger than a high threshold, the pixels are regarded as strong edges, and when the gradient value is between a low threshold and a high threshold, the pixels are regarded as weak edges, and when the gradient value is smaller than the low threshold, the pixels are regarded as non-edges;

And step B205, edge connection, namely, according to the strong edge pixels and the weak edge pixels connected with the strong edge pixels, edge connection is carried out, and a final edge image is obtained.

In a preferred embodiment, the dynamic adjustment of the compression ratio dynamically adjusts the compression parameters according to the importance of the image features and the achieved compression ratio to achieve better image quality and higher compression efficiency, and the specific steps are as follows:

And C1, adjusting compression parameters according to dictionary size adjustment parameters in a compression algorithm to control compression ratio, wherein a specific calculation formula is as follows:

P'=P×s

wherein, P' represents the adjusted parameter value, P is the original parameter value, s is the scaling factor, and the compression ratio is controlled by adjusting the size of the scaling factor s, when s is more than 1, the parameter value is increased to obtain a higher compression ratio, and when s is less than 1, the parameter value is reduced to obtain a lower compression ratio;

Step C2, multi-mode compression, namely dividing an image into different areas or objects, applying different compression parameters to each area or object, and flexibly adjusting the compression ratio;

And step C3, self-adaptive compression, namely automatically selecting different compression parameters according to the density and length change of the edge so as to realize the optimal compression effect of different areas.

In a preferred embodiment, the flow control further comprises the steps of:

Step D1, a sliding window protocol, wherein a sender maintains a sending window, a receiver maintains a receiving window, and the transmission rate is controlled by adjusting the size of the window and the position of the sliding window, wherein the size of the sending window represents the data volume continuously sent, and the position of the sliding window represents the data volume confirmed by the receiver;

And D2, a congestion control algorithm is used for avoiding network congestion by monitoring the network congestion state and adjusting the sending rate.

In a preferred embodiment, the error correction further comprises the steps of:

E1, forward error correction coding, namely adding redundant information into a data stream to enable a receiving party to detect and correct errors in the transmission process;

and E2, a self-adaptive error correction algorithm, namely dynamically adjusting an error correction strategy according to network quality and error rate, and adapting to different error rates by using different error correction codes so as to improve the reliability of transmission.

The invention has the beneficial effects that the endoscope is inserted into a patient, the image is transmitted to the display screen through the camera in the endoscope, the endoscope image is preprocessed, the preprocessed endoscope image is subjected to feature extraction, the key features of the endoscope image are extracted for subsequent compression and transmission processes, a lossless compression algorithm is selected according to the extracted endoscope image features, the compression ratio is dynamically adjusted, the compressed image data is transmitted as a continuous data stream according to the adjusted compression ratio, and the data loss in the transmission process is processed by using a flow control and error correction technology, so that better image quality and higher compression efficiency are realized.

Drawings

FIG. 1 is a flow chart of the method of the present invention.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

Example 1

The embodiment provides an endoscope lossless image compression and transmission method based on an adaptive algorithm as shown in fig. 1, which specifically comprises the following steps:

Step 101, inserting an endoscope into a patient, transmitting an image to a display screen through a camera in the endoscope, and preprocessing the image of the endoscope;

102, extracting features of the preprocessed endoscope image, and extracting key features of the endoscope image for subsequent compression and transmission processes;

Step 103, selecting a lossless compression algorithm according to the extracted endoscope image characteristics, and dynamically adjusting the compression ratio;

Step 104, transmitting the compressed image data as a continuous data stream according to the adjusted compression ratio, and using flow control and error correction technology to handle the data loss in the transmission process.

Preferably, the preprocessing of the endoscope image includes denoising and enhancing operations to improve the effect of subsequent compression and transmission, and the specific steps are as follows:

Step A1, denoising, namely, carrying out mean value filtering on an endoscope image by taking pixels (x, y) as the center for the image I (x, y) by adjusting the size of a filtering window, wherein the specific calculation formula is as follows:

Wherein, Representing denoised image pixel values, I (x, y) representing original image pixel values, S _xy representing a filter window centered around (x, y), η representing the number of pixels within the window;

And A2, enhancing, namely expanding the gray dynamic range of the image by redistributing pixel gray levels through histogram equalization so as to improve the contrast of the image, wherein the specific calculation formula is as follows:

Where I' (x, y) represents the enhanced image pixel value, N _i represents the number of pixels with gray level I in the original image, L represents the number of gray levels, and M and N represent the width and height of the image, respectively.

Preferably, the extraction of key features of the endoscopic image, including texture, edge and color features, will be used in the subsequent compression and transmission process, and the specific steps are as follows:

And B1, extracting texture features by calculating a gray level co-occurrence matrix, and calculating the gray level co-occurrence matrix according to gray level relations and gray level quantity L among different pixel points in an image, wherein the specific calculation formula is as follows:

Wherein P (i, j) represents the number of pixels of gray level i adjacent to pixels of gray level j in the gray level co-occurrence matrix, n _ij represents the number of pixels of gray level i adjacent to pixels of gray level j, and L represents the number of gray levels;

And B2, extracting edge characteristics of the endoscope image by a Canny edge detection algorithm, and calculating gradients in the horizontal and vertical directions by using a Sobel operator, wherein a specific calculation formula is as follows:

Wherein Gradient (x, y) represents the Gradient intensity at coordinates (x, y) in the image, gradient _x (x, y) and Gradient _y (x, y) represent the gradients in the horizontal and vertical directions, respectively;

And B3, color histogram, namely dividing the color space of the image into different areas, and counting the number of pixels in each area, wherein the specific calculation formula is as follows:

wherein Histogram (c) represents the number of pixels of color cc in the color Histogram, delta function represents whether the determination condition is satisfied, I (x, y) represents the original image pixel value, c represents a specific color, and M and N represent the width and height of the image, respectively.

Preferably, the edge feature extracting the edge feature of the endoscope image by the Canny edge detection algorithm comprises the following steps:

step B201, noise suppression, namely smoothing the image by using a Gaussian filter to reduce noise influence;

Step B202, calculating gradients, namely calculating gradients of the smoothed image, and finding the gradient strength and the gradient direction of each pixel point in the image, wherein a specific calculation formula is as follows:

wherein Gradient _x (x, y) and Gradient _y (x, y) represent gradients in the horizontal and vertical directions, respectively, w _i,j represents the weight of the Sobe l operator, and I (x+i, y+j) represents the image pixel gray values of I pixels in the horizontal direction and j pixels in the vertical direction from the point (x, y);

step B203, performing non-maximum suppression on each pixel point in the gradient direction so as to reserve a local maximum point on the edge;

Step B204, double-threshold detection, namely dividing edge pixels into three types of strong edges, weak edges and non-edges according to two thresholds, wherein when the gradient value of the pixels is larger than a high threshold, the pixels are regarded as strong edges, and when the gradient value is between a low threshold and a high threshold, the pixels are regarded as weak edges, and when the gradient value is smaller than the low threshold, the pixels are regarded as non-edges;

And step B205, edge connection, namely, according to the strong edge pixels and the weak edge pixels connected with the strong edge pixels, edge connection is carried out, and a final edge image is obtained.

Preferably, the dynamic adjustment of the compression ratio dynamically adjusts the compression parameters according to the importance of the image features and the achieved compression ratio, so as to achieve better image quality and higher compression efficiency, and specifically comprises the following steps:

And C1, adjusting compression parameters according to dictionary size adjustment parameters in a compression algorithm to control compression ratio, wherein a specific calculation formula is as follows:

P'=P×s

wherein, P' represents the adjusted parameter value, P is the original parameter value, s is the scaling factor, and the compression ratio is controlled by adjusting the size of the scaling factor s, when s is more than 1, the parameter value is increased to obtain a higher compression ratio, and when s is less than 1, the parameter value is reduced to obtain a lower compression ratio;

Step C2, multi-mode compression, namely dividing an image into different areas or objects, applying different compression parameters to each area or object, and flexibly adjusting the compression ratio;

And step C3, self-adaptive compression, namely automatically selecting different compression parameters according to the density and length change of the edge so as to realize the optimal compression effect of different areas.

Preferably, the flow control further comprises the steps of:

Step D1, a sliding window protocol, wherein a sender maintains a sending window, a receiver maintains a receiving window, and the transmission rate is controlled by adjusting the size of the window and the position of the sliding window, wherein the size of the sending window represents the data volume continuously sent, and the position of the sliding window represents the data volume confirmed by the receiver;

And D2, a congestion control algorithm is used for avoiding network congestion by monitoring the network congestion state and adjusting the sending rate.

Preferably, the error correction further comprises the steps of:

E1, forward error correction coding, namely adding redundant information into a data stream to enable a receiving party to detect and correct errors in the transmission process;

and E2, a self-adaptive error correction algorithm, namely dynamically adjusting an error correction strategy according to network quality and error rate, and adapting to different error rates by using different error correction codes so as to improve the reliability of transmission.

In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (9)

1. The endoscope lossless image compression and transmission method based on the self-adaptive algorithm is characterized by comprising the following steps of:

Step 101, inserting an endoscope into a patient, transmitting an image to a display screen through a camera in the endoscope, and preprocessing the image of the endoscope;

102, extracting features of the preprocessed endoscope image, and extracting key features of the endoscope image for subsequent compression and transmission processes;

Step 103, selecting a lossless compression algorithm according to the extracted endoscope image characteristics, and dynamically adjusting the compression ratio;

Step 104, transmitting the compressed image data as a continuous data stream according to the adjusted compression ratio, and using flow control and error correction technology to handle the data loss in the transmission process.

2. The method for compressing and transmitting lossless images of an endoscope based on an adaptive algorithm according to claim 1, wherein the preprocessing of the endoscopic image comprises denoising and enhancing operations, and comprises the following specific steps:

Step A1, denoising, namely, carrying out mean value filtering on an endoscope image by taking pixels (x, y) as the center for the image I (x, y) by adjusting the size of a filtering window, wherein the specific calculation formula is as follows:

Wherein, Representing denoised image pixel values, I (x, y) representing original image pixel values, S _xy representing a filter window centered around (x, y), η representing the number of pixels within the window;

And A2, enhancing, namely expanding the gray dynamic range of the image by redistributing pixel gray levels through histogram equalization so as to improve the contrast of the image, wherein the specific calculation formula is as follows:

Where I' (x, y) represents the enhanced image pixel value, N _i represents the number of pixels with gray level I in the original image, L represents the number of gray levels, and M and N represent the width and height of the image, respectively.

3. The method for compressing and transmitting an endoscopic lossless image based on an adaptive algorithm according to claim 2, wherein the key features of the extracted endoscopic image, including texture, edge and color features, are used in the subsequent compressing and transmitting process, specifically comprising the following steps:

step B1, texture features are extracted by calculating a gray level co-occurrence matrix according to gray level relations and gray level quantities among different pixel points in an image;

And B2, extracting edge characteristics of the endoscope image by a Canny edge detection algorithm, wherein a specific calculation formula is as follows:

Wherein Gradient (x, y) represents the Gradient intensity at coordinates (x, y) in the image, gradient _x (x, y) and Gradient _y (x, y) represent the gradients in the horizontal and vertical directions, respectively;

And B3, extracting color characteristics of the endoscope image through the color histogram, wherein the color characteristics are used for representing frequency distribution of different colors in the image.

4. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 3, wherein the texture feature is extracted by calculating a gray level co-occurrence matrix, and the gray level co-occurrence matrix is calculated according to a gray level relation and a gray level number L between different pixel points in an image, wherein a specific calculation formula is as follows:

Where P (i, j) represents the number of pixels of gray level i adjacent to pixels of gray level j in the gray level co-occurrence matrix, n _ij represents the number of pixels of gray level i adjacent to pixels of gray level j, and L represents the number of gray levels.

5. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 3, wherein the edge feature is extracted by a Canny edge detection algorithm using the steps of:

step B201, noise suppression, namely smoothing the image by using a Gaussian filter to reduce noise influence;

Step B202, calculating gradients, namely calculating gradients of the smoothed image, and finding the gradient strength and the gradient direction of each pixel point in the image, wherein a specific calculation formula is as follows:

Wherein Gradient _x (x, y) and Gradient _y (x, y) represent gradients in the horizontal and vertical directions, respectively, w _i,j represents the weight of the Sobel operator, and I (x+i, y+j) represents the image pixel gray values of I pixels in the horizontal direction and j pixels in the vertical direction from the point (x, y);

step B203, performing non-maximum suppression on each pixel point in the gradient direction so as to reserve a local maximum point on the edge;

Step B204, double-threshold detection, namely dividing edge pixels into three types of strong edges, weak edges and non-edges according to two thresholds, wherein when the gradient value of the pixels is larger than a high threshold, the pixels are regarded as strong edges, and when the gradient value is between a low threshold and a high threshold, the pixels are regarded as weak edges, and when the gradient value is smaller than the low threshold, the pixels are regarded as non-edges;

And step B205, edge connection, namely, according to the strong edge pixels and the weak edge pixels connected with the strong edge pixels, edge connection is carried out, and a final edge image is obtained.

6. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 3, wherein the color histogram divides the color space of the image into different regions, and counts the number of pixels in each region, and a specific calculation formula is as follows:

Wherein Histogram (c) represents the number of pixels of color c in the color Histogram, delta function represents whether the determination condition is satisfied, I (x, y) represents the original image pixel value, c represents a specific color, and M and N represent the width and height of the image, respectively.

7. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 1, wherein the dynamic adjustment of the compression ratio dynamically adjusts the compression parameters according to the importance of the image features and the achieved compression ratio, and specifically comprises the following steps:

And C1, adjusting compression parameters according to dictionary size adjustment parameters in a compression algorithm to control compression ratio, wherein a specific calculation formula is as follows:

P'=P×s

Wherein, P' represents the adjusted parameter value, P is the original parameter value, s is the scaling factor, the compression ratio is controlled by adjusting the size of the scaling factor s, when s is more than 1, the parameter value is increased to obtain a high compression ratio, when s is less than 1, the parameter value is reduced to obtain a low compression ratio;

Step C2, multi-mode compression, namely dividing the image into different areas or objects, applying different compression parameters to each area or object, and adjusting the compression ratio;

and step C3, self-adaptive compression, namely selecting different compression parameters according to the density and length change of the edge so as to realize the optimal compression effect of different areas.

8. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 1, wherein the flow control further comprises the steps of:

Step D1, a sliding window protocol, wherein a sender maintains a sending window, a receiver maintains a receiving window, and the transmission rate is controlled by adjusting the size of the window and the position of the sliding window, wherein the size of the sending window represents the data volume continuously sent, and the position of the sliding window represents the data volume confirmed by the receiver;

And D2, a congestion control algorithm is used for avoiding network congestion by monitoring the network congestion state and adjusting the sending rate.

9. The adaptive algorithm-based endoscopic lossless image compression and transmission method according to claim 1, wherein the error correction further comprises the steps of:

E1, forward error correction coding, namely adding redundant information into a data stream to enable a receiving party to detect and correct errors in the transmission process;

and E2, a self-adaptive error correction algorithm, namely dynamically adjusting an error correction strategy according to network quality and error rate, and adapting to different error rates by using different error correction codes.