Image lossless transmission QoS guarantee method based on endoscope

Abstract

The invention relates to an endoscope-based image lossless transmission QoS (Quality of Service) guarantee method, in particular to the field of data transmission, which comprises the following steps of: segmenting a region of interest of an endoscope image and a background region of the endoscope image, distinguishing the region of interest and the background region of the endoscope image, realizing accurate cutting of the endoscope image, judging and defining a growth criterion according to the similarity among pixel points, and determining the quality of the endoscope image. The method comprises the following steps: respectively carrying out lossless compression coding and lossy compression coding on an interested region and a background region, defining a compression coding rule, synchronously marking a Gaussian filtering weighting process of an endoscope image by using a time window, improving the processing and transmission efficiency of the endoscope image, finely grouping the interested region and the background region of the endoscope image, and carrying out compression coding on the interested region and the background region of the endoscope image. According to the method, the data transmission efficiency and accuracy are improved, the image file header of the endoscope image is read, the endoscope image coefficient in the encoding process is subjected to inverse quantization and inverse downsampling, the interested area and the background area of the endoscope image are reconstructed, and connection is performed through the image file header to obtain the complete endoscope image.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and more specifically, to a method for ensuring QoS of lossless transmission of endoscopic images. Background Art

[0002] Transmitting the image data obtained during an endoscopic examination through a communication method facilitates remote doctors to diagnose and treat the condition. Since it is necessary to observe and record the details and characteristics of the lesion site, the transmission quality and efficiency of endoscopic images are crucial for the diagnosis result and the formulation of the treatment plan.

[0003] Currently, to improve the rapid transmission of data, virtual channels are created, each virtual channel corresponding to a priority level, allowing any one of them to be paused and restarted individually, while allowing the traffic of other virtual channels to pass through without interruption. The priority level of the queue can be identified by differential services code point (DSCP) or virtual local area network tag (VLAN Tag) or quality of services (QoS), etc., so as to complete the rapid data transmission work. However, due to the large amount of information in current endoscopic image data, it is usually only compressed and transmitted and then decoded and read. The movement and changes in endoscopic images are not carefully grouped, increasing unnecessary data transmission and processing workload, not only reducing the data transmission efficiency, but also affecting the integrity and accuracy of endoscopic images. Summary of the Invention

[0004] The present invention aims at the technical problems existing in the prior art, and provides a method for ensuring QoS of lossless transmission of endoscopic images to solve the problems proposed in the above background art.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A method for ensuring QoS of lossless transmission of endoscopic images includes the following steps:

[0006] S101: Segmenting the endoscopic image by the region growing method to obtain the region of interest of the endoscopic image and the background region of the endoscopic image;

[0007] S102: Compressing and encoding the region of interest of the endoscopic image and the background region of the endoscopic image, and denoising the compressed endoscopic image by using Gaussian filter weighting;

[0008] S103: During the Gaussian filtering and weighting process of the compressed endoscopic image, use a time window to synchronously mark the compressed endoscopic image to complete a detailed grouping of the region of interest and the background region of the compressed endoscopic image, and obtain a data packet for the region of interest of the image and a data packet for the background region of the image;

[0009] S104: Configure priorities for the data packet of the region of interest of the image and the data packet of the background region of the image based on the Qos technology;

[0010] S105: Receive the endoscopic image data packet based on the priority, read the endoscopic image data packet, perform inverse quantization and inverse downsampling on the endoscopic image coefficients during the encoding process, and reconstruct the region of interest of the endoscopic image and the background region of the endoscopic image to obtain a complete endoscopic image.

[0011] In a preferred embodiment, in step S101, the endoscopic image is segmented using the region growing method to obtain the region of interest of the endoscopic image and the background region of the endoscopic image, including the following steps: Set a seed point, use the seed point as the starting point of the region of interest, traverse the neighboring pixels of the seed point. When the pixel point meets the region growing criterion and has not been added to the region of interest, add it to the region of interest and use it as a new seed point to continue growing, and continuously iterate and grow until there are no pixel points that meet the region growing criterion, and finally obtain the region of interest of the endoscopic image and the background region of the endoscopic image.

[0012] In a preferred embodiment, when the pixel point meets the region growing criterion and has not been added to the region of interest, add it to the region of interest, including the following steps:

[0013] Use the gray value between pixel points as the region growing criterion. When the difference between the gray value of the pixel point and the gray value of the seed point in the region of interest is less than the set threshold, add the pixel point to the region of interest, where the threshold is set to 20.

[0014] Use the color difference between pixel points as the region growing criterion. When the difference between the color value of the pixel point and the color value of the seed point in the region of interest is less than the set difference threshold, add the pixel point to the region of interest, where the difference threshold is set to 5.

[0015] In a preferred embodiment, in step S102, perform lossless compression encoding on the region of interest of the endoscopic image, define the compression encoding rule, perform lossy compression encoding on the background region of the endoscopic image, and define the compression encoding rule.

[0016] In a preferred embodiment, the compression coding rule of the lossless compression coding is as follows: an optimal binary tree is constructed based on the pixel point frequencies within the region of interest of the endoscopic image, and the pixel points within the region of interest of the endoscopic image with higher frequencies are encoded with shorter codes, while the pixel points within the region of interest of the endoscopic image with lower frequencies are encoded with longer codes.

[0017] In a preferred embodiment, the compression coding rule of the lossy compression coding is as follows: the background region of the endoscopic image is converted to a frequency-domain representation through discrete cosine transform, and a quantization table is used to quantize the frequency-domain coefficients to reduce the detailed information of the high-frequency part of the background region of the endoscopic image.

[0018] In a preferred embodiment, the specific formula for Gaussian filtering weighting in step S102 is as follows:

[0019]

[0020] Where V f represents the denoising result after Gaussian filtering weighting, V i represents the value of the neighborhood points of the i-th pixel point in the region of interest and the background region, d i represents the distance from the neighborhood points of the i-th pixel point in the region of interest and the background region to the current point, and σ represents the standard deviation of the Gaussian distribution.

[0021] In a preferred embodiment, the marking of the time window in step S103 includes the following steps: a time stamp and a sequence number are provided through the time window, the marking process of the time window performs a detailed grouping on the region of interest of the endoscopic image and the background region of the endoscopic image, the object shape features in the region of interest of the endoscopic image and the background region of the endoscopic image are extracted through edge detection as the check codes for the detailed grouping, and the check codes are appended for parallel transmission of the endoscopic image.

[0022] In a preferred embodiment, in step S105, the endoscopic image data packet is read to obtain the distinction, size, and chromaticity information of the region of interest of the endoscopic image and the background region of the endoscopic image. The terminal analyzes the endoscopic image according to the compression coding rule, inverse-quantizes the endoscopic image coefficients during the coding process to restore the quality and data volume of the endoscopic image, and converts the inverse-quantized endoscopic image coefficients to uncompressed pixel point values through inverse transformation, and performs inverse downsampling on the chromaticity information of the endoscopic image. The restored quality and data volume of the endoscopic image, pixel point values, and chromaticity information are concatenated to obtain a complete endoscopic image.

[0023] The beneficial effects of the present invention are as follows: By setting a threshold and a difference threshold and performing accurate segmentation based on the grayscale value and color difference of pixel points, the region of interest and the background region are separated, realizing precise cutting of endoscopic images. By selecting and automatically generating seed points, automatic segmentation of the entire image is achieved, improving the processing and transmission efficiency of endoscopic images. The segmentation results are clearly marked through region annotation. Different compression and encoding rules are adopted for different regions of endoscopic images, reducing the data volume to a relatively small level. While reducing the data volume, important information and details of the region of interest and the background region are retained, improving the image quality. By using Gaussian filtering weighting to remove the noise existing under low-light conditions, the clarity and visualization effect of endoscopic images are enhanced, ensuring the real-time orderliness, data transmission correctness and integrity of the compression and transmission of the region of interest and the background region of endoscopic images. Errors and data loss during the transmission process are reduced through error handling, and the efficiency and accuracy of data transmission are improved through careful grouping and QoS technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0026] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "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 otherwise specifically defined.

[0027] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not elaborated in detail so as not to obscure the description of the present invention with unnecessary details. Therefore, the present invention 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 in this application.

[0028] This embodiment provides a method for guaranteeing QoS of lossless transmission of endoscopic images as shown in Figure 1 the following, which specifically includes the following steps:

[0029] S101: Segment the endoscopic image using the region growing method to obtain the region of interest of the endoscopic image and the background region of the endoscopic image;

[0030] Among the steps of S101, segmenting the endoscopic image using the region growing method to obtain the region of interest of the endoscopic image and the background region of the endoscopic image includes the following steps: Set a seed point, use the seed point as the starting point of the region of interest, traverse the neighborhood pixels of the seed point. When the pixel point meets the region growing criterion and has not been added to the region of interest, add it to the region of interest and use it as a new seed point to continue growing, and continuously iterate and grow until there are no pixel points that meet the region growing criterion. Finally, obtain the region of interest of the endoscopic image and the background region of the endoscopic image. For the obtained region of interest of the endoscopic image and the background region of the endoscopic image, label the image file header, which is beneficial for obtaining the image link later. Among them, when the pixel point meets the region growing criterion and has not been added to the region of interest, adding it to the region of interest includes the following steps:

[0031] Use the gray value between pixel points as the region growing criterion. When the difference between the gray value of the pixel point and the gray value of the seed point in the region of interest is less than the set threshold, add the pixel point to the region of interest, where the threshold is set to 20.

[0032] Use the color difference between pixel points as the region growing criterion. When the difference between the color value of the pixel point and the color value of the seed point in the region of interest is less than the set difference threshold, add the pixel point to the region of interest, where the difference threshold is set to 5.

[0033] The pixel values of the region of interest are set to a red label, and the pixel values of the background region are set to a blue label.

[0034] S102: Perform compression encoding on the region of interest and the background region of the endoscopic image, and use Gaussian filtering weighting to denoise the compressed endoscopic image.

[0035] In the step S102, perform lossless compression encoding on the region of interest of the endoscopic image, define the compression encoding rule, perform lossy compression encoding on the background region of the endoscopic image, and define the compression encoding rule.

[0036] The compression encoding rule of the lossless compression encoding is: construct an optimal binary tree based on the pixel point frequencies in the region of interest of the endoscopic image, use shorter encodings for the pixel points with higher frequencies in the region of interest of the endoscopic image, and use longer encodings for the pixel points with lower frequencies in the region of interest of the endoscopic image.

[0037] The compression encoding rule of the lossy compression encoding is: convert the background region to a frequency domain representation by performing a discrete cosine transform on the background region of the endoscopic image, and use a quantization table to quantize the frequency domain coefficients to reduce the detailed information of the high-frequency part of the background region of the endoscopic image.

[0038] Select encoding compression parameters according to the importance of the region of interest and the background region of the endoscopic image, weigh the quality and data volume of the endoscopic image through the compression parameter ratio, and retain the details and quality of the region of interest.

[0039] The specific formula of the Gaussian filtering weighting in the step S102 is:

[0040]

[0041] where V f represents the denoising result after Gaussian filtering weighting, V i represents the value of the neighborhood points of the i-th pixel point in the region of interest and the background region, d i represents the distance from the neighborhood points of the i-th pixel point in the region of interest and the background region to the current point, and σ represents the standard deviation of the Gaussian distribution.

[0042] S103: During the Gaussian filtering weighting process of the compressed endoscopic image, synchronously use a time window to mark the compressed endoscopic image, complete the detailed grouping of the region of interest and the background region of the compressed endoscopic image, and obtain the data packet of the region of interest of the image and the data packet of the background region of the image.

[0043] Among them, the marking of the time window in step S103 includes the following steps: providing timestamps and serial numbers through the time window, and the marking process of the time window carefully groups the regions of interest and the background regions of the endoscopic images. The shape features of the objects in the regions of interest and the background regions of the endoscopic images are extracted through edge detection as the check codes for the careful grouping, and the check codes are attached to the parallel transmission of the endoscopic images.

[0044] S104: Configure priorities for the data packets of the regions of interest and the background regions of the images based on Qos technology. The priority configuration is based on the fact that the data priority of the regions of interest of the images is greater than that of the data packets of the background regions of the images, and the priorities are further determined according to the order of the timestamps in the data packets. The priority of the timestamp marked earlier is higher.

[0045] S105: Receive the endoscopic image data packets based on the priorities, read the endoscopic image data packets, perform inverse quantization and inverse downsampling on the endoscopic image coefficients during the encoding process, and reconstruct the regions of interest and the background regions of the endoscopic images to obtain a complete endoscopic image;

[0046] Among them, when the terminal receives the endoscopic image data packets, the shape features of the objects in the regions of interest and the background regions of the endoscopic images are extracted through reset edge detection as the check codes for the received grouping and compared with the check codes of the careful grouping. When the check codes are compared incorrectly, the serial numbers of the regions of interest and the background regions of the endoscopic images are selected, and the iterative grouping and comparison operations are returned. The endoscopic image data packets are read to obtain the distinction, size, and chromaticity information of the regions of interest and the background regions of the endoscopic images. The terminal analyzes the endoscopic images according to the compression encoding rules, performs inverse quantization on the endoscopic image coefficients during the encoding process to restore the quality and data volume of the endoscopic images, and converts the inversely quantized endoscopic image coefficients into uncompressed pixel point values through inverse transformation, and performs inverse downsampling on the chromaticity information of the endoscopic images. The restored quality and data volume, pixel point values, and chromaticity information of the endoscopic images are connected. At this time, a complete endoscopic image can be obtained through the image file header.

[0047] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0048] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0049] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

[0050] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

[0052] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A QoS guarantee method for lossless transmission of images based on endoscope, characterized in that: The specific steps include: S101: segmenting the endoscopic image using a region growing method to obtain an endoscopic image region of interest and an endoscopic image background region; S102: compressing and encoding the region of interest of the endoscopic image and the background region of the endoscopic image, and denoising the compressed endoscopic image by using Gaussian filter weighting; S103: In the Gaussian filter weighting process of the compressed endoscopic image, the compressed endoscopic image is synchronously marked using the time window to complete the detailed grouping of the region of interest and the compressed background region of the compressed endoscopic image, and obtain the image region of interest data packet and the image background region data packet; S104: configuring priorities for data packets in the image area of ​​interest and data packets in the image background area based on QoS technology; S105: Based on the priority reception, an endoscopic image data packet is obtained, the endoscopic image data packet is read, the endoscopic image coefficients in the encoding process are dequantized and de-downsampled, and the endoscopic image region of interest and the endoscopic image background region are reconstructed to obtain a complete endoscopic image.

2. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 1 is characterized in that: In the step S101, the endoscopic image is segmented using the region growing method to obtain the endoscopic image region of interest and the endoscopic image background region, including the following steps: setting a seed point, taking the seed point as the starting point of the region of interest, traversing the neighborhood pixels of the seed point, and when a pixel point meets the region growing criteria and has not yet been added to the region of interest, adding it to the region of interest and using it as a new seed point to continue growing, and continuously iterating the growth until there are no pixel points that meet the region growing criteria, and finally obtaining the endoscopic image region of interest and the endoscopic image background region.

3. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 2 is characterized in that: If the pixel point meets the region growing criterion and has not been added to the region of interest, adding it to the region of interest includes the following steps: The grayscale value between pixels is used as the region growing criterion. When the difference between the grayscale value of a pixel and the grayscale value of a seed point in the region of interest is less than a set threshold, the pixel is added to the region of interest, where the threshold is set to 20. The color difference between pixels is used as the region growing criterion. When the difference between the color value of a pixel and the color value of a seed point in the region of interest is less than a set difference threshold, the pixel is added to the region of interest, where the difference threshold is set to 5.

4. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 1 is characterized in that: In the step S102, lossless compression coding is performed on the region of interest of the endoscopic image, and compression coding rules are defined, and lossy compression coding is performed on the background region of the endoscopic image, and compression coding rules are defined.

5. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 4 is characterized in that: The compression coding rule of the lossless compression coding is: construct an optimal binary tree based on the frequency of pixels in the region of interest of the endoscopic image, use shorter codes for pixels in the region of interest of the endoscopic image with higher frequency, and use longer codes for pixels in the region of interest of the endoscopic image with lower frequency.

6. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 4 is characterized in that: The compression coding rule of the lossy compression coding is: the background area of ​​the endoscopic image is converted into a frequency domain representation by performing a discrete cosine transform on the background area of ​​the endoscopic image, and the frequency domain coefficients are quantized using a quantization table to reduce the detail information of the high-frequency part of the background area of ​​the endoscopic image.

7. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 1 is characterized in that: The specific formula for Gaussian filtering weighting in step S102 is: Where V f represents the denoising result after Gaussian filtering weighting, V i Represents the value of the neighborhood point of the i-th pixel in the region of interest and the background area, d i It represents the distance from the neighborhood point of the i-th pixel in the region of interest and the background area to the current point, and σ represents the standard deviation of the Gaussian distribution.

8. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 1 is characterized in that: The time window marking in step S103 includes the following steps: providing a timestamp and a serial number through the time window, and performing detailed grouping of the endoscopic image region of interest and the endoscopic image background region during the time window marking process, extracting the object shape features in the endoscopic image region of interest and the endoscopic image background region through edge detection as a verification code for the detailed grouping, and attaching the verification code to the endoscopic image for parallel transmission.

9. The QoS guarantee method for lossless transmission of images based on endoscope according to claim 1 is characterized in that: In the step S105, the endoscopic image data packet is read to obtain the distinction, size and chromaticity information of the endoscopic image region of interest and the endoscopic image background region, the terminal parses the endoscopic image according to the compression coding rules, dequantizes the endoscopic image coefficients in the encoding process to restore the quality and data volume of the endoscopic image, and converts the dequantized endoscopic image coefficients into uncompressed pixel values ​​through inverse transformation, and de-downsamples the chromaticity information of the endoscopic image, and connects the quality and data volume, pixel values ​​and chromaticity information of the restored endoscopic image to obtain a complete endoscopic image.

Images