Method for automatic freezing of digestive endoscopy image based on perceptual hash algorithm

A perceptual hash algorithm and digestive endoscopy technology, applied in endoscopy, gastroscopy, computing, etc., can solve problems such as field of view deviation, image is not a doctor, and slow response speed, so as to avoid field of view deviation and reduce the work of doctors volume effect

Inactive Publication Date: 2020-10-16
WUHAN ENDOANGEL MEDICAL TECH CO LTD
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method must rely on the endoscopist to operate and press the button to issue a freezing command. Due to factors such as the low level of operation of the endoscopist and slow

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for automatic freezing of digestive endoscopy image based on perceptual hash algorithm
  • Method for automatic freezing of digestive endoscopy image based on perceptual hash algorithm
  • Method for automatic freezing of digestive endoscopy image based on perceptual hash algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] S1, obtain the video stream of endoscopic examination through the endoscopic examination equipment, parse the video stream into pictures (30 frames per second), remove blurred and invalid frame pictures, and take 10 frames of pictures;

[0033] S2, cutting the effective frame picture to a size of 360*360 pixels, further reducing the picture, and only retaining the structural information of the picture;

[0034] A 360*360 picture has more than 100,000 pixels, which contains a huge amount of information, and a lot of details need to be processed. Therefore, we need to zoom the picture to a very small size. The function is to remove the details of the picture, retain only the basic information such as structure, light and shade, and discard the picture differences caused by different sizes and ratios.

[0035] The bi-cubic interpolation method is used for zooming pictures. Although the amount of calculation is large, the image quality after zooming is high and it is not ea...

Embodiment 2

[0046] The difference technology with embodiment one is as follows:

[0047] In step S2, the similarity between different pictures is calculated by calculating the Hamming distance between different pictures. The Hamming distance between different pictures indicates the number of digits that need to be modified to modify the dHash value corresponding to picture A to the dHash corresponding to picture B. The formula for calculating the similarity between the current picture and the previous n frames is:

[0048] Sim=100*(64-d(x,y)) / 64;

[0049] Among them, d(x, y) represents the Hamming distance between different pictures, d(x, y)=Σx⊕y, x and y represent the dHash values ​​corresponding to different pictures, and ⊕ represents XOR.

[0050]Calculate the Hamming distance between different pictures;

[0051] The Hamming distance indicates the number of different characters in the corresponding positions of two equal-length strings. The Hamming distance in dHash is to take the X...

Embodiment 3

[0056] The difference technology with embodiment two is as follows:

[0057] By analyzing the video of the endoscopist manually freezing the image during the endoscopic examination, the boundary line l of the weighted similarity when the image is judged to be frozen is set;

[0058] Weight the similarity of the picture at time point t Compared with the threshold l, when When , it is judged that the image is frozen at the time point t, and the image freezing instruction is triggered at the time point t; when , it is judged that the time point t is not a frozen image, then the freeze image instruction is not triggered at the time point t, and the above steps are repeated at the next time point (t+1).

[0059] Using this technical solution to replace the operation of manually freezing images can not only effectively obtain a clear image of the best field of view, but also reduce the workload of endoscopists. Its core lies in how to trigger the freeze command. Based on the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of medical image processing, in particular to a method for automatic freezing of a digestive endoscopy image based on a perceptual hash algorithm. The method comprises the following steps: S1, analyzing an endoscopy video stream acquired by endoscopy equipment into image data; S2, calculating the similarity between a picture at a time point t and previous n frames of pictures to obtain the weighted similarity k of the picture; and S3, comparing the picture weighting similarity k at the time point t with a freezing boundary l, and triggering an imagefreezing instruction when the value k reaches the value l. After the method is applied, when an endoscopic doctor needs to carefully check a view image, the endoscopic doctor only needs to stop moving an endoscope body to keep the view unchanged, a frozen image can be automatically judged, and the doctor does not need to manually operate a freezing button, so the workload of the doctor is reduced. A system automatically executes a freezing instruction, so offset of a frozen image view or loss of effective information caused by slow response or unskilled operation of people can be avoided, anda clear image of the optimal view can be effectively obtained.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for automatically freezing digestive endoscopy images based on a perceptual hash algorithm. Background technique [0002] Digestive endoscopy is the gold standard for the screening and diagnosis of gastrointestinal lesions, and is the core link of clinical diagnosis and treatment. Digestive endoscopy is through the operation of the endoscopist, so that the digestive endoscope enters the human digestive tract for shooting, and transmits the video image to the endoscope imaging system in real time, and then transmits it to the display terminal for the endoscopist to view after being processed by the system. The image freezing function is a commonly used basic function in the process of endoscopic examination. The endoscopist presses the "freeze" button of the endoscopic equipment to freeze the real-time image and obtain a static image for careful observati...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G06T7/10G06T7/90G06K9/62G16H30/20
CPCG06T7/0012G06T7/10G06T7/90G16H30/20G06T2207/10068G06T2207/20132G06T2207/10016G06T2207/30004G06F18/22G06V20/40G06V10/993G06V2201/03G06V20/46A61B1/0638A61B1/2736G06T3/4007H04N5/2628H04N7/188
Inventor 李超刘金龙刘奇为胡珊
Owner WUHAN ENDOANGEL MEDICAL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap