Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent recognition of bleeding points in capsule gastroscopy images based on Adaboost machine learning

A machine learning and intelligent recognition technology, applied in the field of medical image processing, can solve the problems of heavy workload, tedious and boring, and achieve the effect of high application effect and significance

Active Publication Date: 2019-01-18
ZHEJIANG UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If screening and identification is performed manually, it will be a huge workload and cumbersome and boring thing.

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
  • Intelligent recognition of bleeding points in capsule gastroscopy images based on Adaboost machine learning
  • Intelligent recognition of bleeding points in capsule gastroscopy images based on Adaboost machine learning
  • Intelligent recognition of bleeding points in capsule gastroscopy images based on Adaboost machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Below in conjunction with accompanying drawing, the method of the present invention will be further described.

[0042] Such as figure 1 As shown, a method for intelligent recognition of bleeding points in capsule gastroscopy images based on Adaboost machine learning, its specific implementation steps are as follows:

[0043] Step (1): Input the 1893 capsule gastroscopy images with bleeding points obtained by the collection D t And the corresponding mask image, and then according to the overall depth of the image color to D t Carry out manual classification and divide into normal set DtA and color darker set D tB .

[0044] Step (2): In the Matlab environment, input D sequentially t The image in , and perform color space conversion on each input image, convert it from RGB space to HSI space, and then calculate D in HSI color space t The mean value of the three channels of each image in the image is used to construct the feature vector, such as the image-level featu...

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 discloses a technical method for realizing intelligent recognition of bleeding point of capsule gastroscope image based on Adaboost machine learning algorithm. the method comprises the steps: firstly, the images in the capsule gastroscope hemorrhage image set are converted to HIS space by color space conversion, the mean value of three channels of each image in HSI color space is extracted to construct a three-dimensional vector as image-level eigenvector matrix, and a label matrix is established according to the class of each image for Adaboost training to obtain an image classifier; secondly, threshold segmentation is performed on the normal color atlas and the darker color atlas, respectively, to filter out the invalid area and the dark and bright area in the original image; Then, H, S, I, A, M channel color data of remaining pixels is extracted after threshold segmentation respectively to construct five-dimensional feature vector for Adaboost to train and obtain pixelclassifier; finally, the post-processing is used to optimize the display means, so that the final recognition effect is more conducive to observation and diagnosis.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, in particular to an intelligent recognition method for bleeding points in capsule gastroscope images based on Adaboost machine learning. Background technique [0002] Gastrointestinal diseases have the characteristics of being latent in the early stage and difficult to be cured in the later stage. Once the patient delays the best diagnosis time in the early stage and does not receive timely treatment, there is a high probability that he will not be able to get rid of the troubles of gastrointestinal diseases for a long time. Therefore, compared with treatment after illness, improving the detection methods of gastrointestinal diseases is of great significance to reducing the burden of people's gastrointestinal diseases. [0003] However, most of the detection methods commonly used in hospitals at present are direct detection through traditional insertion gastroscopes and rectoscop...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/32G06K9/46G06K9/62
CPCG06V10/255G06V10/56G06V2201/03G06F18/2431
Inventor 丁勇刘毅胡拓罗述杰冯彪陈宏达
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com