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

Capsule endoscopy image retrieval method based on visual vocabularies and local descriptors

A local descriptor and capsule endoscopy technology, applied in the field of medical image retrieval, can solve problems such as low diagnostic efficiency and difficult inspection volume

Inactive Publication Date: 2015-11-18
BEIJING UNIV OF TECH
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since capsule endoscopy will generate about 55,000 capsule endoscopic images during the entire detection process, doctors generally need 2 hours to complete the diagnosis of a complete case. The diagnosis efficiency is low and it is difficult to cope with a large amount of examination.

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
  • Capsule endoscopy image retrieval method based on visual vocabularies and local descriptors
  • Capsule endoscopy image retrieval method based on visual vocabularies and local descriptors
  • Capsule endoscopy image retrieval method based on visual vocabularies and local descriptors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] figure 1 Be the overall structure flow chart of the present invention, be the concrete implementation steps of the present invention below:

[0060] 1. Create an image library

[0061] Select 30 capsule endoscopic color images as standard case images, and then create an image library containing 300 endoscopic images to be retrieved, 30 of which are suspected case images similar to standard case images.

[0062] 2. Image visual vocabulary acquisition

[0063] (1) Extract the color features of the capsule endoscopy image

[0064] Convert the color space of the capsule endoscopic image from RGB to HSI: the RGB color space includes red (Red), green (Green) and blue (Blue) components, and the HSI color space includes hue (Hue ) component, saturation (Saturation) component and brightness (Intensity) component. After the HSI color value of the pixel is obtained, the color is quantized at non-equal intervals, and the specific details of the quantization can be found in 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 provides a capsule endoscopy image retrieval method based on visual vocabularies and local descriptors. The method concretely comprises the following steps of: building an image library, wherein the image library comprises standard case images and images to be retrieved; converting capsule endoscopy images from an RGB (Red, Green and Blue) color space into an HSI (Hue, Saturation and Intensity) color space, performing quantization processing and extracting a color histogram; extracting an LBP (Local Binary Patterns) texture histogram of the capsule endoscopy images; performing weighing blending on color features and texture features to obtain the visual vocabularies of the images; extracting Sift (Scale invariant feature transform) feature descriptors of the capsule endoscopy images; and performing similarity testing to obtain retrieval results. The method provided by the invention is used for capsule endoscopy image processing; the work intensity of film reading doctors is effectively reduced; and the diagnosis efficiency is improved.

Description

technical field [0001] The invention belongs to the field of medical image retrieval, in particular to a capsule endoscope image retrieval method based on visual vocabulary and local descriptors. Background technique [0002] Gastrointestinal diseases, such as tumors, ulcers and hemorrhage, are a great threat to human health. The traditional gastrointestinal examination method has different degrees of damage to the human body, and cannot examine the small intestine. Capsule endoscopy is a new type of detection technology for gastrointestinal diseases. The patient swallows the capsule, and the capsule moves forward using the power provided by gastrointestinal peristalsis, and continuously takes pictures of the human digestive tract, and the pictures taken are examined and diagnosed by the film reader. The test is painless and can diagnose the entire digestive tract. [0003] Capsule endoscopy expands the field of view of gastrointestinal examination, overcomes the defects ...

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): G06F17/30
CPCG06F16/5838G06F16/5862
Inventor 蔡轶珩詹昌飞盛楠
Owner BEIJING UNIV OF TECH
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