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

Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold

A fundus image and automatic detection technology, applied in the field of image processing, can solve the problems of automatic detection of microaneurysms such as missed judgments and misjudgments

Inactive Publication Date: 2017-01-25
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the summary of existing algorithms, the current automatic detection of microaneurysms mainly has the problems of missed judgment and misjudgment

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
  • Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold
  • Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold
  • Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] This embodiment includes the following steps:

[0073] The first step is to preprocess the image to achieve uniform brightness of the fundus image.

[0074] The preprocessing includes normalization, grayscale transformation and histogram equalization.

[0075] To achieve illumination normalization for fundus images, the gray value of the estimated background can be subtracted from the green channel:

[0076] I norm = I G -I bg

[0077] where I norm is the result after normalization processing, I G is the green channel of the image, I bg for the estimated background. I bg The selection of can be obtained by filtering. by to I G Perform N×N median filtering operation to get the required I bg .

[0078] Grayscale transformation is for image enhancement. Assume that the grayscale value of each pixel in the original image is r=f(x,y), and the grayscale value of each pixel after processing is s=g(x,y), according to For a specific transformation relation T, the g...

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 an automatic detection method for microaneurysm in an eye fundus image on the basis of a local entropy determining threshold. The method comprises steps as follows: step one, the image is preprocessed to realize uniformity of brightness of the eye fundus image; step two, Gaussian matched filtering is adopted to enhance pixels of blood vessels and the microaneurysm in the image; step three, the eye fundus image is subjected to threshold segmentation by the aid of the local entropy determining threshold, and target areas of the blood vessels and the microaneurysm in the image are obtained through segmentation; step four, connected components extracted with mathematical morphology are added after segmentation, length screening is realized, mutually communicating blood vessel structures with the length exceeding a set threshold are removed from a selected dark area, and then a real microaneurysm structure can be detected; step five, noise disturbance points in the image are removed through double-loop filtering, and the accuracy rate of detection is increased. Compared with the prior art, the method has the advantages of high detection accuracy and the like.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an automatic detection method for microaneurysms in fundus images based on local entropy determination thresholds. Background technique [0002] At present, many researches on the detection of microaneurysms in fundus images have been carried out all over the world. The relevant algorithms mainly include three types: mathematical morphology and its top-hat transformation technology, matched filtering technology and object segmentation technology. [0003] In the "Automatic detection of microaneurysms indiabetic fluorescein angiography" published in 1983, Baudoin et al took the lead in realizing the automatic detection of microaneurysms in fluorescein contrast fundus images by computer. This algorithm uses the fundus image obtained by fluorescein contrast technology, which is different from the currently used color fundus image, but the processing technology of the two is...

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): G06T7/11G06T7/155G06T5/00G06T7/41G06T7/136
CPCG06T2207/20192G06T2207/30041G06T5/92G06T5/73
Inventor 盛斌邢思凯杨光
Owner SHANGHAI JIAO TONG 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