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

Retina fovea centralis detection method based on multi-feature model

A detection method and retinal technology, applied in character and pattern recognition, instruments, acquisition/recognition of eyes, etc., can solve problems such as error detection, achieve the effect of improving accuracy and robustness, and stabilizing identity feature information

Active Publication Date: 2017-04-26
HARBIN INST OF TECH
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of the fundus, such as the presence of interference such as illumination noise and fundus lesions, traditional fovea detection algorithms usually have false detections.

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
  • Retina fovea centralis detection method based on multi-feature model
  • Retina fovea centralis detection method based on multi-feature model
  • Retina fovea centralis detection method based on multi-feature model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings, but it is not limited thereto. Any modification or equivalent replacement of the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention should be covered by the present invention. within the scope of protection.

[0040] In the retinal fundus image, the fovea usually appears as a dark red spot, which is located on the symmetry axis of the retinal vascular network, and is about 2.5 times the diameter of the optic disc from the center of the optic disc, such as figure 1 a) as shown. However, for some fundus images, the distribution of the vascular network will be abnormal, and the fovea does not fully comply with the above priors (eg figure 1 b) shown). In addition, dark lesions or hyperpigmentations (eg, figure 1 c)), which has a similar appearance to the fovea...

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 retina fovea centralis detection method based on a multi-feature model. The retina fovea centralis detection method comprises the following steps: 1) carrying out global prior feature extraction; 2) carrying out local prior feature extraction; 3) carrying out depth feature extraction; and 4) establishing a multi-feature-fusion fovea centralis detection model. Through global, local and depth feature information extraction of fovea centralis and effective fusion, accurate detection of the retina fovea centralis is finished. The method can effectively overcome the influence of fundus illumination noise, fundus lesions and abnormal blood vessel distribution on fovea centralis automatic detection, thereby improving fovea centralis detection precision and robustness, and providing more robust identity characteristic information for identity identification based on retinal images.

Description

technical field [0001] The invention relates to a method for detecting the central fovea of ​​retina with fusion of multiple features. Background technique [0002] The fovea area of ​​the fundus retina is the most visually sensitive area on the retina. Its size, shape, and positional relationship with the optic disc and vascular network can provide the necessary auxiliary information for identification based on retinal images. Accurate detection of the retinal fovea can effectively improve the reliability and accuracy of identity recognition using retinal images. However, due to the complexity of the fundus, such as illumination noise, fundus lesions and other interferences, traditional fovea detection algorithms usually have false detections. Contents of the invention [0003] In order to overcome the complex characteristics of the fundus, the present invention proposes a fovea detection method based on a multi-feature model, by extracting the global, local and depth fe...

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): G06K9/00
CPCG06V40/193
Inventor 邬向前卜巍戴百生
Owner HARBIN INST 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