Computer aided characteristic registration identifying method for medical homolateral fundus image

Abstract

The present invention relates to computer applying technology. The registration identifying system of the present invention consists of plate scanner with transparent medium adaptor, microcomputer with keyboard and display, laser printer electrically connected together via signal cables. The registration identifying process includes mainly adaptive enhancing of homolateral fundus vessel image; intersection point and pure node extraction of fundus vessel characteristic; normalization of fundus vessel characteristic nodes; and neighboring region registration and judgement of fundus vessel characteristic nodes. The computer-aided judgement means has light labor strength and other advantages.

Description

(1) Technical field: [0001] The invention relates to a computer-aided feature fitting recognition method of an ipsilateral fundus medical image, which belongs to computer application technology, and particularly relates to biomedical image processing and recognition technology. (two) background technology: [0002] Ophthalmology uses fundus cameras to take fundus photo images or negative film images during fundus clinical diagnosis or medical screening, and its archived data is gradually increasing. The left and right sides of the fundus image are different. To study or compare the follow-up photos or negatives in different periods, it is usually done manually now. The negatives need to be observed in a working environment with transmitted light. It is a very strenuous and complicated work, and the operators are labor-intensive, prone to fatigue, and inconvenient to unify and other troubles and burdens. (3) Contents of the invention: [0003] The purpose of the present in...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome and solve the problem of manual fitting of fundus images in the existing fundus clinical diagnosis of ophthalmology, and the need to operate and observe under the working environment of transmitted light, which is often complicated and laborious and labor intensive. , easy fatigue, and inconvenient unification and other problems and problems such as troubles and burdens, research and invention can overcome and solve the problems and burdens of existing fundus image registration recognition, such as high labor intensity, easy fatigue, and inconvenient unification And other shortcomings and problems, using the sparse intersection of fundus blood vessels as characteristic clues, through the technical means of biomedical image processing and recognition methods and the assistance of electronic equipment such as microcomputers, solve the registration and recognition of fundus images, which can reduce the labor burden of manual methods Computer-aided feature nesting recognition method for ipsilateral fundus medical images

Images