Eye fundus image registration method, eye fundus image optic disk nerve and vessel measuring method and eye fundus image matching method

Abstract

The invention discloses an eye fundus image registration method, an eye fundus image optic disk nerve and vessel measuring method and an eye fundus image matching method. The eye fundus image registration method includes determining a model eye fundus image and an eye fundus image to be registered; selecting an interested area on the model eye fundus image; traversing to form all edge points of vessels in the eye fundus image to be registered, and calculating sg value simultaneously; and determining whether registration succeeds or not by judging the sg value. Both the eye fundus image optic disk nerve and vessel measuring method and the eye fundus image matching method are realized based on the eye fundus image registration method. The eye fundus image registration method is high in speed, correctness and precision, measuring results obtained by the eye fundus image optic disk nerve and vessel measuring method based on the eye fundus registration method are high in accuracy, and the eye fundus image matching method based on the eye fundus registration can realize accurate matching of multiple eye fundus images.

Description

technical field [0001] The invention relates to a method for registering fundus images, a method for measuring optic disc nerves and blood vessels in fundus images, and a splicing method for fundus images, and belongs to the technical field of fundus image processing. Background technique [0002] With the rapid development of science and technology, machine vision technology is more and more widely used in fields such as electronics, printing, medicine, and food. It should be mentioned that although machine vision technology has been applied to medical image analysis for a long time, and there are many successful application examples, the research on machine vision technology applied to ophthalmic images is still in its infancy and quite imperfect. . [0003] At present, ophthalmic image research is mainly aimed at the registration of fundus images, the measurement of optic disc nerves and blood vessels in fundus images, and the mosaic of fundus images. [0004] The exist...

AI Technical Summary

Problems solved by technology

It can be found from practice that the grayscale-based registration method can only tolerate linear illumination changes and rigid body transformation when shooting the fundus, while the edge-based or contour-based registration method has a major defect, that is, the fundus edge in the image needs to be extracted, This leads to the fact that target recognition can only be applied to a very small range of illumination changes. If the contrast of the fundus image is reduced, fewer and fewer edge points will be extracted, and more and more masks will be in the image. The target object may not be found in the contrast fundus image, and due to the characteristics of the fundus image, especially the fundus image with cataract, its contrast is generally lower than that of other images

In short, when faced with interferences such as occlusion, geometric distortion, blurring, and severe nonlinear illumination changes in fundus images, these existing registration methods are helpless, or the registration results are far from ideal

[0005] However, the measurement of optic disc nerves and blood vessels in fundus images and the stitching of fundus images are realized based on fundus image registration. method for accurate splicing between

Images