Brightness evaluation method and device for eye fundus image, electronic equipment and storage medium

Abstract

The invention provides a brightness evaluation method and device for an eye fundus image, electronic equipment and a storage medium. The brightness evaluation method comprises the steps: obtaining a to-be-evaluated eye fundus image; segmenting the eye fundus image into blocks to obtain a plurality of pixel blocks of the eye fundus image; calculating representative brightness values of the plurality of pixel blocks according to the pixel brightness values of the plurality of pixel blocks; determining a target brightness threshold; and comparing the representative brightness values of the plurality of pixel blocks with the brightness threshold so as to evaluate the brightness of the eye fundus image. Therefore, the local brightness condition of the eye fundus image can be more accurately determined; the evaluation accuracy of the local quality of the eye fundus image is improved; disease screening can be more accurately carried out at high quality; and misdiagnosis caused by low qualityof the eye fundus image is reduced as much as possible.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a brightness evaluation method, device, electronic equipment and storage medium of a fundus image. Background technique [0002] With the increasing use of fundus cameras, we can obtain a large number of fundus images, so as to diagnose fundus diseases based on fundus images. For example, fundus diseases such as diabetic retinopathy, glaucoma and age-related macular degeneration can be diagnosed through fundus images. Accurately assessing the quality of fundus images has a significant impact on automatic screening of eye diseases, as poor-quality fundus images may mislead diagnostic results. [0003] However, many fundus images are poor in quality due to uneven lighting, individual eye sensitivity to flash, small pupils, and incorrect photographing methods, among which local overbrightness is mainly caused by uneven brightness / Too dark phenomenon that makes ...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application proposes a fundus image brightness evaluation method, device, electronic equipment, and storage medium, which are used to solve the fundus image brightness evaluation method in the related art, starting from the global statistics of image pixel values, without considering the local parts of the human eye Visual factors, so the local brightness of the fundus image cannot be accurately evaluated, and the technical problem of low accuracy in evaluating the local quality of the fundus image

Images