EYE FUNDUS IMAGE QUALITY EVALUATION METHOD, DEVICE AND STORAGE MEDIUM

摘要

The present invention relates to the technical field of image detection, and provides an eye fundus image quality evaluation method, device, and a storage medium, the method comprises: acquiring an eye fundus image set to be processed; constructing a classification model according to the deep learning method and the eye fundus image set; acquiring an eye fundus image of the clinical patient collected in real time; after determining that the eye fundus image is qualified according to the classification model, performing image black edge cutting processing on the eye fundus image according to the above classification model, and then inputting the processed eye fundus image into the target detection network; positioning the optic disc area and the macular area in the eye fundus image according to the target detection network; if it is determined that the abnormal image with quality defect exists in the processed eye fundus image, sending prompting information for prompting to collect again the collection part corresponding to the abnormal image. By using the solution, the collection quality of the eye fundus image can be fed back in real time, and the quality stability of the eye fundus image is ensured.