Research on Feature Extraction Method of Fundus Image Based on Deep Learning

Image feature extraction is a key step in medical image processing, and it also plays an important role in the recognition and classification of medical images. A feature extraction method of fundus images using deep learning technology is proposed to recognize and classify fundus images. Firstly, the fundus image in the data set needs to be preprocessed. Then, the fundus image is extracted in the VGG16 network for the optic cup and disc region. Finally, the fundus feature image is input into the improved Softmax classifier for recognition and classification. The experimental results show that the fundus image feature extraction method used in the fundus images of glaucoma patients and normal people has a higher classification accuracy rate and the classification effect is better.