Focus image classification and identification method based on fundus image

A fundus image and recognition method technology, applied in the field of medical image processing, can solve the problems of small diseased tissues that cannot be detected in time, difficult, hidden in blood vessels, etc., and achieve the effect of improving capture ability, accurate results, and broad application prospects
CN114821189APending Publication Date: 2022-07-29CHONGQING UNIV OF POSTS & TELECOMM
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
CHONGQING UNIV OF POSTS & TELECOMM
Publication Date
2022-07-29

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a focus image classification and identification method based on fundus images, and belongs to the field of medical image processing. According to the method, a YOLOv5 network structure and a target frame are fused in a weighted mode to form a frame, data sets of collected eye fundus images are deepened through a Mosaic method, the deepened image data sets and loss function training and image classification are combined, then the images enter the target frame weighted fusion frame, and finally binary images of different eye fundus images are output according to classification probabilities. And outputting the focus binary images in a classified manner. According to the method, the focus feature extraction capability of the network model is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of medical image processing, and relates to a lesion image classification and identification method based on fundus images. Background technique

[0002] At present, fundus examination is mainly performed manually by doctors using fundus ophthalmoscopy, fundus imaging technology, fundus camera imaging and mutual interference technology of light. The fundus camera can clearly capture the main tissue structures on the retina. In the color fundus image, the blood vessels are most widely distributed on the retina and appear as a dark red reticular structure, which and optic nerve fibers enter the retina from the optic disc area. The optic disc is characterized by a disc-like structure with clear borders and highlights. In addition, if the color of the fundus image is darker, it can be called the macular area. The macular area is an oval depression, and the depressed part is called the fovea. The fovea is the most sensi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More