A Macular Localization Method Based on Improved Faster R-CNN
A positioning method and macular technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of algorithm failure, easy to be interfered by noise, poor shooting effect, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] The technical solutions of the various embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.
[0031] The present invention provides a kind of macular localization method based on improved Faster R-CNN, comprises the following steps:
[0032] S1. Collect training samples: obtain fundus images from the Kaggle dataset, mark the macula area on the obtained fundus images, and make the marked images into the format of the VOC2007 dataset to construct a training sample set;
[0033] S2. Building a network model: building a CNN feature extraction network, a cascaded region proposa...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


