Xerophthalmia grading evaluation system based on regional adaptive multi-task neural network
A neural network and evaluation system technology, applied in the field of dry eye grading evaluation system, can solve problems such as low accuracy and low efficiency, and achieve the effect of improving accuracy, fast speed and high diagnostic efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0070] Examples:
[0071] The infrared image of the eyelid plate used in this embodiment is divided into the upper and lower tarsal plates, which respectively contain 4 levels of dry eye, including: no dry eye, mild, moderate, and severe dry eye. There are 11,584 samples of eyelid plate infrared images, with the same number of upper and lower eyelid plates, including 2,545 without dry eye, 3623 with mild dry eye, 3242 with moderate dry eye, and 2174 with severe dry eye. From the positive and negative samples, 7823 samples were randomly selected as the training set, 1180 samples were used as the verification set, and 1181 samples were used as the test set. The following specifically introduces the preprocessing and enhancement of the eyelid plate image, the training and testing process of the model.
[0072] S1, preprocessing of the eyelid plate image.
[0073] S1-1: Downsample the image to a size of 224*224 to avoid memory overflow during model training caused by an image that is t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap