Liquid crystal display panel CF picture identification method based on statistical learning
A liquid crystal panel, statistical learning technology, applied in the field of CF image recognition of liquid crystal panels based on statistical learning, can solve the problems of speeding up training and convergence speed, small samples and large training fluctuations, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0085] The following embodiments will further illustrate the technical solutions, principles, etc. of the present invention in conjunction with the accompanying drawings.
[0086] A kind of liquid crystal panel CF picture recognition method embodiment based on statistical learning of the present invention comprises the following steps:
[0087] 1) Abstract the problem of identifying liquid crystal panel defects into target detection and classification problems in image processing;
[0088]2) Exploratory data analysis, first, by observing the missing images of each category, understand the missing features of each category, reclassify or discard the wrongly classified samples; secondly, try traditional methods and deep learning methods to extract features, Because the convolutional neural network can capture higher-order position and category information in the image, the detection effect is more obvious, so the model of deep learning is finally selected; the specific method of...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com