Facial expression recognition algorithm based on discriminative component analysis
A technology of facial expression recognition and facial expression recognition, which is applied in character and pattern recognition, computing, computer components, etc. It can solve problems such as inability to invert the matrix, affect the accuracy of facial expression recognition, and unstable algorithm performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0069] The technical scheme that the present invention takes is:
[0070] A DCA-based facial expression recognition method, the method first obtains a sample subset according to the maximum intra-class distance and minimum inter-class distance criteria; then calculates the projection matrix of the sample subset; finally multiplies the sample with the projection matrix, and passes The nearest neighbor method judges the category of samples and completes the task of facial expression recognition. The invention not only migrates the DCA algorithm to the field of facial expression recognition, but also proposes an improved algorithm based on DCA according to the actual situation. Experimental results prove the effectiveness of the algorithm, and finally reach an average recognition rate of 95.71%.
[0071] Concrete steps of the present invention are as follows:
[0072] 1. Sample initialization
[0073] 1.1. Select 213 images as experimental data. Using the Leave-one-out cross v...
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