Expression recognition method based on reverse synergetic salient region features
An expression recognition and regional feature technology, applied in the field of expression recognition, can solve the problem of lack of correlation between expressions in a single expression image and the limitations of a single classifier
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] 1. Data set preprocessing
[0019] It mainly combines the sneak algorithm and the GVF algorithm to detect the contour of the face, and retains the pixels in the contour of the face, excludes the pixels outside the contour, and resets the pixels outside the contour to 0. The result is as figure 1 As shown, the pure facial expression image is obtained after preprocessing.
[0020] 2. Extraction of salient areas of expressions
[0021] Collaborative saliency detection is divided into two parts: saliency detection and synergy detection. The saliency and synergy analysis are performed using cluster-level spatial features and contrast features respectively, and then the multiplicative feature fusion method is used to generate the expression collaboration saliency map.
[0022] The contrast feature reflects the uniqueness between a single image or multiple images, and is widely used in the saliency calculation of a single image. The present invention uses a cluster-based contrast fea...
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