Compact graph structure face feature extraction algorithm with multi-direction weight optimization
A face feature and graph structure technology, applied in the field of face recognition, can solve the problems of global feature destruction, image grayscale mutation features, inability to distinguish foreground and background, etc., to achieve the effect of improving the recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0033] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
[0034] A face feature extraction algorithm with compact graph structure optimized for multi-directional weights, including the following steps:
[0035] Step 1: In a grayscale image of a human face, traverse all 5×5 neighborhoods.
[0036] The database pictures used in the present invention have been processed into gray-scale images and processed into the same size.
[0037] In this embodiment, the pixel values that make up the graph structure are 56, 80, 45, 38, 90, 40, 52, 3, 8, 15, 61, 45, 60, 62, 58, 55, 51, 32, 84, 85, 30, 64, 25, 18, 40, such as figure 1 Shown.
[0038] Step 2: Construct a graph structure in four directions at the center point in each 5×5 neighborhood, which are 0 degrees, 45 degrees, 90 degrees, and 135 degrees, such as Figure 2 to Figure 5 As shown, each graph structure uses the element pointed by the arrow and the elemen...
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