Face recognition method based on extraction of multiple evolution features
A feature extraction and face recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of not taking into account the spatial relationship between two samples, not being able to generalize globally, etc., to achieve easy implementation and improve reliability. , the effect of simple principle
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0035] The present invention will be further described in detail below with reference to the drawings and specific embodiments of the specification.
[0036] Such as figure 1 As shown, the face recognition method of the present invention based on evolutionary multi-feature extraction includes the following steps:
[0037] (1) Take a part of all data set D as training samples. This part of the training sample is divided into 2 parts: one part is D 1 , Contains M 1 Samples for feature extraction; the other part is D 2 , Contains M 2 A sample is used for weight evolution. The size of the training sample will affect the result.
[0038] (2) In the same sample set D 1 ={x 1 ,x 2 ,...,X M1 } Above, a variety of subspace methods are used to construct features. In order to facilitate the construction of features, it is first necessary to convert the picture into a vector form, and then the process of feature extraction. Various methods such as PCA, LDA, LPP, KPCA, etc. can be used according...
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.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap