Image scene classification method based on multi-characteristic fusion
A multi-feature fusion and scene classification technology, applied in the field of computer image processing, can solve problems such as misclassification and misclassification of image scene classification methods, and achieve the effects of high efficiency, shortening training time, and improving classification accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0027] For different objects in the image, the advantages of various features are different, and there are complementary phenomena among them. Multi-feature fusion can solve the deficiency of single feature description. The present invention proposes an image scene classification method based on multi-feature fusion. First, the GIST feature, SIFT feature and PHOG feature of the image are extracted. Since GIST features belong to sparse grid division, different scene features may be included in a grid, and the specific details in it may be ignored. The SIFT feature is a local feature widely used in image scene classification to achieve precise positioning of feature points. The PHOG feature is a spatial shape description, which characterizes the local shape of an image and the spatial relationship of its shape. The combination of the three to describe the image scene can provide richer information, and the features can complement each other. Then, Locality-constrained linear c...
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