Three-classification face detection method using context information
A face detection and three-classification technology, applied in the field of face detection, can solve the problems of poor extraction accuracy of foreground areas, weak robustness, poor detection ability, etc., to solve the problem of insufficient face detection accuracy, improve use efficiency, The effect of improving the recall rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0037] This embodiment provides a three-category human face detection method using context information, including:
[0038] 1. Data preparation stage
[0039] 1.1 Manually label each face in the RGB image collection: use a rectangular frame to mark all the faces that can be recognized by the naked eye in the picture where the face is located (the size of the face is greater than 20*20 pixels), including blacks, whites, Yellow people, etc., non-real human faces (such as cartoons, sculptures, etc.) do not need to be labeled. The error between the position and size of the marked rectangular frame and the real data shall not exceed 10%. In the case of partial occlusion (occlusion less than 50%), the exact position should also be marked. For the front face, the upper boundary is the forehead edge, the lower boundary is the chin, and the ...
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