Method for automatically segmenting face in digital photo
An automatic segmentation and photo technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as complex faces, and achieve the effect of improving system robustness, stable detection, and speeding up evolution.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0026] 1. Face detection: The Adaboost algorithm is used to realize the initial positioning of the face area, and the face area is marked with a rectangular frame, or the entire photo can be treated as a face area.
[0027] 2. Initial contour positioning: an improved algorithm based on the single Gaussian model SGM is used to detect the face skin area, and this part of the area is ellipse fitting used as the initial contour line in the next step. The specific implementation steps are as follows:
[0028] The distribution of skin color in the color space is quite concentrated, and it will be affected by lighting and ethnicity. In order to reduce the skin color from being affected by the lighting intensity, the present invention converts the color from the RGB space to the YCbCr color space, then abandons the brightness component Y, and only uses the Cb and Cr components as the information for skin color training and classification, which overcomes the impact of lighting to a certain...
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