Method for extracting front human face outline based on complexion model and shape constraining

A technology of skin color model and frontal face, applied in the field of computer vision, can solve problems such as neck separation

Inactive Publication Date: 2010-02-17
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem that the existing face contour extraction method based on skin color is difficult to separate the neck from the face area, and proposes a frontal face contour extraction method based on skin color model and shape constraints. The skin color area is initially positioned, and then filtered to remove non-face areas, and finally the preliminar

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for extracting front human face outline based on complexion model and shape constraining
  • Method for extracting front human face outline based on complexion model and shape constraining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The face contour extraction method based on the skin color model and shape constraints proposed by the present invention includes the following steps, and the specific process is as attached figure 1 Shown:

[0017] (1) Establishment of skin color model: Skin color plays an important role in face information processing and analysis. It does not depend on the detailed features of the face, and it will not follow the rotation of the face, facial expressions, and partial occlusion of the face (such as Hair, glasses) and other complex changes, have relative stability. In most cases, the skin color will have a large color difference from the color of the background object, so the skin color feature is one of the most effective features in face information processing and analysis. At the same time, face segmentation based on skin color has the characteristics of simple principle and fast implementation, so it is suitable for real-time use. Segmenting face regions from non-f...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for obtaining a human face outline, which comprises the following steps: carrying out threshold analysis on image data and establishing a complexion model in a YCbCrspace, initially positioning the complexion area through the complexion model, and marking a communicated area of the complexion area to further screen and remove a non-face area according to an areapixel; then extracting the initial outline of a human face and removing the neck outline by combining the face morphology proportion; and finally constructing the human face chin outline through humanface morphological constraining parameters and obtaining a continuous and closed human face outline. The method basically solves the problems that the chin outline is difficult to extract from the neck, can well extract the human face outline from images with relatively-complicated background, meet the requirements of characteristic extraction of the human outline, and has higher timeliness.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for extracting frontal human face contours based on a skin color model and shape constraints. Background technique [0002] Face contour is a feature that describes the shape and structure of the face. As an important part of face features, it is the basis for subsequent detection and extraction of other face features and face recognition, and plays an important role in face information processing and analysis. . The face contour extraction algorithm based on skin color is based on the color-based skin detection, and the skin-like area is obtained by establishing a skin color model, and the face contour can be obtained after area screening and contour tracking extraction. The advantage of this method is that the amount of calculation is small, a complete closed contour can be obtained, and it has certain robustness to the shape and position of the face; its disa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/46
Inventor 黄福珍陈红寅
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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