Human Face Detection via Characterized Convex Regional Relationship in Color Images

Chang-Woo PARK  Euntai KIM  Mignon PARK  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E86-D   No.4   pp.759-762
Publication Date: 2003/04/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing, Image Pattern Recognition
Keyword: 
face detection,  face location,  color space,  convex-hull,  image segmentation,  

Full Text: PDF(236.2KB)>>
Buy this Article




Summary: 
In this letter, we propose a new method to detect faces in color images based on the characterized convex regional relationship. We detect skin and hair likeness regions using the derived skin and hair color models and the convex skin likeness and hair likeness regions are adopted as the characteristic convex regions. Finally, human faces can be detected via their intersection relationship. The proposed algorithm can accomplish face detection in an image including not only single face but also multi-faces and also detect deformed faces efficiently. To validity the effectiveness of the proposed method, we make experiments with various cases.