Multi-angle face detection based on skin color and histogram with complex background

Jun Bao; Shengrong Gong; ChunPing Liu

doi:10.1117/12.832856

30 October 2009 Multi-angle face detection based on skin color and histogram with complex background

Jun Bao, Shengrong Gong, ChunPing Liu

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74951O (2009) https://doi.org/10.1117/12.832856
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

Face detection is a key step in computer vision applications, such as face recognition and video surveillance. There is a difficult question in automatically segmenting color images into skin color and background regions when using the method of skin color segmentation. The border of skin color region has some background noise patches, especially using edge detection to extract facial organ characteristics, which will lead to some redundant gradient features near the border. In this paper, we introduce a new method based on the histogram to smooth face contour and reduce background noise patches. The performance of our face detector based on the smoothing contour algorithm has been tested on reference test sets, and clearly show some improvements in face detection which is based on knowledge-based methodology.

Citation Download Citation

Jun Bao, Shengrong Gong, and ChunPing Liu "Multi-angle face detection based on skin color and histogram with complex background", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74951O (30 October 2009); https://doi.org/10.1117/12.832856

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available