Multimodule method for detection of a human face from complex backgrounds

Ming Xu; Takao Akatsuka

doi:10.1117/12.323239

1 October 1998 Multimodule method for detection of a human face from complex backgrounds

Ming Xu, Takao Akatsuka

Proceedings Volume 3460, Applications of Digital Image Processing XXI; (1998) https://doi.org/10.1117/12.323239
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1998, San Diego, CA, United States

Abstract

In this paper, we proposed a multi-module method for detecting human face from complex background. Each module utilizes one of the cues of human face, such as color, geometric property, motion, depth and etc.. Facial region is obtained by fusion of detected parameters result from each module, and the result is surely robust than that of using any single module. As an actual preliminary implementation, we constructed a face detection system using color module and geometric module. Although only two modules are realized in our system, the conceptual structure of the proposed multi-module method is through to be an efficient solution to the problem of face detection. Multi-module method can not only improve the robustness of detection, but also make the development of new applications, especially face detection systems an easy task, which only need to combine the extra modules with other pre-existing modules. Experimental results show that faces in complex background can be extracted efficiently with multi-module method.

Citation Download Citation

Ming Xu and Takao Akatsuka "Multimodule method for detection of a human face from complex backgrounds", Proc. SPIE 3460, Applications of Digital Image Processing XXI, (1 October 1998); https://doi.org/10.1117/12.323239

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