Automatic face detection and tracking based on Adaboost with camshift algorithm

Hui Lin; JianFeng Long

doi:10.1117/12.913368

1 October 2011 Automatic face detection and tracking based on Adaboost with camshift algorithm

Hui Lin, JianFeng Long

Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 82854Z (2011) https://doi.org/10.1117/12.913368
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt

Abstract

With the development of information technology, video surveillance is widely used in security monitoring and identity recognition. For most of pure face tracking algorithms are hard to specify the initial location and scale of face automatically, this paper proposes a fast and robust method to detect and track face by combining adaboost with camshift algorithm. At first, the location and scale of face is specified by adaboost algorithm based on Haar-like features and it will be conveyed to the initial search window automatically. Then, we apply camshift algorithm to track face. The experimental results based on OpenCV software yield good results, even in some special circumstances, such as light changing and face rapid movement. Besides, by drawing out the tracking trajectory of face movement, some abnormal behavior events can be analyzed.

Citation Download Citation

Hui Lin and JianFeng Long "Automatic face detection and tracking based on Adaboost with camshift algorithm", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82854Z (1 October 2011); https://doi.org/10.1117/12.913368

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