Paper:
Language: English:

Robust Face Detection for Low-Resolution Images

Shinji Hayashi^, and Osamu Hasegawa^,**

*Tokyo Institute of Technology
R2-52, 4259 Nagatsuta, Midori-ku, Yokohama 226-8503, Japan
**PRESTO, Japan Science and Technology Agency (JST)

Received: April 22, 2005

Accepted: June 27, 2005

Keywords: face detection, low resolution

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.10, No.1 pp. 93-101, 2006

Abstract

Face detection, one of the most actively researched and progressive computer vision fields, has been little studied in low-resolution images. Using the AdaBoost-based face detector and MIT+CMU frontal face test set -- the standard detector and images for evaluation in face detection -- we found that face detection rate falls to 39% from 88% as face resolution decreases from 24×24 pixels to 6×6 pixels. We discuss a proposal using “portrait images,” “image expansion,” “frequency-band limitation of features” and “two-detector integration” and show that 71% of face detection rate is obtained for 6×6 pixel faces of MIT+CMU frontal face test set. Note that each of the above detections involves 100 false positives for 112 evaluation images.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: