A SNoW-Based Face Detector

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or incremen(cid: 173) tally learned feature space and is specifically tailored for learning in the presence of a very large number of features. A wide range of face images in different poses, with different expressions and under different lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and oth(cid: 173) ers. Furthermore, learning and evaluation using the SNoW-based method are significantly more efficient than with other methods.

Authors

• Ming-Hsuan Yang University of California at Merced
• Dan Roth University of Pennsylvania
• Narendra Ahuja University of Illinois at Urbana-Champaign, USA

Keywords

No keywords are indexed for this paper.