Learning discriminant features for multi-view face and eye detection

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 373 - 379 vol. 1
• Main Authors: Peng Wang, Qiang Ji
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Computer vision; Error analysis; Eyes; Face detection; Feature extraction; Object detection; Pattern recognition; Shape; Statistical learning; Systems engineering and theory
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2005.200

In current face detection, mostly often used features are selected from a large set (e.g. Haar wavelets). Generally Haar wavelets only represent the local geometric feature. When applying those features to profile faces and eyes with irregular geometric patterns, the classifier accuracy is low in the later training stages, only near 50%. In this paper, instead of brute-force searching the large feature set, we propose to statistically learn the discriminant features for object detection. Besides applying Fisher discriminant analysis(FDA) in AdaBoost, we further propose the recursive nonparametric discriminant analysis (RNDA) to handle more general cases. Those discriminant analysis features are not constrained with geometric shape and can provide better accuracy. The compact size of feature set allows to select a near optimal subset of features and construct the probabilistic classifiers by greedy searching. The proposed methods are applied to multi-view face and eye detection and achieve good accuracy.