Boosting Nested Cascade Detector for Multi-View Face Detection

In this paper, a novel nested cascade detector for multi-view face detection is presented. This nested cascade is learned by Schapire and Singer's improved boosting algorithms that use real-valued confidence-rated weak classifiers [1], where we use confidence-rated LookUp-Table (LUT) weak classifiers based on Haar features. Experiments show the system performance is significantly improved compared with previous methods.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Bo Wu, Chang Huang, Haizhou Ai, Shihong Lao
• Keywords: Computer Vision, Confidence-rated Weak Classifiers, ICPR 2004, Weak Classifiers