Hybrid cascade of active/lazy boosting
Hongliang Li, King Ngi Ngan · 2009
In this paper, we present an active boosting algorithm to learn the object detector. This algorithm is to find good features from a confidential map instead of brute-force searching the predefined feature set. The confidential map is computed from the importance re-sampled data. A new feature is created by the linear combination of blocks that are selected from different segmented regions. In addition, lazy boosting associated with the hybrid cascade is developed to speed up the object detection. Experimental results demonstrate the effectiveness of our proposed method that can achieve good performance for the face detection.