A Face Detection Method Based on LAB and Adaboost
Jia-Yao Bi, Jianqiang Chen, Shu Yang, Chengcai Li, Jing Wang, Bo Zhang · 2016
Face detection has been a hotspot either in research and in commercial application. In this paper, Locally Assembled Binary (LAB) feature and Adaboost algorithm are combined to recognize human face in images. On the basis of ensuring the detection speed, the detection accuracy is improved. Integral image technology is also conducted in consideration of detection speed. The proposed method is tested on CMU and FDDB face databases. On CMU, the result of the test indicates that the true positive rate is about 85% and the false positive rate is about 1%. The true positive rate is about 72.9% on FDDB. This method is much more better than Viola-Jones method.