Multi pose face detection and pose estimation using Multi-class LogitBoost algorithm

Abstract

We handle the problem of detecting and classifying face pose views in images at the same time developing a Multi-class view detection. In order to solve this problem we use Multi-class LogitBoost algorithm in order to construct corresponding classifier structure. Although approaches generally use binary classifiers for each view class detection, we develop one multi-class classifier using LogitBoost algorithm. We collect large number of background images under a cascade of classifiers constructed with multi-class boosting algorithm. Using this classification approach each pose view of the face images can be detected and classified at the same time and rejecting the background images at each stage of the multi-class classifier cascade as well. Experiments on video images have shown that the performance of this classification approach is similar to the other state-of-art approaches for the detection and pose estimation of face images.