Abstract
In this paper, we propose a rotation invariant multi-view face detection method based on Real Adaboost algorithm [Improved Boosting Algorithms Using Confidence-rated Predictions]. Human faces are divided into several categories according to the variant appearance from different view points. For each view category, weak classifiers are configured as confidence-rated look-up-table (LUT) of Haar feature [Rapid Object Detection using a Boosted Cascade of Simple Features]. Real Adaboost algorithm is used to boost these weak classifiers and construct a nesting-structured face detector. To make it rotation invariant, we divide the whole 360-degree range into 12 sub-ranges and construct their corresponding view based detectors separately. To improve performance, a pose estimation method is introduced and results in a processing speed of four frames per second on 320 ?240 sized image. Experiments on faces with 360-degree in-plane rotation and ?90-degree out-of-plane rotation are reported, of which the frontal face detector subsystem retrieves 94.5% of the faces with 57 false alarms on the CMU+MIT frontal face test set and the multi-view face detector subsystem retrieves 89.8% of the faces with 221 false alarms on the CMU profile face test set.