Research on Face Detection Classifier Using an Improved Adboost Algorithm

Since face detection use a single classification is very time-consuming and inefficient. To solve this problem, we propose to establish two classifiers which are based on facial features and human eye features using the Adboost algorithm. First, use the facial features classifier detected out a rough location of the face. Then give out the accurate location of the face accord to the distance and the perspective of two eyes which have been detect out. At the same time to correct images if they are tilt. The experimental result shows the algorithm has a faster speed and more efficient on the face detection.