Face Detection Approaches Research Based On AdaBoost

In recent years, with the extending of computer technology and the rapid development of digital multimedia technology, face detection has been an important problem in the domain of digital image management and intelligence computation. Intelligent computing technology has been developed fast, new approaches and new technologies will continue to be used, which bring more facilitate conditions, and detection result and robustness has been improved.In this paper, firstly we give an outline of the situation of study and the development of face detection, and studied the face detection method based on the AdaBoost algorithm importantly, besides, optimized the process of training for detection machine, on that basis the cascade AdaBoost is a advanced method for detecting the face fast. However, several important issues involved in: How to select the most discriminative weak learners and how to optimally combine them. On that account problem, we adopted the optimized AdaBoost algorithm for improved detection method. Firstly through studying the property of weak classifier, a method of computing threshold is proposed which achieved high detection rate for using fewer weak classifiers. Secondly selecting discriminative weak learners to optimize the detection performance and giving the number of Haar-like features in the AdaBoost training. Lastly, through the cascade manner combine the classifiers is to advanced the capacity of distinguish faces and non-faces.In our paper, we adopt Haar-like features to train the optimized weak classifiers, we experimented in the face data of MIT and CBCR, the result of experiment concluded that our proposed method in the frontal face and the small rotate angles the detection rate is improved fast and the time complexity is decreased.