Toward an Efficient Implementation of Boosting Cascaded Classifiers for Face Detection

摘要

The problem of face detection is still a standing problem in the research area. One of the most famous approaches that is successful is the Viola & Jones algorithm. In this paper, we were designed a two systems based on this approach to measure the effectiveness of using different Haar feature types, and to compare two types of threshold computing methods. The two methods used for computing thresholds are the average of means and the optimal threshold methods. The implemented systems have been trained using a handpicked database. The database contains 350 face and nonface images. Adaboost algorithm has been used to build our detectors. Each detector consists of 3 cascade stages. In each stage, we randomly use a number of weak classifiers to build the strong classifier. Each weak classifier is computed based on threshold before entering the Adaboost algorithm. If the image can pass through all stages of the detector, then the face will be detected. Based on these results, we could solve the problem of the overlap to get better detection rates, do more comparisons with more threshold methods (single or multi threshold), add multi-face detection and building a face detection system that's more accurate and faster.