Face Detection in Complex Background Using AdaBoost Algorithm

摘要

This paper has studied one kind based on rectangle features face detection technology. The first use of a fixed size training set training out of each rectangle features corresponding to the weak classifier, the weak classifier selection, made some improvement. Using AdaBoost algorithm to train the weak classifier, we get a strong classifier. In the end, we make strong classifier construction into a cascade structure of a human face detector, the experimental results show that the detector can quickly and accurately detect the human face images.