Face Detection Based on LWE-AdaBoost Algorithm

Focusing on the disadvantages of AdaBoost algorithms: If difficult samples exist in the training samples, with the increase of the iterative number this easily causes degeneration phenomenon, and reduces the generalization ability of the classifier. This article proposes LWE-AdaBoost algorithm which can limit weight expansion, this algorithm makes the appropriate adjustment to the weight update rules, first calculates average value and standard deviation of current sample weight, and then updates the weights according to the level of difference between average value and current weight value, so that weights of hard samples would not expand too much. The experimental results indicate that the LWE-AdaBoost algorithm can restrain the occurrence of degeneration phenomenon well.