Comparative study of the features used by algorithms based on viola and jones face detection algorithm

Abstract

The problem of face detection has been one of the main topics in computer vision investigation and lots of methods have been proposed to solve it. One of the most important is the algorithm proposed by Viola and Jones that offer good results. Many studies have used this algorithm but none have analysed the advantages or disadvantages of using a certain type of feature in either the detection or the computation time. In this article we analyse the Viola algorithm [12] and other derivatives from the point of view of input characteristics and computing time.