les méthodes de point intèieur pour la dètection faciale

Abstract

bstract : Facial detection involves developing code that, in an arbi- trary image, can detect and locate human faces. It is gaining interest as an important research area with important applications in security surveillance, human-machine interaction, and other areas of computer vision and machine learning. Many methods have been developed with several approaches. The majority of the approaches used are based on two tasks. The rst is the feature extraction task, it concerns the precise digital description of what distinguishes human faces from other objects. The second task is usually a supervised classi cation algorithm which will have to recognize a face from a non-face with good precision. The objective of our work is to use an interior point method, in order to solve the quadratic program in SVMs. We will then focus on the behavior of th