Face Detection Using Support Vector Machine Classifier and Different Features

Face recognition is widely used in computer vision and in many other biometric applications where security is a major concern. Biometric technology is based on the physiology or behavioral characteristics of a human body. Naturally, before recognizing a face, it must be detected in the image. Many algorithms have been developed with different approaches to overcome some detection problems such as occlusion, illumination condition, and scale, among others. Histograms of Oriented Gradients (HoG), Haar Wavelet Transformation and Gabor Filter are the effective descriptor for object recognition and detection. In this project, we use different feature extraction method and SVM classifier to detect faces with a comparison among these features. We compare the results comes from using different features in the term of time duration, precession, recall, error and accuracy rate. We have tried to overcome many of these limitations, we have tried to detect the face which is not frontal. 

• Supervision