Face recognition using HMAX method for feature extraction and support vector machine classifier

Whereas features extraction is an important phase in face recognition, we intend to use a new features extraction technique which is robust with respect to rotate and scale variant, in this paper. Therefore we use original HMAX and new HMAX model which is motivated by a quantitative model of visual cortex. The identification process can be divided into the following stages: capturing the image, preprocessing image, extracting the face from image and normalizing it, and then extracting features, finally, we used the K-nearest neighbor (KNN) and support vector machine (SVM) as classifiers. The ORL database is exploited to test our approach. The experimental results showed the effectiveness of the system in terms of the recognition rate.