Face recognition method combining SVM machine learning and scale invariant feature transform

Facial recognition is a method to identify an individual from his image. It has attracted the intention of large number researchers in field computer vision recent years due its wide scope application several areas (health, security, robotics, biometrics...). The operation this technology, so much demand today's market, based on extraction features input image using techniques such as SIFT, SURF, LBP... and comparing them with others another confirm or assert identity individual. In paper, we have performed comparative study machine learning-based approach classification methods, applied two face databases, which will be divided into groups. first one Train database used for training stage our model second Test database, test phase model. results comparison showed that SIFT technique merged SVM classifier outperforms other classifiers terms identification accuracy rate.