Face Recognition Based On Hog - Lbp Feature

As a classic one of pattern recognition problems, Face recognition has been concerned a lot for a long time. As computer technology matures, Face recognition have been extensively applied to the new human-machine interfaces, content-based retrieval, object-based video compression, digital video processing, visual monitoring and many other fields. With more than30years’ development, Face recognition has made great achievements. The state-of-the-art Face recognition system can perform identification successfully under well-controlled environment, and many commercial Face recognition systems have appeared. However, due to the complexity and uncertainty of face recognition, there are still many key problems to be resolved for further application of Face Identification. Feature extraction is the crux of face recognition problem, which directly related to the selection of the classification algorithm and the accuracy of the system.In this paper, current face identification technique is researched. Classic feature extraction methods, including PCA,2DPCA and LBP, and some popular classification method, as SVM and AdaBoost, are studied. A face identification method based on Histograms of oriented gradients (HOG) feature is proposed. HOG is similar to edge orientation histograms, scale-invariant feature transform descriptors and shape contexts. Based on OpenCV, we test it on the YALE dataset by using a linear SVM, and achieved a good result.