Image Processing is one of the vibrant research areas nowadays and particularly face recognition is given much importance in all the sectors. Accordingly this research paper proposes a hybrid Face Recognition System to find facial changes due to the aging factor in a robust manner. The highly qualified sharp features are extracted using the algorithms SURF(Speed Up Robust Features), HOG(Histogram of Oriented Gradient) and MSER(Maximally Stable Extremal Regions) to get better results. The proposed method divides the face into five regions. The whole face area is named Region1 can have a complete set of face features extracted using the SURF and it acts as a holistic feature. The Region 2, the nasal bridge features are extracted using the HOG. The Region 3 and Region 4 extract the features of the eyes of the face and the Region 5 extracts the features of the region around the nose and the mouth. The features of these regions are extracted using MSER. These different features from five regions are matched by point matching technique with the database of the target image. Experimental results are evaluated using the datasets such as Yale, FGNET and MORPH dataset. The experimental results show that the proposed face recognition algorithm is superior to traditional methods in terms of recognition rate and time complexity.
Read full abstract