A Design of Face Recognition Model with Spatial Feature Extraction using Optimized Support Vector Machine

In recent times, the face recognition is regarded as the better technique in the computer vision process. It is also considered as one of the biometric processes because; it is easier as well as acquires a large range. But, the face recognition process is always considered as a difficult process in facial expression, pose, and illumination and in computer vision. In other words, it is defined as the system application in order to automatically detect the person over the still images. In this work, a new model for extracting the spatial features for face recognition is developed. Initially, the standard benchmark images are collected and fed to the pre-processing phase, which results in enhancing the quality of images. Then, the spatial features are extracted using the Local Binary Patterns (LBP). Next, the feature reduction is performed using Principal Component Analysis (PCA) for easier visualization and analysis of data. Finally, the gathered PCA-reduced features are fed to the optimized Support Vector Machine (OSVM) for performing the face recognition process, where the parameters of the SVM are tuned via a Rat Swarm optimizer (RSO). The recognition rate of the proposed approach has achieved higher accuracy than other approaches.