Face Recognition Based on Multi- Scale Face Components by Artificial Neural Networks

Abstract: Face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. Face recognition is a challenge in image analysis and computer vision and received a great attention in last few years. Here we have mentioned some of the face recognition techniques that are worth useful and there are many like these techniques. Recognizing objects from large image databases, histogram based methods have proved simplicity and usefulness in last decade. Initially, this idea was based on color histograms. For achieving the perfection in accuracy of proposed system, the merger of histogram and Phase-Only Correlation (POC) techniques is used in implementation of suggested system. For training, grayscale images with 256 bins are used.

Keywords: Face recognition, Phase-Only Correlation (POC) techniques. Processed Histogram Phase Only correlation. Principal Component Analysis (PCA). Olivetti Research Laboratory (ORL)