International Association of Scientific Innovation and Research (IASIR)
Artificially recognizing the human face is a challenging problem and is one of those challenging problems having no technique that provides a robust solution to all situations. This paper provides a new technique for human face recognition. Principal Component Analysis (PCA) is used for dimensionality reduction and for feature extraction. A Self Organize Map (SOM) is used as classifier to identify whether the subject is present or not present in the image database. Recognition with SOM is carried out by classifying intensity values of gray scale pixels into different groups.