Face Recognition is one of the most popular problems in the field of image processing. Face recognition is a technology which recognize the human by his/her face image. Identifying a person from an unknown face is usually done by comparing the unknown face with the known faces from a face database. Face Recognition system should be able to automatically detect a face in images or face database. Principal component analysis (PCA) is appearance-based statistical technique used for dimension reduction and recognition, and widely used for facial feature extraction and recognition. In this paper we have attempted a comparative study of appearance based statistical method that is principal component analysis. The experiment is used standard face 96 database, local database and pose variation database. The performance of principal component analysis face 96 database is 100%.The experiment is also tested for locally created poor image quality database and pose variation database and its PCA performance is 100%.

Full text: IJEIR_1001_Final.pdf