Face Recognition using Independent Component Analysis Algorithm
Zaid Abdi · International Journal of Computer Applications · 2015
Face recognition system is an intelligent application, which is able to identify or verify a person from digital sources such as (digital image or a video stream).In spite of the existence of alternative technologies such as fingerprint and iris recognition, the human face remains one of the most popular cues for identity recognition in biometrics.The easy way to recognize any face is by comparing the facial features from the input image (tested image) with a facial database.The most important task in face recognition is how to find the best matching between the tested and training faces.In this paper, how to recognize a face is presented; for evaluating the proposed system, the author was used two various analysis algorithms which are Eigenface and Independent Component Analysis (ICA).The local dataset used in this paper is preprocessed using statistical standard methods.Pre-processing software, Face Identification Evaluation System Version 5.0 under Unix Shell scripts, was written via ANSII C code, which is provided by the Colorado State University (CSU).Independent Component Analysis algorithm (ICA) is written using Matlab R2012b for face recognition implementation.Finally, the results show several graphs by Matlab.In addition, the proposed system shows the best results in Illumination images comparing with Occlusion images.