Face recognition in different colour spaces

• Main Author: Noraidil Sufyan Kamsani
• Other Authors: Jiang Xudong
• Format: Final Year Project
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/72044
• Institution: Nanyang Technological University

With the development of information technology in today’s globalized world, a great deal of attention has been paid to biometric identification especially the human face recognition. In human face recognition, there is no need to have contact with target which makes it much more convenient as compared to other methods. There are many applications to this method such as identification of criminals, identification of bank account and human-computer interaction systems. In human face recognition, there must be an input image in which the system will compare it with the ones in the database and identify which person the image belongs to. In some cases, an image may not be recognized at all and it will be regarded as unknown. Input images of known or unknown faces may come in different colour spaces, such as gray-level (black and white), RGB, YCbCr and CMYK. This paper presents the usage of method called Principle Component Analysis to recognize faces of various colour spaces and compare its performance.