Comparison of Eye Imaging Pattern Recognition Using Neural Network

• Main Authors: Wan Daud, Wan Mohd Bukhari, Sulaima, Mohamad Fani, M. Nasir, Mohamad Naim, Yahaya, M. S
• Format: Article
• Language: English
• Published: ICOMEIA2014 Proceedings 2014
• Subjects: T Technology (General)
• Online Access: http://eprints.utem.edu.my/id/eprint/12450/1/ICOMEIA-WMB.pdf; http://eprints.utem.edu.my/id/eprint/12450/; http://icomeia2014.unimap.edu.my/openconf/modules/request.php?module=oc_proceedings&action=proceedings.php&a=Accept
• Institution: Universiti Teknikal Malaysia Melaka

The beauty of eye recognition system that it is used in automatic identifying and verifies a human weather from digital images or video source. There are various behaviors of the eye such as the color of the iris, size of pupil and shape of the eye. This study represents the analysis, design and implementation of a system for recognition of eye imaging. All the eye images that had been captured from the webcam in RGB format must through several techniques before it can be input for the pattern and recognition processes. The result shows that the final value of weight and bias after complete training 6 eye images for one subject is memorized by the neural network system and be the reference value of the weight and bias for the testing part. The target classifies to 5 different types for 5 subjects. The eye images can recognize the subject based on the target that had been set earlier during the training process. When the values between new eye image and the eye image in the database are almost equal, it is considered the eye image is matched.