Abstract
Biometric recognition is a viable and powerful improvement to any security systems. It varies uniquely from one person to another and each of them will never be the same as the other. Without it, anyone could lie or forge anything and acquire entrance onto restricted areas as long as the other party believes it. Such incidents could be seen to occur in UiTM Melaka Jasin Campus as it only requires showing a student card, no matter who‟s, for entrance into campus grounds. In order to overcome this slight but crucial problem, the Biometric Recognition System for UiTM Melaka Student‟s Campus Entrance is proposed. The system detects the facial structures and features between the student card image and it’s holder thus determining whether it is the same person or not. It is likely that the holder is not the owner if the results come out below than 50% as the system has a facial features detection rate of 100%. The system utilized a combination of algorithms such as the Viola-Jones algorithm and SURF for facial structures and features detection. Upon testing, the system achieved 51.44% accuracy out of 100 testing images of 50 students.
Metadata
Item Type: | Student Project |
---|---|
Creators: | Creators Email / ID Num. Jamaluddin, Khairul Rohaizzat UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Computer software > Application program interfaces Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Artificial immune systems. Immunocomputers Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Algorithms |
Divisions: | Universiti Teknologi MARA, Melaka > Jasin Campus > Faculty of Computer and Mathematical Sciences |
Keywords: | Biometric recognition; Security systems; Algorithms |
Date: | 2017 |
URI: | https://ir.uitm.edu.my/id/eprint/21363 |
Download
TD_KHAIRUL ROHAIZZAT JAMALUDDIN M CS 17_5.pdf
Download (325kB) | Preview