Performance evaluation of face verification: a comparative study on different classifiers
The task offace verification is to verify the identity or decide whether the a priori user is an impostor or not from the known a priori identity of the user. The paper presents the performance evaluation carried out using different classifiers for face verification. The paper initially describes th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/10113/1/ShahrinAzuanNazeer2007_Perfor...luationOfFaceVerification.pdf http://eprints.utm.my/10113/ http://www.cita07.org |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1845472309884747776 |
|---|---|
| author | Nazeer, Shahrin Azuan Khalid, Mazuki Omar, Nazaruddin Awang, Mat Kamil |
| author_facet | Nazeer, Shahrin Azuan Khalid, Mazuki Omar, Nazaruddin Awang, Mat Kamil |
| author_sort | Nazeer, Shahrin Azuan |
| building | UTM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Malaysia |
| content_source | UTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | The task offace verification is to verify the identity or decide whether the a priori user is an impostor or not from the known a priori identity of the user. The paper presents the performance evaluation carried out using different classifiers for face verification. The paper initially describes the approaches used for the face representation. and classification of face verification system. It then evaluates the performance of the system by applying three types of classifier: template-based matching, artificial neural network classifier. and Bayesian classifier based on AT & T and local face daJasets. The measures used for performance evaluation are the false acceptance rate (FAR) and false rejection rate (FAR). Based on the experimental results, the artificial neural network classifier provides promising results for face verification with FAR of 4.44% and FRR 4.50% using AT&T face daJaset, and FAR of 3.88 and FRR 4.00 % using local face dataset. |
| format | Conference or Workshop Item |
| id | my.utm.eprints-10113 |
| institution | Universiti Teknologi Malaysia |
| language | en |
| publishDate | 2007 |
| record_format | eprints |
| spelling | my.utm.eprints-101132010-08-26T08:53:38Z http://eprints.utm.my/10113/ Performance evaluation of face verification: a comparative study on different classifiers Nazeer, Shahrin Azuan Khalid, Mazuki Omar, Nazaruddin Awang, Mat Kamil QA75 Electronic computers. Computer science TR Photography The task offace verification is to verify the identity or decide whether the a priori user is an impostor or not from the known a priori identity of the user. The paper presents the performance evaluation carried out using different classifiers for face verification. The paper initially describes the approaches used for the face representation. and classification of face verification system. It then evaluates the performance of the system by applying three types of classifier: template-based matching, artificial neural network classifier. and Bayesian classifier based on AT & T and local face daJasets. The measures used for performance evaluation are the false acceptance rate (FAR) and false rejection rate (FAR). Based on the experimental results, the artificial neural network classifier provides promising results for face verification with FAR of 4.44% and FRR 4.50% using AT&T face daJaset, and FAR of 3.88 and FRR 4.00 % using local face dataset. 2007 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/10113/1/ShahrinAzuanNazeer2007_Perfor...luationOfFaceVerification.pdf Nazeer, Shahrin Azuan and Khalid, Mazuki and Omar, Nazaruddin and Awang, Mat Kamil (2007) Performance evaluation of face verification: a comparative study on different classifiers. In: Fifth International Conference on Information Technology in Asia 2007, 9-12th July 2007, Kuching, Sarawak, Malaysia. http://www.cita07.org |
| spellingShingle | QA75 Electronic computers. Computer science TR Photography Nazeer, Shahrin Azuan Khalid, Mazuki Omar, Nazaruddin Awang, Mat Kamil Performance evaluation of face verification: a comparative study on different classifiers |
| title | Performance evaluation of face verification: a comparative study on different classifiers |
| title_full | Performance evaluation of face verification: a comparative study on different classifiers |
| title_fullStr | Performance evaluation of face verification: a comparative study on different classifiers |
| title_full_unstemmed | Performance evaluation of face verification: a comparative study on different classifiers |
| title_short | Performance evaluation of face verification: a comparative study on different classifiers |
| title_sort | performance evaluation of face verification: a comparative study on different classifiers |
| topic | QA75 Electronic computers. Computer science TR Photography |
| url | http://eprints.utm.my/10113/1/ShahrinAzuanNazeer2007_Perfor...luationOfFaceVerification.pdf http://eprints.utm.my/10113/ http://www.cita07.org |
| url_provider | http://eprints.utm.my/ |