FACE MORPHING DETECTION USING LOCAL BINARY PATTERN AND CHINESE REMINDER THEOREM
| dc.contributor.author | Kadir Akeem Femi | |
| dc.contributor.author | Abdulrauf Uthman Tosho | |
| dc.contributor.author | Saka Kayode Kami | |
| dc.contributor.author | Aro Taiye | |
| dc.date.accessioned | 2025-03-12T14:57:02Z | |
| dc.date.available | 2025-03-12T14:57:02Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | Face biometrics offer a wide range of uses since they are straightforward for human observers to verify during passport issuing and border control. However, the development of facial biometric attacks has made it possible to evade passport issuance procedures, as demonstrated by morphing attacks. Due to the lengthy computation times associated with facial feature extraction techniques, survey research has revealed that the current face morphing detection method took a while to identify the image attack. Conversely, further study is needed to develop a model to enhance the current face morphing recognition methods. The aim of this study is to develop an enhanced face morphing recognition system using the Local Binary Pattern (LBP) and Residue Number System (RNS). We combine elements from CRT and LBP to extract features from both bona fide and morph images. Extensive experiments are carried out on FRGCv2 datasets to benchmark the proposed method's detection performance and the existing methods. The best classification accuracy of 98% was achieved for the FRGCv2. An equal error rate of 0.02370 was achieved for the FRGCv2 database. The study concluded that the high dimensionality of LBP was well reduced and optimized by the CRT algorithm, which improved the performance of face morphing recognition. The obtained results indicate that the proposed LBP-CRT outperforms existing system with respect to training time, equal error rate, and accuracy of morph detection | |
| dc.identifier.citation | 28 | |
| dc.identifier.uri | https://kwasuspace.kwasu.edu.ng/handle/123456789/4757 | |
| dc.language.iso | en | |
| dc.publisher | Sule Lamido University Journal of Science & Technology | |
| dc.relation.ispartofseries | 8 | |
| dc.title | FACE MORPHING DETECTION USING LOCAL BINARY PATTERN AND CHINESE REMINDER THEOREM | |
| dc.type | Article |