| Proj No. | A3102-251 |
| Title | Biometric-Based Authentication System Using traditional and AI/ML algorithms for Fingerprint recognition |
| Summary | Recent studies show that use of online services has significantly increased, however, the online attacks have also been on the rise at the same time and in majority cases, the attack was results of an unauthorized access. Thus, this project aims to develop a biometric-based authentication system that uses fingerprint recognition for secure access control. It integrates traditional image processing algorithms with AI/ML techniques to enhance accuracy and security. Students will be required to extract fingerprint features using Traditional Image Processing Approach (Gabor Filters & Ridge Extraction to detect fingerprint ridges. Use Euclidean Distance Matching for fingerprint comparison) and AI/ML-Based Approach (Use CNNs to extract deep features. Use a Siamese Neural Network for one-to-one fingerprint verification). Finally, students will be required to compare traditional image processing techniques with machine learning (ML) & deep learning (DL) algorithms to improve fingerprint matching accuracy and resistance to spoofing attacks. |
| Supervisor | A/P Mohammed Yakoob Siyal (Loc:S2 > S2 B2A > S2 B2A 28, Ext: +65 67904464) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Computer Engineering I (Loc: S2-B4c-15) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |