| Proj No. | A3101-251 |
| Title | Multimodal Biometric Authentication System for Cyber Security Using Fingerprint, Face, and Palm Recognition |
| Summary | Cybersecurity threats are increasing rapidly, necessitating more robust and secure authentication methods. Traditional password-based security systems are prone to hacking, phishing, and brute-force attacks. This project aims to develop a multimodal biometric authentication system that integrates fingerprint, face, and palm recognition to enhance security and prevent unauthorized access. For fingerprint, Minutiae Matching Algorithm (Used for fingerprint recognition by comparing ridge endings and bifurcations) and Deep Learning methods (CNN-based Fingerprint Recognition) can be used. For face recognition, Deep Learning (FaceNet or ResNet50, CNN) and traditional Methods (PCA, LBPH, or Eigenfaces) will be used. For Palm recognition, Traditional Methods (SIFT, SURF, and Gabor Filter-based feature extraction) and Deep Learning (CNN-based palm recognition) will be used. For combining fingerprint, face, and palm recognition, fusion algorithms like Weighted Score Fusion (Assigns weights to each biometric trait like 50% face, 30% fingerprint, 20% palm) and Machine Learning Classifier (SVM, Random Forest, or CNN-based fusion model) for decision-making will be used. It is expected that by combining multiple biometric features, the system will reduce false positives and negatives, making authentication more robust. This approach significantly improves authentication accuracy and security, making it suitable for various cyber protection applications. |
| 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?: |