원문정보
초록
영어
Biometric systems are considered as human pattern recognition systems that can be used for individual identification and verification. The decision on the authenticity is done with the help of some specific measurable physiological or behavioral characteristics possessed by the individuals. Robust architecture of any biometric system provides very good performance of the system against rotation, translation, scaling effect and deformation of the image on the image plane. Further, there is a need of development of real-time biometric system. There exist many graph matching techniques used to design robust and real-time biometrics systems. This paper discusses two graph matching techniques that have been successfully used in face biometric traits.
목차
1. Introduction
2. Preliminaries
2.1. Scale Invariant Feature Transform (SIFT) Descriptor
2.2. Correspondence Graph Definitions
2.3. Probabilistic Relaxation Graph
3. Face Recognition using Complete Graph Topology
3.1 Gallery Image based Match Constraint
3.2. Reduced Point based Match Constraint
3.3. Regular Grid based Match Constraint
3.4. Weighting the Score Reliability
3.5. Fusion of Matching Scores
4. Face Recognition using Probabilistic Relaxation Graph
4.1 Fusion of Matching Scores
5. Experimental Results
5.1 Experimental Results Determined from Complete Graph based Matching
5.2 Experimental Results Determined from Probabilistic Graph Matching
6. Conclusion
References