원문정보
초록
영어
This paper presents a feature level fusion approach which uses the improved K-medoids clustering algorithm and isomorphic graph for face and palmprint biometrics. Partitioning around medoids (PAM) algorithm is used to partition the set of n invariant feature points of the face and palmprint images into k clusters. By partitioning face and palmprint images with scale invariant features SIFT points, a number of clusters are formed on both the images. Then on each cluster, an isomorphic graph is drawn. Most probable pair of graphs is searched using iterative relaxation algorithm from all possible isomorphic graphs for a pair of corresponding face and palmprint images. Finally, graphs are fused by pairing the isomorphic graphs into augmented groups in terms of addition of invariant SIFT points and in terms of combining pair of keypoint descriptors by concatenation rule. Experimental results obtained from the extensive evaluation show that the proposed feature level fusion with the improved K-medoids partitioning algorithm improves the performance of the system.
목차
1. Introduction
2. Extraction of SIFT Keypoints
2.1 Extrema Detection in Gaussian Scale-Space
2.2 Keypoints Localization
2.3 Orientation Assignment
2.4 Keypoint Descriptor
3. Feature Partitioning and Isomorphic Graph Representation
3.1 SIFT Keypoints Partitioning using PAM Characterized K-Medoids Algorithm
3.2 Establishing Correspondence between Clusters of Face and Palmprint Images
3.3 Isomorphic Graph Representations of Partitioned Clusters
4. Fusion of Keypoints
5. Matching Criterion and Verification
6. Experimental Evaluation
6.1 Databases
6.2 Experimental Results
6.3 Comparison with a Well Known Technique
7. Conclusion
References