Multi-modal fusion of palm-dorsa vein pattern for accurate personal authentication

This paper proposes an efficient multi-modal authentication system which makes use of palm-dorsa vein pattern. There are four levels of fusion in the system and they are multi-algorithm fusion, data fusion, feature fusion and score fusion. Multi-algorithm fusion is applied to extract genuine vein patterns from a vein image by using various vein extraction algorithms. All false vein patterns are eliminated from the extracted patterns through data fusion. Three types of features are obtained from each extracted vein pattern and they are shape features, minutiae and features obtained from hand boundary shape. Third level of fusion is at feature level to fuse minutiae and shape features. Finally, fused features and hand boundary shape features are matched to obtain matching scores which are fused at score level. The proposed system has been tested on the database acquired from 4120 images of 1030 subjects. It has achieved an accuracy of 100%. Experimental results reveal that it performs better than other existing systems.