Feature-level fusion of major and minor dorsal finger knuckle patterns for person authentication

The identification of individuals by their finger dorsal patterns has become a very active area of research in recent years. In this paper, we present a multimodal biometric personal identification system that combines the information extracted from the finger dorsal surface image with the major and minor knuckle pattern regions. In particular, first the features are extracted from each single region by BSIF (binarized statistical image features) technique. Then, extracted information is fused at feature level. Fusion is followed by dimensionality reduction step using PCA (principal component analysis) + LDA (linear discriminant analysis) scheme in order to improve its discriminatory power. Finally, in the matching stage, the cosine Mahalanobis distance has been employed. Experiments were conducted on publicly available database for minor and major finger knuckle images, which was collected from 503 different subjects. Reported experimental results show that feature-level fusion leads to improved performance over single modality approaches, as well as over previously proposed methods in the literature.

Automated summary

In this paper, a multimodal biometric personal identification system combining finger dorsal surface image information with major and minor knuckle pattern regions is presented. Features extracted from each region using BSIF technique are fused at feature level and dimensionality reduced using PCA + LDA scheme for improved discriminatory power. Experimental results show that this feature level fusion approach outperforms single modality methods and previously proposed techniques in the literature.