Abstract
Among several palmprint recognition methods proposed recently, coding-based approaches using multi-spectral palmprint images are attractive owing to their high recognition rates. Aiming to further improve the performance of these approaches, this paper presents a novel multi-spectral palmprint recognition approach based on oriented multiscale log-Gabor filters. The proposed method aims to enhance the recognition performances by proposing novel solutions at three stages of the recognition process. Inspired by the bitwise competitive coding, the feature extraction employs a multi-resolution log-Gabor filtering where the final feature map is composed of the winning codes of the lowest filters’ bank response. The matching process employs a bitwise Hamming distance and Kullback–Leibler divergence as novel metrics to enable an efficient capture of the intra- and inter-similarities between palmprint feature maps. Finally, the decision stage is carried pout using a fusion of the scores generated from different spectral bands to reduce overlapping. In addition, a fusion of the feature maps through two proposed novel feature fusion techniques to allow us to eliminate the inherent redundancy of the features of neighboring spectral bands is also proposed. The experimental results obtained using the multi-spectral palmprint database MS-PolyU have shown that the proposed method achieves high accuracy in mono-spectral and multi-spectral recognition performances for both verification and identification modes; and also outperforms the state-of-the-art methods.
Original language | English |
---|---|
Pages (from-to) | 274-286 |
Journal | Neurocomputing |
Volume | 205 |
Early online date | 11 May 2016 |
DOIs | |
Publication status | Published - 12 Sept 2016 |
Keywords
- Palmprint recognition
- Multi-spectral biometrics
- 2D log-Gabor filter
- Competitive coding
- Kullback–Leibler divergence
- Feature map fusion