Fingerprint image super resolution using sparse representation with ridge pattern prior by classification coupled dictionaries. Issue 5 (13th January 2017)

• Record Type: Journal Article
• Authors: Bian, Weixin; Ding, Shifei; Xue, Yu
• Is Part Of: IET biometrics. Volume 6:Issue 5(2017)
• Page Start: 342
• Page End: 350
• Publication Date: 2017-01-13
• Subjects: fingerprint identification -- image classification -- image resolution -- image representation -- image reconstruction -- estimation theory; fingerprint image superresolution -- sparse representation -- ridge pattern prior -- classification coupled dictionary -- fingerprint SR image reconstruction -- training patch estimation -- weighted linear projection analysis; Biometric identification -- Periodicals; 570.15195
• DOI: 10.1049/iet-bmt.2016.0097
• Languages: English
• ISSNs: 2047-4938

Abstract

Abstract : A new algorithm for reconstructing the fingerprint super‐resolution (SR) image is presented. The basic idea of the algorithm is to reconstruct the SR image by using sparse representation with ridge pattern prior based on classification coupled dictionaries. First, the orientations of training patches are estimated by the weighted linear projection analysis. In the second procedure, the qualities of patches are assessed by the coherence of point orientations, the training patches are subsequently classified into eight groups based on their own orientations and qualities, and then the training patches of each class are selected from candidate patches by their own quality and the corresponding classification coupled dictionaries are learned. In the end, single SR fingerprint is reconstructed using sparse representation with ridge pattern by classification coupled dictionaries. The experiments with the database of FVC2000, FVC2004 and FVC 2006 are carried out using various SR reconstruction methods. The experiments show that the proposed method achieves better results in comparison with other methods and will help to improve the performance of automatic fingerprint identification system.