A New Method to Enhance Fingerprint Image Reconstruction Using Deep Boltzmann Machine

Abstract

A new algorithm for increasing fingerprint with large noise is enhanced in this paper. The fingerprint image is first pre-improved depending on Gabor filters, and local adaptive thresholds are used to achieve a binary fingerprint. In order to reconstruct these regions, which have incorrectly improved in the first stage, the classification deep Boltzmann machines (DBMs) with a range pattern before are used. The proposed technique completely enhances each other by a traditional technique of improvement relying upon Gabor filtering and deep learning. The FVC 2004, Biometrika, Italdata, Crossmatch, and Swipe databases are conducted by different techniques. Experiments indicate that in contrast with other techniques, the suggested technique achieves stronger outcomes and enhances fingerprint performance. Experimental findings indicate that the use of the proposed technique allows the extremely accurate fingerprint image to be reconstructed. The average performance of the proposed method is 91.31, which is better than the average performance of another method. When there exist 18,000 features, the running time of UniNap1, ATVS, Dermalog, and CAoS are 68, 74, 59, 87 s respectively, while the running time of the proposed method is 45s.The proposed technique is superior for removing noise than other techniques, in particular for improving fingerprints of poor performance.