Recently, great improvement has been achieved in the fingerprint sensing technology and automatic recognition algorithms. Various techniques, including fingerprint acquisition, classification, enhancement and matching, are highly advanced as well. However, there are still some challenge tasks,such as the enhancement for the low quality fingerprint, deformed fingerprints matching and fake finger detection, etc. These issues seriously affect the whole fingerprint recognition system’s performance. In this paper, we will discuss these challenging issues, The main work of this dissertation is as follows: (1) We propose an efficient algorithm based on anisotropic filtering to enhance the low quality fingerprint. The experimental results confirm that the proposed algorithm is effective and robust for the enhancement of low quality fingerprint. (2) We present a novel algorithm for distorted fingerprints matching based on local topological structure. Our algorithm has two main steps. First, the template and input fingerprints were aligned. In this process, the local topological structure matching was introduced to improve the robustness of global alignment. Second, a method based on statistical analysis was introduced to compute the similarity between the template and input fingerprints. Experimental results prove that our algorithm is reliable and effective for fingerprint matching with non-liner distortions. (3) We propose a novel method, fuzzy feature match (FFM) based on local triangle feature set to match the deformed fingerprints. The fingerprint is represented by the fuzzy feature set: local triangle feature set. The similarity between fuzzy feature set was used to characterize the similarity between fingerprints. Experimental results confirm that our algorithm is reliable and effective for fingerprint matching with non-linear distortions. (4) We propose a novel method based on analysis of the elasticity of the finger skin for discriminating fake fingers from real ones. The thin plate spline (TPS) model was used to globally describe the finger distortion. The experimental results on a database of real and fake fingers show that the performance of the new method is very promising.
修改评论