A Fingerprint Indexing Method Based on Minutia Descriptor and Clustering (1811.08645v1)

Abstract: In this paper we propose a novel fingerprint indexing approach for speeding up in the fingerprint recognition system. What kind of features are used for indexing and how to employ the extracted features for searching are crucial for the fingerprint indexing. In this paper, we select a minutia descriptor, which has been used to improve the accuracy of the fingerprint matching, as a local feature for indexing and construct a fixed-length feature vector which will be used for searching from the minutia descriptors of the fingerprint image using a clustering. And we propose a fingerprint searching approach that uses the Euclidean distance between two feature vectors as the similarity between two indexing features. Our indexing approach has several benefits. It reduces searching time significantly and is irrespective of the existence of singular points and robust even though the size of the fingerprint image is small or the quality is low. And the constructed indexing vector by this approach is independent of the features which are used for indexing based on the geometrical relations between the minutiae, like one based on the minutiae triplets. Thus, the proposed approach could be combined with other indexing approaches to gain a better indexing performance.