Bit-string representation of a fingerprint image by normalized local structures

作者：

Highlights：

• Each minutia (reference minutia) in a fingerprint image is represented by a collection of neighboring minutiae enclosed within a circle, referred as a minutia-based local structure (MBLS).

• A texture-based local structure (TBLS) is devised and fused with the MBLS via a weighted feature-level fusion scheme to improve the intermediate fingerprint representation discriminative before bit-string conversion.

• A K-means algorithm is applied to transform the fused MBLSs and TBLSs into a fixed-length bit-string.

• A finger-specific bit-training mechanism is proposed to further enhance the accuracy on fingerprint bit-strings.

摘要

•Due to the proposed normalized local structure, two central minutiae in the two local structures are now resided in the Euclidean space, and their dissimilarity can be computed by the Euclidean distance (ED) in pixel-based space.•Each minutia (reference minutia) in a fingerprint image is represented by a collection of neighboring minutiae enclosed within a circle, referred as a minutia-based local structure (MBLS).•A texture-based local structure (TBLS) is devised and fused with the MBLS via a weighted feature-level fusion scheme to improve the intermediate fingerprint representation discriminative before bit-string conversion.•A K-means algorithm is applied to transform the fused MBLSs and TBLSs into a fixed-length bit-string.•A finger-specific bit-training mechanism is proposed to further enhance the accuracy on fingerprint bit-strings.

论文关键词：Bit-oriented,Fingerprint,Clustering,Fixed-length bit-string representation,Bit-training,Minutiae-based local structure

论文评审过程：Received 8 July 2019, Revised 5 January 2020, Accepted 28 February 2020, Available online 29 February 2020, Version of Record 13 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107323