A survey of fingerprint classification Part I: Taxonomies on feature extraction methods and learning models

作者：

Highlights：

• The state-of-the-art on fingerprint classification is reviewed.

• A double perspective of the fingerprint classification problem is considered: feature extraction and learning models.

• Three taxonomies are proposed: orientation map extraction, singular point detection and feature extraction.

• The different classification approaches considered in fingerprint classification are reviewed.

• A critical discussion is presented, which has led us to develop the second part of this paper.

摘要

•The state-of-the-art on fingerprint classification is reviewed.•A double perspective of the fingerprint classification problem is considered: feature extraction and learning models.•Three taxonomies are proposed: orientation map extraction, singular point detection and feature extraction.•The different classification approaches considered in fingerprint classification are reviewed.•A critical discussion is presented, which has led us to develop the second part of this paper.

论文关键词：Fingerprint classification,Feature extraction,Classification,Fingerprint recognition,SVM,Neural networks,Ensembles,Orientation map,Singular points

论文评审过程：Received 7 October 2014, Revised 9 January 2015, Accepted 8 February 2015, Available online 14 February 2015.

论文官网地址：https://doi.org/10.1016/j.knosys.2015.02.008