Fingerprint classification by a hierarchical classifier

作者：

Highlights：

• A regularized fingerprint orientation diffusion model is proposed.

• A five-stage hierarchical classifier is proposed for fingerprint classification.

• The orientation model is tested over FVC-onGoing and a promising result is obtained.

• A classification accuracy of 95.9% for five-class classification is obtained on NIST 4.

摘要

Highlights•A regularized fingerprint orientation diffusion model is proposed.•A five-stage hierarchical classifier is proposed for fingerprint classification.•The orientation model is tested over FVC-onGoing and a promising result is obtained.•A classification accuracy of 95.9% for five-class classification is obtained on NIST 4.

论文关键词：Fingerprint classification,Complex filter response,Support vector machine,Ridge line flow,Hierarchical classifier

论文评审过程：Received 20 March 2012, Revised 25 March 2013, Accepted 9 May 2013, Available online 22 May 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.05.008