Quality-based Fingerprint Verification

摘要：

The performance of an automatic fingerprint verification system relies heavily on the quality of the captured fingerprint images. In this paper, we propose a new method using fingerprint image quality to improve the accuracy of fingerprint verification. Comparison to conventional fingerprint verification that only use the matching score, a final score is calculated by the matching score and quality score in our method. Experimental results show that our proposed quality-based method leads better accuracy than conventional method. The equal error rate (EER) of our method decreases significantly in each database, with 2.4％ in FVC2000db1, 2.3％ in FVC2000db2, 1.2％ in FVC2002db1, 1.7％ in FVC2002db2, 3％ in FVC2004db1 and 3.5％ in FVC2004db2, respectively.

作者: Lianzheng Zhao Yilong Yin Gongping Yang Wei Qin

作者单位: School of Computer Science and Technology, Shandong University, Jinan 250101

会议类型: 国际会议

会议名称: 2011亚太信号与信息处理协会年度峰会(APSIPAASC 2011)

会议地点: 西安

会议语种:英文

页码: 1-4

在线出版日期: 2011-10-18（万方平台首次上网日期，不代表论文的发表时间）