A Fingerprint Inpainting Technique Using Improved Partial Differential Equation Methods

摘要：

In an automatic fingerprint identification system (AFIS), fingerprint inpainting is a critical step in the preprocessing procedures. Because partially fouled, breaking or scratched latent fingerprint is difficult to be correctly matched to a known fingerprint. However, fingerprint restoration proved to be a particularly challenging problem because conventional image restoration schemes can not be directly applied to fingerprint due to the unique ridge and valley structures in typical fingerprint images. Based on partial differential equations algorithm, this paper presents a fingerprint restoration algorithm composing gradient and orientation field. According to gradient and orientation field of the known pixel points, different weights are used in different orientation field in the restoration process. Experimental results demonstrate that the proposed restoration algorithm can effectively reduce the false feature points.

作者: Xiukun Yang Dan Wang Zhigang Yang

作者单位: Information and Communication Engineering College, Harbin Engineering University, Harbin 150001, China

会议类型: 国际会议

会议名称: 2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)

会议地点: 长沙

会议语种:英文

页码: 474-478

在线出版日期: 2010-12-14（万方平台首次上网日期，不代表论文的发表时间）