文章基本信息

标题：SURF Based Design and Implementation for Handwritten Signature Verification
本地全文：下载
作者：Surabhi Garhawal ; Neeraj Shukla
期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：8
出版社：S.S. Mishra
摘要：People are comfortable with pen and papers for authentication and authorization in legal transactions. Due to increase in amount of offline handwritten signatures it is very essential that a person's hand written signature to be identified uniquely. In this paper we will evaluate the use of SURF features in handwritten signature verification. For each known writer we will take a sample of three genuine signatures and extract their SURF descriptors. We will calculate the intra class Euclidean distances among SURF descriptors of this known signature. Key points Euclidean distances, Image distances and the intra class thresholds will be stored as templates. We will calculate various intra class distance thresholds like maximum, average, minimum and range. Each signature claimed to be of the known writers, we then ex tract its SURF descriptors and calculate the inter-class distances that is the Euclidean distances between each of its SURF descriptors and those of the known template and image distances between the test signature and members of the genuine section. The intra class threshold will be compared to the inter class threshold for the claimed signature to be measured a forgery. A database of 90 signatures consisting of a training set and a test set will be used. Training set creates 54 genuine signatures from 18 known writers each contributing a sample of 3 signatures. The test set will comprise 36 signatures, 18 genuine signa tures and 18 forged signatures. Specificity of the verifier will be measured and compared with the results from the analysis of Universal signature database
关键词：Static signature verification; SURF feature; FAR (False Acceptance Rate); FRR (False Rejection Rate).