期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：8
出版社：Journal of Theoretical and Applied
摘要：Human being authentication by offline handwritten signature biometric research has been increasing, especially in the last decade. Verification process of an offline handwritten signature is not trivial task, because an individual rarely signs exactly the same signature whenever he/she signs, which is referred to as intra-user variability. The objective of this paper is proposing a feature vector of an offline handwritten signature by using an efficient algorithm as a strong feature extraction namely Histogram Orientation Gradient (HOG), in order to be passed into Support Vector Machine (SVM) classifier for the recognition operation. An experiment has been conducted to estimate the accuracy and performance of the proposed algorithm by using SIGMA database, which has more than 6,000 genuine and 2,000 forged signature samples taken from 200 individuals. The result has given accuracy as 96.8% as successful rate coming from the error type as: False Accept Rate (FAR) is 3% and False Reject Rate (FRR) is 3.35%.
