Offline Handwritten Signature Verification Using Decision Tree

Abstract

AbstractThe verification of a signature is an exigent research area as the signatures of two individuals may have similarity whereas the signatures of a person may vary at various circumstances. The accuracy of signature verification framework relies mainly upon the classifier used for the classification process and the feature extraction scheme. Keeping this perspective in sight, the goal of this study is to see how well a decision tree classifier combined with a Local Binary Pattern feature set can be utilized to construct an offline writer-independent signature verification system. To evaluate the system’s performance, two signature databases of 100 and 260 writers are used. Genuine signatures as well as random forgery signatures are utilized for the development of the desired system, while genuine signatures, as well as random forgery, unskilled forgery, and simulated forgery are used to test the performance of the developed system. In simulation study, false acceptance rate of 1.00%, 7.00% and 11.00% for random, unskilled, and simulated forgery signatures, respectively is obtained whereas the false rejection rate of 0.00% is achieved using Local Binary Pattern features.KeywordsDecision treeWriter-independent approachFalse acceptance rateOffline-signature verificationFalse rejection rateLocal binary pattern features