Offline signature verification using nn, KNN and SURF
Jaya Sharma, Kumud Sachdeva · International Journal in IT & Engineering · 2016
Signature is one of the most popular and widely accepted bio-metric for authentication and identification of a person. In order to permit a check or it is a mark as well as mark made by an individual to execute a document and signify knowledge, acceptance, or obligation. There are diverse techniques in the course of which one can categorize the signature as accurate or fictitious. As Major documents such as demand drafts, property papers are generally subjectedto malpractices. Hence prerequisite of automatic signature verification becomes unavoidable as the degree of processing and locating the individuals augmented several fold in legal and financial transaction. Thus an automated signature verification system is mandatory. The principal objective of the signature verification system is to make out the exclusive characteristics of personal styles of writing. Basically signature recognition deals with identifying a person whereas verification deals with detecting whether the signature is genuine or fake. The inevitable side-effect of the signatures is that they can be misused for the purpose of the faking a data genuineness Different techniques give different figures for measurement of FAR (False Rate), FRR (False Rejection Rate), EER(Equal Error Rate)which were evaluated further.