Signature Verification System using Different Algorithms

Abstract

In our paper, we proposed a system for signature verification based on pixels and strokes. Nowadays signature is a basic and important verification system for every individual. Everyone has a unique signature and every individual can differ from others. In many areas, this verification system is offline and not so accurate. Online verification is very efficient than the offline one. We use pixel-based method, Harris algorithm and surf to verify whether the signature belongs to the particular person or not. Our proposed system is presented to check signature using pixels, strokes etc. It is efficient enough to compare signatures easily. There is a system using only a single signature they say that it is efficient but everyone may not keep the perfect signature for the first time they may be in a hurry or in a bad mood while signing. So there may be some difference. The main need of this system is if we use human analysis for signature verification then the humans cannot differentiate between the original and fake one and this system can differ them because it takes so many things into consideration like index points, corners point signature thickness at different points so someone cannot fool this system so easily