Proposed Preprocessing Algorithm for Signatures Recognition

Signatures are used everyday to authorize the transfer of funds of millions of people, Bank checks, credit cards and legal documents, all of which require our signatures. Different people sign their signatures with different orientation, size, deviation, etc. Even the signatures of the same individual change temporarily in the aforementioned attributes under different circumstances (e.g. the size of the signing space). To minimize the variation in the final results, all signatures are normalized for duration, rotation, position and size. The preprocessing includes some operations such as scaling and rotation to get a fixed size and direction. Introduction Since the beginning of the computer industry, users of computers have been forced to modify their behavior to utilize these devices. User interfaces ranged from confusing to downright hostile. May be the computer should be able to read our handwriting [1]. The benefits of an automatic handwriting recognition system have long been known [2]. A handwritten signature is a kind of agreement. Mostly, it is an agreement to the content of a document. It can be the signature on a contract, an application from an official document [3]. Handwritten signatures come in many different forms and there is a great deal of variability even in signatures of people who use the same language. Some people simply write their name while others may have signatures that are only vaguely related to their name, some signatures may be quite complex while others are simple and appear as if they may be forged easily. It is also interesting to note that the signature style of individuals relates to the environment in which the individual developed their signature. It is known that no two genuine signatures of a person are precisely the same and some signature experts note that if two signatures of the same person written on paper were identical they could be considered forgery by tracing. Successive signatures by the same person will differ and may also differ in scale and orientation [4].