Signature Recognition and Verification System via Neural Network

Abstract: As every person has a unique signature with its specific behavioural property ,signatures are widely accepted bio-metric for authentication and identification of a person , so it is very much necessary to prove the authenticity of signature itself. A huge increase in forgery cases relative to signatures induced a need of efficient �Signature Verification System�. These systems can be online or offline based on type of input taken by the system. This paper represents a brief review on various approaches used in signature verification systems. Before extracting different features from the signature, some pre-processing of the signature is done. In pre-processing, the signature is colour normalized and scaled into a standard format. The algorithm is based on extracting global features like Area, Height, and Width etc. Euclidean Distance model is used while finding match between test signature and signature stored in the database. The algorithm gives good recognition rate. If a query signature is in the acceptance range then it is an authenticated signature else, it is a forged signature.

Keywords: Signature Verification, Forgery Detection, Global Features, Euclidean Distance and Verification Technique, FAR, FRR.