NVP-AUY922 There exist a number of biometrics methods at present e

There exist a number of biometrics methods at present, e.g. signatures, fingerprints, iris, etc. Fingerprints and iris verification require the installation of costly equipments and hence cannot be used at day to day places like banks, etc. There is considerable interest in authentication based on handwritten signature verification system as it NVP-AUY922 is the cheapest way to authenticate a person. Banks and Government bodies recognize signatures as a legal means of authentication. Signature verification technology utilizes the distinctive aspects of the signature to verify the identity of individuals. Criminal experts cannot be employed at every place and hence there has been considerable effort towards developing computerized algorithms that could verify and authenticate the individual’s identity. A handwritten signature is biologically linked to a specific individual. Modern forensic document examiners commonly compare a suspect signature with several examples of known valid signatures. They look for signs of forgery which include: Signatures written at a speed which is significantly slower than the genuine signatures; frequent change of the grasp of the writing implement; rounded line endings and beginnings; poor line quality with hesitant and shake of the line; retracing and patching; and stops in places where the writing should be free. Compared with other electronic identification methods such as fingerprints scanning and retinal vascular pattern screening, it is easier for people to migrate from using the popular pen- and paper signature to one where the online handwritten signature is captured and verified electronically. Many times the signatures are not even readable by human beings. Signature verification problem therefore is concerned with determining whether a particular signature truly belongs to a person or not. There are two approaches to signature verification, online and offline differentiated by the way data is acquired. In offline case, signature is obtained on a piece of paper and later scanned. Offline signature verification deals with a 2D static image record of the signature. It is useful in automatic signature verification found on bank checks and documents authentication. Offline verification techniques are based on limited information available only from shape and structural characteristics of the signature image. A fundamental problem in the field of offline signature recognition is the lack of a significant shape representation or shape factor. In contrast, online signature verification systems are extremely precise. It require the presence of the author during both the acquisition of the reference data and the verification process. This restrict their use to specific applications. Online handwritten signature is usually obtained on an electronic tablet and pen. Online signature verification track down path and other time-variable sequence variables using specially designed tablets or other devices during the act of signing. Automatic online signature verification is an interesting intellectual challenge with many practical applications. This technology examines the behavioral components of the signature such as: stroke order, speed, and pressure, as opposed to comparing visual images of signatures. Unlike traditional signature comparison technologies, online signature verification measures the physical activity of signing. The target of diploid research is to present online handwritten signature verification system based on DWT features extraction and neural network classification. This research paper is organized as the following. An overview on handwritten signature verification structure, specially online, is given in Section 1. Brief survey on current research area in this field and problem statement is presented in Section 2. The proposed system description is briefed in Section 3. The process of extracting features existing in handwritten signatures and discrete wavelet transform (DWT) is discussed in Section 4. Feature matching (classification) is discussed in Section 5. Experimental setup and obtained results are explained in Section 6. Finally, concluding remarks are in Section 7.