IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 2, Ver. III (Mar.-Apr. 2017), PP 33-37 www.iosrjournals.org DOI: 10.9790/0661-1902033337 www.iosrjournals.org 33 | Page Online Signature Verification: A Review Urvashi Chaudhary, Chandra Kanta Samal 2 , Vinesh Kumar 3 # Department of Electrical Engineering, IIT Delhi, Department of Computer Science, Acharya Narender Dev College University of Delhi, Delhi Abstract: In past few decades Online Signature Verification have been employed in many applications such as security control, banking, law enforcement etc. A number of techniques have been proposed in the realization of reliable signature verification system such as Dynamic Time Wrapping (DTW), Hidden Markov Model (HMM), Support Vector Machine (SVM) and Neural Networks (NN)In this paper we have presented a review of research carried out in recent field of online signature verification and made a qualitative analysis of these state-of-the- art approaches. Keywords: Signatures, Verification, fraudulence, feature Extraction, training, Forgery I. Introduction Biometrics is the utilization of physiological traits (face, iris, and fingerprint) or behavioral traits (signature, voice) for the verification of an individual identity. Biometric based authentication system is a trustable alternative to the password-based security systems as it is relatively hard to be forgotten, stolen, or guessed. Signature being a behavioural biometric it is mainly used in the banks to verify the checks and accounts. Unlike physiological biometrics, it is fraught with problem of change over a time and it is not difficult to forge. One of the main challenges in signature verification is related to the signature variability. While signatures from the same user show considerable differences between different captures (high intra-class variability), skilled forgers can perform signatures with high resemblance to the user’s signature (low intra - class variability). Signature verification aims at using such properties for making reliable authentication. However the wide spread acceptance of the signature by the public makes it more suitable for certain lower-security authentication needs. However, signature verification is a challenging task due to practical constraints. For instance, MasterCard estimates a $450 million loss each year due to credit card fraud, likewise some billions of dollars being lost because of fraudulent encashment of checks. Reliable automatic signature verification could be a proper solution to reduce such losses since handwritten signatures are already involved in the credit card transactions and bank checks encashment. 1.1 The Signature Verification Modes There are two modes to the signature verification depending on how the signatures are collected from a user. Offline (static) Signature Verification: In this mode data is acquired by scanning handwritten signatures which are then processed as static images. The verification is based on these static signature images. This mode is useful in automatic verification of signatures obtained from bank checks and other paper documents. Online (dynamic) Signature Verification: In this mode the signatures are captured by social hardware ( e.g. smart pens or pressure sensitive tablets ) which is capable of measuring dynamic properties of a signature in addition to the shape, while shape is the only information in offline signatures. Dynamic information (e.g. pen pressure) makes the signature more unique and more difficult to forge. Applications of online signature verification include identity verification in payments using a credit card; authorization of computer users for accessing sensitive data or programs, authentication of individuals for accessing physical devices or buildings, and protection of small personal devices from unauthorized usage. Online signature verification is more robust, reliable and accurate than offline signature verification as its dynamic properties make the process of forging an online signature more difficult. Therefore online signature has become an attractive biometric method as it facilitates the authentication of the internet transactions and contracts (e-commerce, e-banking, e-business, e-contract). Need Signature is a special characteristic of any person. By the help of signature we can identify the person. In today day to day life as we talk about the verification of any person, we normally verify them by two ways firstly by face and secondly by signature. In banking or security system the person is normally verified by his or her signature. Hence we can say that the signature is alternate way to identify the person. In most of the organizations, the signature is normally verified by their experts by matc hing old signature’s samples.