Signature is a special case of handwriting which includes special characters and flourishes. Many signatures can be unreadable. They are a kind of artistic handwriting objects. However, a signature can be handled as an image, and hence, it can be recognized using computer vision and artificial neural network techniques. Handwritten signatures are widely utilized as a form of personal recognition. However, they have the unfortunate shortcoming of being easily abused by those who would fake the identification or intent of an individual which might be very harmful. Therefore, the need for an automatic signature recognition system is crucial.
Signature Recognition Overview
The basic goal of the handwritten signatures is to provide an accurate method in order to verify a person’s identity based on the way in which he/she signs his/her name. Hence for this reason, the handwritten signatures are widely accepted, socially and legally throughout the world. There are basically two types of systems – online and offline. The hand-written signature verification uses the features conveyed by every signatory such that the features considered have a unique understanding and the way of signing presents the behavioral biostatistics. Some researchers considered common issues with the extraction of identification data from different biometric types, and protection of such data against conceivable attacks. Handwritten signatures are very much dependant on the user’s psychology and has great difference in different surroundings and time.
Signature recognition is an important research area in the field of authentication of a person as well as documents in e-commerce and banking. We can generally distinguish between two different categories of signature recognition systems: online, for which the signature signal is captured during the writing process, thus making the dynamic information available, and offline for which the signature is captured once the writing process is over and thus, only a static image is available.
Definition of Signature Recognition
Handwritten signatures have a very widely known tradition of use in commonly encountered recognition tasks such as financial transactions and document authentication. Moreover, signatures are easily used and well accepted by the public, and signatures are straightforward to produce with fairly cheap devices. Signature recognition is divided into verification and identification. In the verification, we detect whether or not a claimed signature is genuine and belongs to the claiming signer (accept or reject), in contrast to identification, in which an imposter signature is recognized and referred to the correct signer.
Signature recognition systems measure and analyze the physical activity of signing such as stroke order, pressure applied and the speed of the pen while signing. It differs substantially from the way signature recognition on paper is done which compares the visual aspects of the signature.
Figure 1: Biometric Signature Recognition
There are few key factors our signature depends on:
- Physical and psychological state of the person – includes illness, injuries, fears, heart rate, person’s age, calmness, goodwill, etc.
- Body position – it is not the same if the person is standing or sitting while signing a document, where is person looking at a moment, what is the burden on signing hand, etc.
- Writing surface and writing material (pen) – signature will look different on the various types of paper. It will look different if taken with digitizing tablet or specialized pen. Writing with pen, pencil, stylus or feather also impacts person’s signature.
- Purpose of signing – signature is usually significantly different if taken in formal environment then in informal.
- Environmental factors – environment and people that surround the signatory. This includes noise, luminance, temperature, humidity, etc.
Application of Signature Recognition
This technology has reached far enough and is being implemented in several organizations and sectors such as in banking, insurance, government, education, retail, etc. Dynamic features of signature biometrics can be used in the following applications:
Finance: IT-Processing centers of German savings banks are offering their customers solutions to embed dynamic signatures securely into electronic documents in an Adobe Live Cycle environment.
Insurance: Signing an insurance contract and documenting the consulting process that is required by EU legislation from July 1st 2007 onwards are triggers for several insurance companies to go paperless with either signature capturing tablets connected to a notebook or a tablet PC.
Real Estate: Increasingly popular among real estate agents in USA, there are options of paperless contracting through signing on Tablet PCs.
Health: The hospital of Ingolstadt is capturing and verifying the signatures of their doctors that fill electronic patient records on tablet PCs. The “National Health Service” organization in the United Kingdom has started such an implementation.
Telecom: Signing phone and DSL contracts in the telecom shops is another emerging market.
 Fotak, Tomislav, Miroslav Bača, and Petra Koruga, “Handwritten signature identification using basic concepts of graph theory”, WSEAS Transactions on Signal Processing 7 (2011): pp. 117-129.
 Zaidi, Syed Faraz Ali, and Shahzaan Mohammed, “Biometric Handwritten Signature Recognition”.
 Khuwaja, Gulzar A., and Mohammad S. Laghari, “Offline handwritten signature recognition”, World Academy of Science, Engineering and Technology 59 (2011): pp. 1300-1303