29-06-2012, 03:31 PM
HAND-WRITTEN SIGNATURE ANALYSIS
HAND-WRITTEN SIGNATURE ANALYSIS.docx (Size: 17.65 KB / Downloads: 33)
Signatures were considered an important tool for authenticating the identity of human beings. So, signature verification was one of the biggest uses for that. Hand-written signature verification is categorized into behavioralbiometrics. Biometrics can be classified into two broad categories,behavioral (signature verification, keystroke dynamics, etc.) andphysiological (iris characteristics, fingerprint, etc.). Handwrittensignature is amongst the first few biometrics to be used evenbefore the advent of computers. Signature verification is widelystudied and discussed using two approaches, i.e., online and off-line. On-line approachuses an electronic tablet and a stylus connected to a computer toextract information about a signature and takes dynamicinformation like; pressure, velocity, etc., whereas in offlineapproach stable dynamic variations are not used for verificationpurpose. Present seminar offers a methodical detail of off-line approach based upon statistical method. Offline systems are more applicable and easy to use incomparison with on-line systems in many parts of the worldhowever it is considered more difficult than on-line verificationdue to the lack of dynamic information. Thisseminar presents asurvey of off-line signature verification approaches beingfollowed in different areas. This being a nascent area underresearch, the survey covers some of the examples of the ways. The proposed algorithmicapproach, found from literature, for the verification of handwritten signatures by applying some statistical method is presented in an understandable form to initiate the research work in this area. The algorithm is studied and explained in a lucid manner with a critical remark for future scope.