Online signature verification

Handwritten signature verification systems are most widely used in any financial and other documentation activities for authorization of identity of any human activity. However still these types of systems are mainly based on manual verification, such that a person only by looking with eyes and comparing the given signature with the test signature. Thus a more robust system is required which can be based on some computer based classification. For this aim, in this thesis, an online signature verification is proposed. This purposed system is simply based on normalized dynamic features of the signature using Dynamic Time Warping (DTW) as the classification method. Online Signature Verification is a process of verifying the writer's identity by using signature verification system. This system can be used as a security system such as verification for assessing entry application and password substitutions. Signature verification technology requires primarily a digitizing tablet and a special pen connected to the Universal Serial Bus Port (USB port) of a computer. An individual can sign on the digitizing tablet using the special pen regardless of his signature size and position. The signature is characterized as pen-strokes consisting x-y coordinates and the data will be stored in the signature database in the form of a .txt file. These characteristics uniquely identify a person and cannot be imitated or stolen.