Online Signature Verification: Present State of Technology

Abstract

The way a person signs his or her name is known to be characteristic of that individual. Signatures are influenced by the physical and emotional conditions of a subject. A signature verification system must be able to detect forgeries, and, at the same time, reduce rejection of genuine signatures. Significant research has been conducted in feature extraction and selection for the application of on-line signature verification. All these features may be important for some problems, but for a given task, only a small subset of features is relevant. In addition to a reduction in storage requirements and computational cost, these may also lead to an improvement in general performance. On the other hand, selection of a feature subset requires a multi-criterion optimization function, e.g. the number of features and accuracy of classification. In this paper all these techniques are reviewed.