Reference Work Entry

Encyclopedia of Biometrics

pp 1382-1387


Signature Matching

  • Marcos Martinez-DiazAffiliated withBiometric Recognition Group – ATVS, Escuela Politecnica Superior, Universidad Autonoma de Madrid, Campus de Cantoblanco
  • , Julian FierrezAffiliated withUniversidad Autonoma de Madrid
  • , Seiichiro HangaiAffiliated withDepartment of Electrical Engineering, Tokyo University of Science


Signature similarity computation


The objective of signature matching techniques is to compute the similarity between a given signature and a signature model or reference signature set. Several pattern recognition techniques have been proposed as matching algorithms for signature recognition. In online signature verification systems, signature matching algorithms have followed two main approaches. Feature-based algorithms usually compute the similarity among multidimensional feature vectors extracted from the signature data with statistical classification techniques. On the other hand, function-based algorithms perform matching by computing the distance among time sequences extracted from the signature data with technique such as hidden Markov models and dynamic time warping. Off-line signature matching has followed many different approaches, most of which are related to image processing and shape recognition.

This entry focuses on online signature matching, although off ...

This is an excerpt from the content