Off-line signature verification using directional PDF and neural networks

Author

Sabourin, Robert ; Drouhard, Jean-Pierre

Author_Institution

Lab. de Modelisation Tridimensionnelle et d´´Imagerie Ecole de Technol. Superieure, Montreal, Que., Canada

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

321

Lastpage

325

Abstract

The first stage of a complete automatic handwritten signature verification system (AHSVS) is described in this paper. Since only random forgeries are taken into account in this first stage of decision, the directional probability density function (PDF) which is related to the overall shape of the handwritten signature has been taken into account as feature vector. Experimental results show that using both directional PDFs and the completely connected feedforward neural network classifier are valuable to build the first stage of a complete AHSVS

Keywords

character recognition; feature extraction; feedforward neural nets; probability; AHSVS; automatic handwritten signature verification system; directional PDF; directional probability density function; feature vector; feedforward neural network classifier; neural networks; random forgeries; Cameras; Feature extraction; Feedforward neural networks; Forgery; Handwriting recognition; Image sampling; Neural networks; Probability density function; Production systems; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2915-0

Type

conf

DOI

10.1109/ICPR.1992.201782

Filename

201782