Identification and authentification of handwritten signatures with a connectionist approach
Résumé
TCSF/LER has developed an automatic system to identify or verify offline handwritten signatures, using a connectionnist approach. Our method combines image processing which consists in extracting significant parameters from the signature image and classification by a multi-layer perceptron which uses the previous parameters as input.In this paper, the image processing step is de-scribed according to the intrinsic features of hand-writing. Then, the proposed neural networks are compared with others classifiers as pseudo-inverse, k-nearest-neighbours and k-means and the influence of pre-processing and bad segmentation is measured. On a base of around fifty signers (comprising English, French signatures and paraphs), many experimental results are given for identification and verification purposes.
Origine : Fichiers produits par l'(les) auteur(s)
Licence : Copyright (Tous droits réservés)
Licence : Copyright (Tous droits réservés)