TCSF/LER has developed an automatic system to identify or verify off-line 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 described according to the intrinsic h t u r e s of handwriting. Then, the proposed neural networks are compared with others classifiers as pseudcdnverse, 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 paraphes), many experimental results are given for identification and verification purposes.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.