CVSL Logo
FrancaisHome
AboutPeopleResearchPublicationsEventsProfile
About
Publications

 

 

 

CERVIM

REPARTI

MIVIM

Cursive Character Detection using Incremental Learning


Jean-François Hébert and Marc Parizeau


Abstract - This paper describes a new hybrid architecture for an artificial neural network classifier that enables incremental learning. The learning algorithm of the proposed architecture detects the occurrence of unknown data and automatically adapts the structure of the network to learn these new data, without degrading previous knowledge. The architecture combines an unsupervised self-organizing map with a supervised Perceptron network to form the hybrid Self- Organizing Perceptron (SOP) network. Recognition experiments conducted on isolated characters taken in the context of cursive words show the promising incremental capabilities of this SOP network.

download document

Bibtex:

@inproceedings{Hébert50,
    author    = { Jean-François Hébert and Marc Parizeau },
    title     = { Cursive Character Detection using Incremental Learning },
    booktitle = { Proc. of the International Conference on Document Analysis and Recognition (ICDAR) },
    pages     = { 808-811 },
    year      = { 1999 },
    month     = { September },
    location  = { Bangalore (India) }
}

Last modification: 2002/06/14 by parizeau

     
   
   

©2002-. Computer Vision and Systems Laboratory. All rights reserved