Incremental classification of invoice documents - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Incremental classification of invoice documents

Hatem Hamza
  • Function : Author
  • PersonId : 830528
Yolande Belaïd
Abdel Belaïd
  • Function : Author


This paper deals with incremental classification and its particular application to invoice classification. An improved version of an already existant incremental neural network called IGNG (Incremental Growing Neural Gas) is used for this purpose . This neural network tries to cover the space of data by adding or deleting neurons as data is fed to the system. The improved version of the IGNG, called I2GNG used local thresholds in order to create or delete neurons. Applied on invoice documents represented with graphs, I2GNG shows a recognition rate of 97.63%.
Fichier principal
Vignette du fichier
versionEditeurPDF.pdf (268.6 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

inria-00346942 , version 1 (05-02-2009)



Hatem Hamza, Yolande Belaïd, Abdel Belaïd, Bidyut Baran Chaudhuri. Incremental classification of invoice documents. 19th International Conference on Pattern Recognition - ICPR 2008, Dec 2008, Tampa, United States. 4 p., ⟨10.1109/ICPR.2008.4761832⟩. ⟨inria-00346942⟩
210 View
839 Download



Gmail Facebook Twitter LinkedIn More