Form Analysis by Neural Classification of Cells

Yolande Belaïd (1) , Abdel Belaïd (1)

1 READ - READ

Our aim in this paper is to present a methodology for linearly combining multi neural classifier for cell analysis of forms. Features used for the classification are relative to the text orientation and to its character morphology. Eight classes are extracted among numeric, alphabetic, vertical, horizontal, capitals, etc. Classifiers are multi-layered perceptrons considering firstly global features and refining the classification at each step by looking for more precise features. The recognition rate of the classifiers for 3. 500 cells issued from 19 forms is about 91 %.

Mots clés: Form Cell; Neural Approach; Cell Classification; Form Analysis

Domaines: Interface homme-machine [cs.HC]; Réseau de neurones [cs.NE]; Traitement du texte et du document

Yolande Belaïd, Abdel Belaïd. Form Analysis by Neural Classification of Cells. S. -W. Lee and Y. N akano. Document Analysis Systems: Theory and Practice: Third IAPR Workshop, DAS'98. Selected Papers, 1655 (1655), Springer Verlag, pp.58-71, 1999, Lecture Notes in Computer Science. ⟨inria-00133716⟩