Using top n recognition candidates to categorize on-line handwritten documents - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Using top n recognition candidates to categorize on-line handwritten documents

Résumé

The traditional weighting schemes used in text categorization for the vector space model (VSM) cannot exploit information intrinsic to texts obtained through on-line handwriting recognition or any OCR process. Especially, top n (n > 1) candidates could not be used without flooding the resulting text with false occurrences of spurious terms. In this paper, an improved weighting scheme for text categorization, that estimates the occurrences of terms from the posterior probabilities of the top n candidates, is proposed. The experimental results show that the categorization performances increase for texts with high error rates.
Fichier non déposé

Dates et versions

hal-00405419 , version 1 (20-07-2009)

Identifiants

Citer

Sebastián Peña Saldarriaga, Emmanuel Morin, Christian Viard-Gaudin. Using top n recognition candidates to categorize on-line handwritten documents. 10th International Conference on Document Analysis and Recognition (ICDAR 2009), Jul 2009, Barcelona, Spain. pp.881-885, ⟨10.1109/ICDAR.2009.137⟩. ⟨hal-00405419⟩
117 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More