Unsupervised Categorization of Heterogeneous Text Images Based on Fractals
| Autor: | R. Mullot, M.A. Alimi, B. Khelifi, Nizar Zaghden |
|---|---|
| Přispěvatelé: | REsearch Group in Intelligent Machines [Sfax] (REGIM-Lab), École Nationale d'Ingénieurs de Sfax | National School of Engineers of Sfax (ENIS), Laboratoire Informatique, Image et Interaction - EA 2118 (L3I), Université de La Rochelle (ULR), L3I, IAPR, Zaghden, Nizar |
| Jazyk: | angličtina |
| Rok vydání: | 2008 |
| Předmět: |
Matching (statistics)
documents anciens Computer science Feature extraction 0211 other engineering and technologies ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Character encoding 02 engineering and technology classes Text mining Font 0202 electrical engineering electronic engineering information engineering 021101 geological & geomatics engineering [INFO.INFO-MM] Computer Science [cs]/Multimedia [cs.MM] Contextual image classification business.industry Search engine indexing segmentation [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] Pattern recognition Categorization fontes Pattern recognition (psychology) dimensions fractales ComputingMethodologies_DOCUMENTANDTEXTPROCESSING 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | international conference on pattern recognition International conference on Pattern Recognition International conference on Pattern Recognition, Dec 2008, Tampa, United States. pp.1-4,INSPEC Accession Number: 10444373 ICPR |
| Popis: | 04; International audience; This paper deals about text extraction from heterogeneous documents for categorizing documents and indexing tasks. The purpose of this work is to find similar text regions basing on their fonts. First text regions are extracted, and then font matching is performed using fractal descriptors. Experiments are done for both maps and ancient documents. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|