Paper Details: Downloads: 564
Serial Number: P1150535160
Title: Arabic / English Identification in a hybrid complex document images
Authors: Yasser M. Abbass and Waleed Fakher and Mohsen Rashwan
Abstract: Document image pre-processing is a series of steps in OCR (optical character recognition) that starts by enhancing the document and ends with segmented characters or words. The accuracy of the final recognition process may vary a lot if a priori knowledge about the word language is present. This paper discusses the document image pre-processing steps starting with image enhancement, noise removal, text/graphics separation and identification and word language identification. We limited our language recognition into classifying either Arabic or English.
Keywords: Segmentation, Pre-Processing, Document Image Analysis, Language Identification, OCR Arabic/English classification
Journal/Conference: ICGST Conference on Graphics, Vision and Image Processing, GVIP-05
Volume:
Issue:
Submission Date: 8/1/2005 12:00:00 AM
Review Date: 10/1/2005 12:00:00 AM
Publishing Date: 12/19/2005 12:00:00 AM
Article Downloads: 564
Download:

Facebook