Title :
Segmentation and Word Spotting Methods for Printed and Handwritten Arabic Texts: A Comparative Study
Author :
Kchaou, M.G. ; Kanoun, Slim ; Ogier, J.
Author_Institution :
Nat. Sch. of Eng. (ENIS), Univ. of Sfax, Sfax, Tunisia
Abstract :
This paper presents a comparative study for word spotting techniques according to holistic approach. So, the current work consists in experimenting word image segmentation, characterization and matching to show the most reliable techniques. The experimental process is done in the same printed and handwritten Arabic dataset. Our aim is to realize an effective system of information retrieval.
Keywords :
handwritten character recognition; image matching; image segmentation; information retrieval; natural language processing; text analysis; word processing; handwritten Arabic dataset; handwritten Arabic texts; information retrieval; printed texts; word image characterization; word image matching; word image segmentation; word spotting methods; Educational institutions; Feature extraction; High definition video; Image segmentation; Information retrieval; Printing; Vectors; Arabic script; holistic approach; information retrieval; text segmentation; word characterization and matching; word spotting;
Conference_Titel :
Frontiers in Handwriting Recognition (ICFHR), 2012 International Conference on
Conference_Location :
Bari
Print_ISBN :
978-1-4673-2262-1
DOI :
10.1109/ICFHR.2012.266
