Off-line handwritten Arabic character segmentation algorithm: ACSA

T. Sari1, L. Souici1, M. Sellami1
1Laboratoire LRI Département d'Informatique, Université Badji Mokhtar Annaba, Annaba, Algeria

Tóm tắt

Character segmentation is a necessary preprocessing step for character recognition in many OCR systems. It is an important step because incorrectly segmented characters are unlikely to be recognized correctly. The most difficult case in character segmentation is the cursive script. The scripted nature of Arabic written language poses some high challenges for automatic character segmentation and recognition. In this paper, a new character segmentation algorithm (ACSA) of Arabic scripts is presented. The developed segmentation algorithm yields on the segmentation of isolated handwritten words in perfectly separated characters. It is based on morphological rules, which are constructed at the feature extraction phase. Finally, ACSA is combined with an existing handwritten Arabic character recognition system (RECAM).

Từ khóa

#Character recognition #Handwriting recognition #Image segmentation #Optical character recognition software #Feature extraction #Natural languages #Computer vision #Graphics #Lattices #Conferences

Tài liệu tham khảo

miled, 1997, Une me?thode rapide de reconnaissance de l'e?criture arabe manuscrite, 16e?me Coll Trait Sign et Images T 2 10.1016/0031-3203(94)90166-X 10.1016/0031-3203(91)90058-D 10.1016/0031-3203(90)90091-X 10.1016/0031-3203(95)00072-0 10.1109/PROC.1973.9030 10.1109/TEC.1961.5219197 10.1109/ICPR.1990.118196 10.1016/0031-3203(90)90078-Y 10.1109/ICPR.1996.546952 10.1109/5.156468 pavlidis, 1981, Algorithms for Graphics and Image Processing 10.1109/34.824821 rosenfeld, 1982, Digital Image Processing, 347 sari, 2001, Proble?matique de la reconnaissance et de la correction des mots arabes, Actes Confe?rence Internationale sur l'Automatisation du Tre?sor de la Langue Arabe ATLA'01, 23 10.1109/IWFHR.2002.1030953 sellami, 1998, Contribution a? la reconnaissance de mots arabes manuscrits, CARI'98 Colloque Africain de Recherche en Informatique, 122 vinciarelli, 2000, A survey on off-line cursive script recognition, IDIAP Research Report RR-00-34 ymin, 1996, On the segmentation of multifont printed uygur scripts, Proc of 13th ICPR, 3, 215 10.1109/TPAMI.1987.4767970 al badr, 1995, Survey and bibliography of arabic optical text recognition, Sign Process, 41, 49, 10.1016/0165-1684(94)00090-M 10.1109/ICPR.1992.201844 10.1109/34.295912 10.1016/S0031-3203(97)00084-8 zahour, 1990, Une me?thode de reconnaissance de l'e?criture manuscrite arabe cursive, The?se de Doctorat 10.1109/21.44052 amin, 1982, Machine recognition of hand written arabic words by the irac ii system, Proc of 6th ICPR, 1, 34 amin, 1980, Hand written arabic character recognition by the irac system, Proc 6th ICPR, 729 10.1109/34.506792 10.1109/34.23114