Title :
Global feature extraction of off-line Arabic handwriting
Author :
Touj, Sofien ; Ben Amara, Najoua ; Amiri, Hamid
Author_Institution :
Inst. Superieure des Etudes Technologiques de Gabes, Tunisia
Abstract :
We present the parameterisation stage of an off-line Arabic handwriting recognition system. The method is based on the Hough transform. This technique is well known for its robustness for detection of lines in images and for its capacity of absorption of distortions as well as noises that can blemish the script. We show through the obtained results the efficiency of this method for the extraction of the global features of Arabic letter tracing.
Keywords :
Hough transforms; document image processing; feature extraction; handwritten character recognition; optical character recognition; Arabic letter tracing; Hough transform; OCR; global feature extraction; line detection; noise; offline Arabic handwriting recognition system; parameterisation stage; Absorption; Data mining; Feature extraction; Handwriting recognition; Humans; Image edge detection; Noise robustness; Optical character recognition software; Shape; Writing;
Conference_Titel :
Systems, Man and Cybernetics, 2002 IEEE International Conference on
Print_ISBN :
0-7803-7437-1
DOI :
10.1109/ICSMC.2002.1173264
