Title :
Arabic/Persian cursive signature recognition and verification using line segment distribution
Author :
Chalechale, Abdolah ; Naghdy, Golshah ; Pramaratne, Prashan
Author_Institution :
Sch. of Electr. Comput. & Telecommun. Eng., Wollongong Univ., NSW, Australia
Abstract :
This work proposes a fast method for line segment extraction based on chain code differentiation. It is applied to cursive signature recognition of Arabic/Persian. The evaluation method is introduced to obtain a quantitative value for the recognition rate. The comparative results show the existing differences among the methods in recognition, building time and searching time criteria. The two methods used for comparison are invariant moments and CBLSE method.
Keywords :
feature extraction; handwriting recognition; image segmentation; Arabic-Persian cursive signature recognition; CBLSE method; chain code differentiation; invariant moments; line segment distribution; signature verification; Application software; Computer vision; Face recognition; Feature extraction; Histograms; Image analysis; Image retrieval; Image segmentation; Shape; Telecommunication computing;
Conference_Titel :
Information and Communication Technologies: From Theory to Applications, 2004. Proceedings. 2004 International Conference on
Print_ISBN :
0-7803-8482-2
DOI :
10.1109/ICTTA.2004.1307838
