Title :
An evolutionary neuro-fuzzy approach to recognize on-line Arabic handwriting
Author_Institution :
Dept. of Electr. Eng., Ecole Nat. d´´Ingenieurs de Sfax, Tunisia
Abstract :
The author describes a system that recognizes on-line Arabic cursive handwriting. In this system, a genetic algorithm is used to select the best combination of characters recognized by a fuzzy neural network. The handwritten words used in this system are modelled by a theory of movement generation. Based on this motor theory, the features extracted from each character are the neuro-physiological and biomechanical parameters of the equation describing the curvilinear velocity of the script. The evolutionary approach proposed permits the recognition of cursive handwriting with a segmentation procedure allowing overlapped strokes having neuro-physiological meaning
Keywords :
biomechanics; character recognition; character sets; feature extraction; fuzzy neural nets; genetic algorithms; image segmentation; neurophysiology; biomechanical parameters; character combination; curvilinear script velocity; evolutionary neuro-fuzzy approach; feature extraction; fuzzy neural network; genetic algorithm; handwritten words; motor theory; movement generation theory; neurophysiological parameters; on-line Arabic cursive handwriting recognition; overlapped strokes; segmentation procedure; Character recognition; Equations; Feature extraction; Fuzzy neural networks; Genetic algorithms; Handwriting recognition; Machine intelligence; Shape; System testing; Writing;
Conference_Titel :
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on
Conference_Location :
Ulm
Print_ISBN :
0-8186-7898-4
DOI :
10.1109/ICDAR.1997.619875
