Title :
Handwritten Farsi character recognition using evolutionary fuzzy clustering
Author :
Dehghan, Mehdi ; Faez, Karim
Author_Institution :
Electr. Eng. Dept., AmirKabir Univ. of Technol., Tehran, Iran
Abstract :
In this paper, a Fuzzy clustering method based on Fuzzy c-Means clustering(FCM) and Evolutionary Strategies (ES) is proposed for handwritten Farsi character recognition. Experimental result showed that not only this algorithm can represent accurately the ambiguity of handwritten characters but also it outperforms the classical crisp based methods especially when word recognition is the main concern.
Keywords :
evolutionary computation; fuzzy set theory; handwritten character recognition; natural language processing; pattern clustering; evolutionary fuzzy clustering; evolutionary strategies; fuzzy c-means clustering; handwritten Farsi character recognition; word recognition; Character recognition; Clustering algorithms; Handwriting recognition; Shape; Sociology; Statistics; Testing;
Conference_Titel :
Signal Processing Conference (EUSIPCO 1998), 9th European
Conference_Location :
Rhodes
Print_ISBN :
978-960-7620-06-4
