Title :
Fuzzy logic based handwritten character recognition
Author :
Hanmandlu, M. ; Chakraborty, Shiladri
Author_Institution :
Dept. of Comput. Eng., Multimedia Univ., Selongor
fDate :
6/23/1905 12:00:00 AM
Abstract :
This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this approach, the character image is partitioned into a fixed number of sub images called boxes. The features consist of normalized vector distance (γ) and angle (α) from each box to a fixed point. The recognition schemes used are back propagation neural network (BPNN) and fuzzy logic. The recognition rate is found to be around 100% with the fuzzy based approach on the standard database
Keywords :
backpropagation; feature extraction; fuzzy logic; handwritten character recognition; image segmentation; neural nets; backpropagation neural network; box method; feature extraction; fuzzy logic; handwritten character recognition; image partitioning; normalized vector angle; normalized vector distance; Character recognition; Computer science; Feature extraction; Fuzzy logic; Handwriting recognition; Image databases; Multi-layer neural network; Neural networks; Optical character recognition software; Shape;
Conference_Titel :
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location :
Thessaloniki
Print_ISBN :
0-7803-6725-1
DOI :
10.1109/ICIP.2001.958046
