Recognition of persian numeral fonts by combining the entropy minimized fuzzifier and fuzzy grammar

Authors:
H. Ebrahimnezhad;Gh. A. Montazer;N. Jafari
Affiliations:
School of Engineering, Tarbiat Modarres University, Tehran, Iran;School of Engineering, Tarbiat Modarres University, Tehran, Iran;School of Engineering, Tarbiat Modarres University, Tehran, Iran
Venue:
AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
Year:
2007

Citing 5
Cited 0

A high accuracy algorithm for recognition of handwritten numerals

Pattern Recognition
Off-Line, Handwritten Numeral Recognition by Perturbation Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings

Pattern Recognition
Fuzzy technique based recognition of handwritten characters

Image and Vision Computing
Fuzzy model based recognition of handwritten numerals

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a combined method for recognition of multi-font Persian numeral characters. At first, the binary image of a character is divided into a fixed number of sub-images called boxes. The average vector distance and angle of each box are computed as features. These features have some variations in different fonts of any character. So, we can employ the fuzzy sets to face with recognition problem. To have a best effect of fuzzy measure for any box features we employ an exponential fuzzification involving two extra parameters, which take account of the variations in the fuzzy sets. These parameters are obtained by minimizing the entropy of fuzzy membership function. After defuzzification, the three most probable candidates of numbers are selected. These candidates are post-processed with another fuzzy recognition system which uses the other features of numerals, i.e. the type of primitives. This combined method increases the robustness of recognition.