A neuro-fuzzy inference engine for Farsi numeral characters recognition

Information Systems Dept., DeGroote School of Business, McMaster University, Hamilton, ON, Canada
Expert Systems with Applications (Impact Factor: 2.24). 09/2010; 37(9):6327-6337. DOI: 10.1016/j.eswa.2010.02.088
Source: DBLP


Character recognition of Farsi and Arabic texts as an open and demanding problem needs to encounter sophisticated specifications of the characters such as their shapes, continuity, dots and also, different fonts. Utilizing fuzzy set theory as a tolerant approach toward uncertainty and vagueness and artificial neural networks as a machine learning method in this paper, we propose a neuro-fuzzy inference engine to recognize the Farsi numeral characters. This engine takes holistic approach of character recognition through the comparison of the unknown character’s features with the features of the existing characters that itself is characterized through Mamdani inference engine on fuzzy rules which is largely enhanced with a multi layer perceptron neural network’s learning on features of the different fonts’ characters which leads to more comprehensive recognition of Farsi numeral characters in the proposed system. Having applied this novel engine on a dataset of unknown numeral characters consisted of 33 different Farsi fonts, it yielded more accurate results than the corresponding researches. The recognition rates of unknown numeral characters are greater than 97% except for Farsi character 4, so as the proposed schema could not score a better result than 95% for this numeral character which implies its recognition is still in need of more enhancement.

  • Source
    • "Furthermore, gradient features have been proposed for handwritten character recognition [14] [15] where Awaidah and Mahmoud combined them with structural and concavity features for the recognition of Arabic (Indian) numerals using hidden Markov models (HMM) [16]. A probabilistic neural network (PNN) approach for the recognition of the handwritten Indian numerals [17] based on the center of gravity and a set of vectors to the boundary points of the digit has been presented however Montazer et al. [18] proposed a holistic approach using neuro-fuzzy inference engine to recognize the Farsi numeral characters. Finally, Impedovo et al. introduced a genetic algorithm based clustering approach using zoning features [19] whereas an adaptive zoning techniques for handwritten digit recognition are presented [20] [21] where the features are extracted according to an optimal zoning distribution. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an efficient handwritten digit recognition system based on support vector machines (SVM). A novel feature set based on transition information in the vertical and horizontal directions of a digit image combined with the famous Freeman chain code is proposed. The main advantage of this feature extraction algorithm is that it does not require any normalization of digits. These features are very simple to implement compared to other methods. We evaluated our scheme on 80,000 handwritten samples of Persian numerals and we have achieved very promising results.
    Full-text · Article · May 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: The design and implementation of a local area network for the Department of Mathematics and Computer Science at Western Carolina University are presented. This was part of a project to establish one of many local area networks which will eventually be connected by a campus backbone. The various design stages and work details that should be addressed before installing a local area network are discussed. A schematic design of the layout of the network is included
    No preview · Conference Paper · Apr 1993
  • [Show abstract] [Hide abstract]
    ABSTRACT: The performance of a code-division multiple-access (CDMA) cellular system for different RF modulation techniques, such as quadrature phase-shift keying (QPSK) and differential phase-shift keying (DPSK), is analyzed. The analysis emphasizes how voice quality deteriorates with increasing system load and determines the maximum acceptable load and minimum acceptable E <sub>b</sub>/ N <sub>0</sub> for producing acceptable quality voice
    No preview · Conference Paper · Apr 1993
Show more