Application of Data Mining Tools for Recognition of Tifinagh Characters

Oujaoura, Mustapha; Ayachi, Rachid El; Bencharef, Omar; Chihab, Younes; Jarmouni, B.

doi:10.14569/specialissue.2013.030201

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Markov model for each character complicates the integration of this system. Many other works was published in the same area but none of them was exceeded and achieved a recognition rate of the proposed approach [5,6]. Also, the fact that some descriptors give a very good result with some classifiers in some situation leads us to conclude that their combination can be a good idea to develop a very efficient system for character recognition especially tifinagh characters.…”

Section: Introductionmentioning

confidence: 94%

Recognition of Isolated Printed Tifinagh Characters

Oujaoura¹,

Minaoui²,

Fakir³

et al. 2014

IJCA

Self Cite

View full text Add to dashboard Cite

Most of the reported works in the field of character recognition systems achieve modest results by using a single method for calculating the parameters of the character image and a single approach in the classification phase of the system. So, in order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of some classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments, Hu moments, Walsh transform, GIST and texture are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the Bayesian network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method with each single classification method are compared with our approach to show its robustness. A recognition rate of 100 % is achieved by using some combined descriptors and classifiers.

show abstract

Section: Introductionmentioning

confidence: 94%