STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology

STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology

STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology

STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology

STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology
STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD` - Problems of Information Technology
AZERBAIJAN NATIONAL ACADEMY OF SCIENCES

№2, 2018

STUDY OF AZERBAIJANI HAND-PRINTED CHARACTERS RECOGNITION SYSTEM BY NEW FEATURE CLASS AND SVM METHOD`

Elviz A.Ismayilov

Although there are widely spread Latin scripts in Azerbaijani alphabet, intending special symbols and morphological content of the language requires individual approach for character recognition. In this paper, “soft” (close to human mind, constructed on base of characteristics used in alphabet learning) features and SVM for recognition of Azerbaijani hand-printed characters are used. For character classification, bootstrap resampling procedure of support vector machines is used. Results are compared with results of other feature classes and methods (pp.89-94).

Keywords: “soft” features, SVM, hand-printed symbols, recognition system.
DOI : 10.25045/jpit.v09.i2.11
References
  • Cristianini N., Shawe-Taylor J. An Introduction to support vector machines and other kernelbased learning methods. Cambridge University Press, 2000.
  • Aida-zade K.R., Hasanov J.Z., Cursive Handwritten Azerbaijani Latin Text Segmentation Based on Word baseline. / INISTA, Trabzon, Turkey, 2009, pp.63–66.
  • Aida-zade K.R., Hasanov J.Z., Word base line detection in handwritten text recognition systems. // International journal of computer systems science and engineering, 2009, no.4, pp. 49–53.
  • Aida-zade K.R., Mustafayev E.E., On a hierarchical handwritten forms recognition system on the basis of the neural network. / Proceed. Inter. Conf. TAINN, Canakkale, 2003.
  • Moubtahij H.E., Halli A., Satori K., Review of feature extraction techniques for offline handwriting arabic text recognition // International journal of advances in engineering & technology, 2014, pp.50–58.
  • Hadidi G., Delavari H., Persian handwritten words detection based on features, extraction and fuzzy algorithm. //Electrical and electronics engineering: an international journal (elelij) 2015, vol.4, no.2, pp.93–104.
  • Hussain E., Hannan A., Kashyap K., A zoning based feature extraction method for recognition of handwritten assamese characters. // International journal of computer science and technology 2015, vol. 6, no.2, pp.226–228.
  • Lawgali A., Bouridane A., Angelova M., Ghassemlooy Z., Handwritten arabic character recognition: which feature extraction method?. // International journal of advanced science and technology, 2011, vol.34, pp.1–8.
  • Platt J. Fast training of support vector machines using sequential minimal optimization. Advances in Kernel Methods — Support Vector Learning, MIT Press, 1999, pp.185–208.
  • Atienza F.A. Bootstrap feature selection in Support Vector Machines for ventricular fibrillation detection / ESANN’2006, Belgium, 2006, pp.233–238.
  • Chen W., Sui L., Xu Z., Lang Y. Improved Zhang-Suen thinning algorithm in binary line drawing applications // ICSAI, 2012, doi: 10.1109IICSAI.2012.6223430
  • Ismayilov E., Ismayilova N., Fuzzy Features Extraction for Hand-printed character/digit recognition system. / INISTA 2014, Italy, pp.249–253.