Offline handwritten pre-segmented character recognition of Gurmukhi script

• Autorzy: Kumar M. , Jindal M. K. , Sharma R. K. , Jindal S. J.

Identyfikatory

DOI

10.22630/MGV.2016.25.1.5

• Języki publikacji: EN

Abstrakty

EN

In this paper, we have proposed a feature extraction technique for recognition of segmented handwritten characters of Gurmukhi script. The experiments have been performed with 7000 specimens of segmented offline handwritten Gurmukhi characters collected from 200 different writers. We have considered the set of 35 basic characters of the Gurmukhi script and have proposed the feature extraction technique based on boundary extents of the character image. PCA based feature selection technique has also been implemented in this work to reduce the dimension of data. We have used k-NN, SVM and MLP classifiers. SVM has been used with four different kernels. In this work, we have achieved maximum recognition accuracy of 93.8% for the 35-class problem when SVM with RBF kernel and 5-fold cross validation technique were employed.

Słowa kluczowe

EN

feature extraction; classification; PCA; k-NN; SVM; MLP

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2016
• Tom: Vol. 25, No. 1/4
• Strony: 45--55
• Opis fizyczny: Bibliogr. 16 poz., il., schem., wykr.

Twórcy

autor

Kumar M.

• Maharaja Ranjit Singh Punjab Technical University, Department of Computer Applications, GZS Campus College of Engineering & Technology, Bathinda, Punjab, India

autor

Jindal M. K.

• Panjab University Regional Centre, Department of Computer Science & Applications, Muktsar, Punjab, India

autor

Sharma R. K.

• Thapar University, Department of Computer Science & Engineering, Patiala, Punjab, India

autor

Jindal S. J.

• Yadavindra College of Engineering, Talwandi Sabo, Computer Science & Engineering Section, Bathinda, Punjab, India

Bibliografia

• [1] U. Bhattacharya, M. Shridhar, and S. K. Parui. On recognition of handwritten bangla characters. In P. K. Kalra and S. Peleg, editors, Proc. 5th Indian Conf. Computer Vision, Graphics and Image Processing ICVGIP 2006, pages 817–828. Springer Berlin Heidelberg, Madurai, India, December 13-16, 2006. doi:10.1007/11949619_73.
• [2] H. Bunke and T. Varga. Off-line Roman cursive handwriting recognition. In B. B. Chaudhuri, editor, Digital Document Processing: Major Directions and Recent Advances , pages 165–183. Springer, London, 2007. doi:10.1007/978-1-84628-726-8_8.
• [3] E. Grosicki and H. E. Abed. ICDAR 2009 Handwriting Recognition Competition. In Proc. 10th Int. Conf. Document Analysis and Recognition ICDAR 2009, pages 1398–1402, July 2009. doi:10.1109/ICDAR.2009.184.
• [4] A. Kacem, N. Aouïti, and A. Belaïd. Structural features extraction for handwritten arabic personal names recognition. In Proc. Int. Conf. Frontiers in Handwriting Recognition ICFHR 2012, pages 268–273, September 2012. doi:10.1109/ICFHR.2012.276.
• [5] M. Kumar, M. K. Jindal, and R. K. Sharma. A novel hierarchical technique for offline handwritten Gurmukhi character recognition. National Academy Science Letters, 37(6):567–572, December 2014. doi:10.1007/s40009-014-0280-1.
• [6] M. Kumar, M. K. Jindal, and R. K. Sharma. Offline handwritten Gurmukhi character recognition: Analytical study of different transformations. Proceedings of the National Academy of Sciences, India Section A: Physical Sciences, 87(1):137–143, March 2017. doi:10.1007/s40010-016-0284-y.
• [7] M. Kumar, R. K. Sharma, and M. K. Jindal. Efficient feature extraction techniques for offline handwritten Gurmukhi character recognition. National Academy Science Letters, 37(4):381–391, August 2014. doi:10.1007/s40009-014-0253-4.
• [8] R. S. Kunte and R. D. S. Samuel. A simple and efficient optical character recognition system for basic symbols in printed Kannada text. Sadhana, 32(5):521–533, October 2007. http://www.ias.ac.in/article/fulltext/sadh/032/05/0521-0533.
• [9] L. M. Lorigo and V. Govindaraju. Offline Arabic handwriting recognition: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(5):712–724, May 2006. doi:10.1109/TPAMI.2006.102.
• [10] U. Pal, T. Wakabayashi, and F. Kimura. Handwritten Bangla compound character recognition using gradient feature. In Proc. 10th Int. Conf. Information Technology ICIT 2007, pages 208–213, December 2007. doi:10.1109/ICIT.2007.62
• [11] U. Pal, T. Wakabayashi, and F. Kimura. Comparative study of Devnagari handwritten character recognition using different feature and classifiers. In Proc. 10th Int. Conf. Document Analysis and Recognition ICDAR 2009, pages 1111–1115, July 2009. doi:10.1109/ICDAR.2009.244.
• [12] N. Sharma, U. Pal, F. Kimura, and S. Pal. Recognition of off-line handwritten Devnagari characters using quadratic classifier. In P. K. Kalra and S. Peleg, editors, Proc. 5th Indian Conf. Computer Vision, Graphics and Image Processing ICVGIP 2006, pages 805–816. Springer Berlin Heidelberg, Madurai, India, December 13-16, 2006. doi:10.1007/11949619-72.
• [13] D. C. Tran, P. Franco, and J. M. Ogier. Accented handwritten character recognition using SVM – application to French. In Proc. 12th Int. Conf. Frontiers in Handwriting Recognition ICFHR 2010, pages 65–71, November 2010. doi:10.1109/ICFHR.2010.16.
• [14] X. Wang, V. Govindaraju, and S. Srihari. Holistic recognition of handwritten character pairs. Pattern Recognition, 33(12):1967–1973, 2000. doi:10.1016/S0031-3203(99)00204-6.
• [15] T. Y. Zhang and C. Y. Suen. A fast parallel algorithm for thinning digital patterns. Commun. ACM, 27(3):236–239, March 1984. doi:10.1145/357994.358023.
• [16] B. Zhu, X.-D. Zhou, C.-L. Liu, and M. Nakagawa. A robust model for on-line handwritten Japanese text recognition. International Journal on Document Analysis and Recognition (IJDAR), 13(2):121–131, June 2010. doi:10.1007/s10032-009-0111-y.