Odia-Conjunct character recogntion using evolutionary algorithm


  • Mamata Nayak Institute of Techinal Education and Research, Siksha O Anusandhan University
  • Ajit Kumar Nayak


Odia language, Optical Character Recognition (OCR), Artificial Neural Network (ANN), Genetic Algorithm (GA)


Most efforts have been devoted to the recognition of isolated printed and handwritten Odia basic fonts; however recognition of complex conjunct characters is still an area of active research. This paper presents an effective text recognition scheme for Odia conjunct characters. The shape of conjunct characters is inherently complex and imposes great challenges to the researcher group of Odia Optical Character Recognition. The weightiness of this work lies on design and development of an optimized classification method by combining the back-propagation neural network with genetic algorithm to achieve both the training swiftness and accuracy for recognition. We compare the back-propagation neural network (BPNN) and genetic algorithm optimized in artificial neural network (GAONN) and found that GAONN produces more promising result then BPNN.    Finally we show that the method yields high accuracy rate and depict the most promising research guidelines in this field.

Author Biography

Mamata Nayak, Institute of Techinal Education and Research, Siksha O Anusandhan University

Assistant Professor Computer Science and Information Technology


P. K Charles, V.Harish, M.Swathi, CH. Deepthi, “A Review on the Various Techniques used for Optical Character Recognitionâ€, International Journal of Engineering Research and Applications (IJERA), No. 1, Vol. 2, pp.659-662, .2012

U. Pal, B.B. Chaudhuri, “Indian script character recognition: a surveyâ€, The Journal of Pattern Recognition, No. 37, pp. 1887–1899, 2004.

D. Ghosh, T.a Dube, and A. P. Shivaprasad, “Script Recognition—A Reviewâ€, IEEE Transaction On Pattern Analysis And Machine Intelligence, No. 12, Vol. 2, 2010

A. K. Sadasivana, T.Senthilkumar, “Automatic Character Recognition in Complex Imagesâ€, International Conference on Communication Technology and System Design 2011, Elsevier Procedia Engineering

P. Xiu, H. S. Baird, “Whole-Book Recognitionâ€, IEEE Transaction on Pattern Analysis and Machine Intelligence, No. 12, Vol. 34, 2012

M. Cheriet, M. E. Yacoubi, H. Fujisawa, D. Lopresti, G. Lorette, “Handwritten Recognition Research: twenty years of achievement and beyondâ€, Pattern Recognition 42 (12) (2009) 3131–3135.

G. Nagy, “Twenty Years of Document Image Analysis in PAMI,†IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 38-62, Jan. 2000.

B.Indira, M.Shalini, “Classification and Recognition of Printed Hindi Characters Using Artificial Neural Networksâ€, I.J. Image, Graphics and Signal Processing, No. 6, pp. 15-21, 2012

D. Yadav, S. Sánchez-Cuadrado and J. Morato, “Optical Character Recognition for Hindi Language Using a Neural-network Approachâ€, J Inf Process Syst, Vol.9, No.1, 2013.

S. Bag, G. Harit, P. Bhowmick, “Recognition of Bangla compound characters using structural decompositionâ€, Pattern Recognition, No.47, pp.1187–1201, 2014.

N. Das, R. Sarkar, S. Basu, P. K.Saha, M. Kundu, M. Nasipuri, “Handwritten Bangla character recognition using a softcomputing paradigm embedded in two pass approachâ€, PatternRecognition, No. 48, pp. 2054–2071, 2015.

N. Sankaran, A. Neelappa and C. V. Jawahar, “Devanagari Text Recognition: A Transcription Based Formulationâ€, 12th International Conference on Document Analysis and Recognition, pp.678-682, 2013.

R.J. Kannan, “A comparative study of optical character recognition for Tamil scriptâ€, European Journal of Scientific Research, No. 35 (4) , pp.570–582, 2009.

V. Lakshmi, C. Patvardhan, “A high accuracy OCR system for printed Telugu textâ€, Tencon Conference on Convergent technologies for the Asia-Pacific Region, Vol. 2, pp. 725 – 729.

M.A. Rahiman, M.S. Rajasree, “Printed Malayalam character recognition using back-propagation neural networksâ€, in: International Advance Computing Conference, 2009, pp. 197–201.

S. Naz, K. Hayat, M. I. Razzak, M.W. Anwar, S. A. Madani, S.U. Khan “The optical character recognition of Urdu-like cursive scriptsâ€, Pattern Recognition, No.47, pp.1229–1248, 2014.

T.V. Ashwin, P.S. Sastry, “A font and size-independent OCR system for printed Kannada documents using support vector machines, SÄdhanÄ 27 (1) (2002),35–58.

G.S.Lehal, “A Complete Machine-Printed Gurmukhi OCR Systemâ€, Springer Book Chapter, Guide to OCR for Indic Scripts, Advances in Pattern Recognition

A. A. Desai, “Gujarati handwritten numeral optical character reorganization through neural networkâ€, Pattern Recognition Elsevier, Vol 43, 2010

U. Garain, B.B. Chaudhuri, “Compound character recognition by run-numberbased metric distanceâ€, International Symposium on Electronic Imaging: Science and Technology, Vol. 3305, pp. 90–97, 1998,

N. Das, B. Das, R. Sarkar, S. Basu, M. Kundu, M. Nasipuri, “Handwritten Bangla basic and compound character recognition using MLP and SVM classifierâ€, Journal of Computing, No. 2, Vol.2, pp.109–115, 2010.

B.B.Chaudhuri, U.Pal, M. Mitra, "Automatic Recognition of Printed Oriya Script", pp. 23-34, Sadhana, Vol.27, part 1,2002.

S. Mohanty, H. K. Behera, “A Novel Approach for Bilingual (English - Oriya) Script Identification and Recognition in a Printed Documentâ€, International Journal of Image Processing (IJIP), CSC Journals, Kuala Lumpur, Malaysia, 175 – 191, No. 2, Vol.4.

U. Pal, T. Wakabayashi, and F. Kimura, “A System for Off-line Oriya Handwritten Character Recognition using Curvature Featureâ€, 10th International Conference on Information Technology, IEEE Society, pp.227-230.

S.D.Meher and D. Basa, “An Intelligent Scanner with Handwritten Odia Character Recognition Capabilityâ€, In: proceedings of IEEE Fifth International Sensing Technology(ICST), pp 53-59, 2011

M. Nayak, A. K. Nayak, "Odia Characters Recognition by Training Tesseract OCR Engine", International Journal of Computer Applications (0975 – 8887), pp.25-30, 2013

T.K.Mishra, B.Majhi, S.Panda, “A comparative analysis of image transformations for handwritten Odia numeral recognitionâ€, In : proceedings of IEEE International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 790-793, 2013.

V. Shrivastava and N. Sharma, “Artificial Neural Network Based Optical Character Recognitionâ€, Signal & Image Processing : An International Journal (SIPIJ), Vol.3, No.5, 2012

M. D. Garris, C. L. Wilson, and J. L. Blue, “Neural Network-Based Systems for Handprint OCR Applicationsâ€, IEEE Transaction On Image Processing, Vol. 7, No. 8, 1998

B. Xue, M. Zhang, and W. N. Browne, “Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approachâ€, IEEE Transaction On cybernetics, Vol.34, No.6, pp-1656-1671, 2013.




How to Cite

Nayak, M., & Nayak, A. K. (2015). Odia-Conjunct character recogntion using evolutionary algorithm. Asian Journal of Applied Sciences, 3(4). Retrieved from https://www.ajouronline.com/index.php/AJAS/article/view/3002