Convolution Based Technique for Indic Script Identification from Handwritten Document Images

Full Text (PDF, 499KB), PP.49-57

Views: 0 Downloads: 0


Sk Md Obaidullah 1,* Nibaran Das 2 Kaushik Roy 3

1. Dept. of Computer Science & Engineering, Aliah University, Kolkata - 700091, WB, India

2. Dept. of Computer Science & Engineering, Jadavpur University, Kolkata - 700032, WB, India

3. Dept. of Computer Science, West Bengal State University, Kolkata - 700126, WB, India

* Corresponding author.


Received: 22 Nov. 2014 / Revised: 3 Feb. 2015 / Accepted: 4 Mar. 2015 / Published: 8 Apr. 2015

Index Terms

Handwritten Script Identification, Convolution, 2D Gabor Filter, Morphological Filters, Statistical Performance Analysis


Determination of script type of document image is a complex real life problem for a multi-script country like India, where 23 official languages (including English) are present and 13 different scripts are used to write them. Including English and Roman those count become 23 and 13 respectively. The problem becomes more challenging when handwritten documents are considered. In this paper an approach for identifying the script type of handwritten document images written by any one of the Bangla, Devnagari, Roman and Urdu script is proposed. Two convolution based techniques, namely Gabor filter and Morphological reconstruction are combined and a feature vector of 20 dimensions is constructed. Due to unavailability of a standard data set, a corpus of 157 document images with an almost equal ratio of four types of script is prepared. During classification the dataset is divided into 2:1 ratio. An average identification accuracy rate of 94.4% is obtained on the test set. The average Bi-script and Tri-script identification accuracy rate was found to be 98.2% and 97.5% respectively. Statistical performance analysis is done using different well known classifiers.

Cite This Paper

Sk Md Obaidullah , Nibaran Das, Kaushik Roy,"Convolution Based Technique for Indic Script Identification from Handwritten Document Images", IJIGSP, vol.7, no.5, pp.49-57, 2015. DOI: 10.5815/ijigsp.2015.05.06


[1], accessed 1st October 2014.

[2]Mantas J., "An overview of Character Recognition Methodologies", Pattern Recognition, vol. 19, pp. 425-430, 1986.

[3]S. M. Obaidullah, S. K. Das, K. Roy, "A System for Handwritten Script Identification From Indian Document", in Journal of Pattern Recognition Research, vol. 8, no. 1, 2013, pp. 1-12.

[4]D. Ghosh, T. Dube, A. P. Shivaprasad, "Script Recognition- A Review", IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 2142-2161, 2010.

[5]L. Zhou, Y. Lu , C. L. Tan, "Bangla/English Script Identification Based on Analysis of Connected Component Profiles", Lecture Notes in Computer Science, Volume 3872/2006, 24354, 2006, DOI: 10.1007/11669487_22.

[6]V. Singhal, N. Navin, D. Ghosh, "Script-based Classification of Hand-written Text Document in a Multilingual Environment", Research Issues in Data Engineering, pp.47, 2003.

[7]J. Hochberg, P. Kelly, T. Thomas, L. Kerns, "Automatic Script Identification from Document Images Using Cluster-based Templates", IEEE Trans. on Pattern Analysis & Machine Intelligence, vol. 19, no. 2, pp. 176-181, 1997.

[8]K. Roy, S. K. Das, S. M. Obaidullah, "Script Identification from Handwritten Document", In Proceedings of The third National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), Hubli, Karnataka, pp. 66-69, 2011.

[9]S. B. Moussa, A. Zahour, A. Benabdelhafid, A.M. Alimi, "Fractal-Based System for Arabic/Latin, Printed/Handwritten Script Identification", In Proceedings of International Conference on Pattern Recognition, pp. 1-4, 2008.

[10]M. Hangarge, B. V. Dhandra, "Offline handwritten script identification in document images", International Journal of Computer Application, 4(6), pp. 6-10, 2010.

[11]M. Hangarge, K. C. Santosh, R. Pardeshi, "Directional Discrete Cosine Transform for Handwritten Script Identification", In Proceedings of 12th International Conference on Document Analysis and Recognition, pp. 344-348, 2013.

[12]K. Roy, U. Pal, A. Banerjee, "A system for word-wise handwritten script identification for Indian postal automation", IEEE INDICON, pp. 266-271, 2004.

[13]I. Fogel, D. Sagi, "Gabor filters as texture discriminator", Biological Cybernetics, 61 (2), 1989.

[14]D. Gabor, "Theory of Communication", Journal of the Institute of Electrical Engineers, 93, pp. 429-457, 1946.

[15]J. Daugman, "Two-dimensional analysis of cortical receptive field profiles", Vision Research, 20, pp. 846–856, 1980.

[16]J. Daugman, "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters", Journal of the Optical Society of America-A, 2(7), pp. 1160–1169, 1985.

[17]M. Haghighat, S. Zonouz, M. A. Mottaleb, "Identification Using Encrypted Biometrics", Computer Analysis of Images and Patterns, LNCS 8048, pp. 440-448, 2013.

[18]V. Shiv Naga Prasad, Justin Domke, "Gabor filter visualization", Technical Report, University of Maryland, 2005.

[19]A. Kaehler, G. R. Bradski, "Learning OpenCV", O'reilly Media, 2008.

[20]M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann and I. H. Witten, "The WEKA Data Mining Software: An Update", SIGKDD Explorations, Vol. 11, pp. 10-18, 2009.

[21]N Friedman, D Geiger, M Goldszmidt, "Bayesian network classifiers", Machine learning 29 (2-3), 131-163, 1997.

[22]R. E. Fan, K. W. Chang, C. J. Hsieh, X. R. Wang, C. J.Lin, "LIBLINEAR: A library for large linear classification", Journal of Machine Learning Research, vol. 9, pp. 1871-1874, 2008.

[23]J. Hühn, E. Hüllermeier, P. U. Marburg, "FURIA: An Algorithm for Unordered Fuzzy Rule Induction", Data Mining and Knowledge Discovery, Vol. 19, pp. 293-319, 2009.

[24]N. Landwehr, M. Hall, E. Frank, "Logistic Model Trees", Machine Learning, Vol. 95, pp. 161-205, 2005.

[25]M. Sumner, E. Frank, M. Hall, "Speeding up Logistic Model Tree Induction", 9th European Conference on Principles and Practice of Knowledge Discovery in Databases, pp. 675-683, 2005.

[26]M. D. Buhmann, "Radial Basis Functions: Theory and Implementations", 12th Cambridge Monographs on Applied and Computational Mathematics, Cambridge University Press, Cambridge, 2003.

[27]S. V. Chakravarthy, J. Ghosh, "Scale-Based Clustering using Radial Basis Function Network", IEEE Trans. on Neural Networks, vol. 7, pp. 1250-1261, 1996.

[28]A. J. Howell, H. Buxton, "RBF Network Methods for Face Detection and Attentional Frames", Neural Processing Letters, Vol. 15, pp.197-211, 2002.

[29]S. M. Obaidullah, N. Das, K. Roy, "Gabor Filter Based Technique for Offline Script Identification from Handwritten Document Images", at Proceedings of International Conference on Devices, Circuits and Communications, Mesra, Ranchi, 2014.

[30]A. B. Khalifa, L. Rzouga, N. E. B. Amara, "Wavelet, Gabor Filters and Co-occurrence Matrix for Palmprint Verification", IJIGSP, vol.5, no.8, pp.1-8, 2013.DOI: 10.5815/ijigsp.2013.08.01.

[31]S. M. Obaidullah, A. Mondal, N. Das, and K. Roy, "Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers," Applied Computational Intelligence and Soft Computing, vol. 2014, Article ID 896128, 12 pages, 2014. doi:10.1155/2014/896128.