Linking the Researchers, Developing the Innovations Manuscripts submittal opens till 31 October, 2017. Please submit your papers at editor@kwpublisher.com or editorkwpublisher@gmail.com

  • Volume 2016

    Bangla Hand Written Character Recognition Using Support Vector Machine
    (International Journal of Engineering Works)

    Vol. 3, Issue 6, PP. 36-46, June 2016
    Keywords: Handwritten character recognition, Support vector machine, LibSVM,rbf,Bangla, Pattern recognition, Pattern Recognition, Supervised Learning

    Download PDF

    Abstract

    Recognizing handwritten character using computer is still consider a strong area of research. A fundamental problem in the field of Bangla character recognition is the lack of availability of Bangla handwritten character data set. In this thesis our main objective is to generate a larger dataset of Bangla character and as well as improving the recognition rate using Support Vector Machine. Support Vector Machines (SVM) is used for classification in pattern recognition widely. In our proposed method we applied support vector machine for increasing the recognition rate. A scanner is used to capture handwritten data sheet written in white paper by various people. After that several approaches used to generate the final data set for training and testing in SVM. A cropped image is scaled into 16*16 pixel matrix and then combing large number of image a dataset is produced. A binary classification technique of Support Vector Machine is implemented and rbf kernel function is used in SVM. This rbf SVM produces 93.43% overall recognition rate which is satisfactory result among all techniques applied on handwritten Bangla handwritten character recognition system.

    Author

    Riasat Azim, I am born in Bangladesh, in 1989. I have received the B.Sc. degree (with honors) in computer science and engineering from the Khulna University, Khulna in 2012. I have joined Smart Aspects Limited, Dhaka, Bangladesh, in 2012. I have received the M.Sc. degree in Computer science & Technology in Wuhan University of Technology, China in 2016. Now I am working as a researcher on the area of big data and Deep learning. My current research interests include big data, data mining, machine learning and artificial intelligence.

    M. Fazlul Karim, I am born in Khulna, Bangladesh, in 1990. I have received the B.Sc. degree (with honors) in computer science and engineering from the Khulna University, Khulna, Bangladesh, in 2012. I have joined Metatude Asia Limited, Dhaka, Bangladesh, in 2012. I am currently working as a Software engineer in Together Initiatives Limited, Dhaka, Bangladesh. My current research interests include machine learning and artificial intelligence.

    Wahidur Rahman, Hi I am born in Khulna City, at Bangladesh in September 1, 1988. I have completed my graduation in Computer Science and Engineering from one of the renowned public university in Bangladesh named Khulna University.  Currently I worked as a Software Engineer in Bangladesh. I have already passed 3 years in web development sector. I have so much interest in web content research.I want to build web application which is helpful for the root level people and want to research about web application security, database management and so on which is related to web application.   

    Full Text

    Cite

    Riasat Azim, Wahidur Rahman, M. Fazlul Karim, "Bangla Hand Written Character Recognition Using Support Vector Machine" International Journal of Engineering Works, Vol. 3, Issue 6, PP. 36-46, June 2016. 

    References

    [1]     Shailedra Kumar Shrivastava, Sanjay S. Gharde, “Support Vector Machine for Handwritten Devanagari Numeral Recognition”, International Journal of Computer Applications (0975 – 8887) Volume 7– No.11, October 2010.

    [2]     Mohammad Badiul Islam, MollahMasumBillahAzadi, Md. AbdurRahman and M. M. A. Hashem, “Bengali Handwritten Character Recognition using Modified Syntactic Method”, NCCPB-2005 © Independent University, Bangladesh.

    [3]     SandipKaur, “ Recognition of Handwritten Devanagri Script using Feature Based on Zernike Moments and Zoning and Neural Network Classifier”, A M. Tech. Thesis Report, Panjabi University, Patiala, 2004, pp.

    [4]     Gaurav Jain, Jason Ko, “Handwritten Digits Recognition”, Multimedia Systems, Project Report, University of Toronto, November 21, 2008, pp. 1-3.

    [5]     Anita Pal and Dayashankar Singh; “Handwritten English Character Recognition Using Neural Network”, In International Journal of Computer Science & Communication,Vol. 1, No. 2, July-December 2010, pp. 141-144.

    [6]     Al MamunurRasid and Muhammad Masroor Ali, “On Line Recognition of Handwritten Characters Using 1-Dim, 1-Dim DP approach”, Proc. ICCIT’1998 , 18-20 December, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh.pp.86-90.

    [7]     Mohammed Ali AsgerMoshad and Muhammad Masroor Ali, “Recognition of Handwritten Bangla Digits by Intelligent Regional Search Method”, Proc. ICCIT’2001, 28-29 December, Dhaka University, Dhaka, Bangladesh.pp.297-302.

    [8]     A.O.M. Asaduzzaman, Md. Khademul Islam Molla and M. Ganjer Ali, “Printed Bangla Text Recognition Using Artificial Neural Network with Heuristic Method”, Proc. ICCIT’2002 , 27-28 December, East West University, Dhaka, Bangladesh.

    [9]     Anita Pal &Dayashankar Singh; “Handwritten English Character Recognition Using Neural Network”, In International Journal of Computer Science & Communication,Vol. 1, No. 2, July-December 2010, pp. 141-144.

    [10]  Md. Badrudoza, “Recognition of Bengali Handwritten Letters Using Self-Organizing Maps(SOM)”, Proc. ICCIT’2003, Jahangirnagar University, Dhaka, Bangladesh.pp.355-359.

    [11]  Md. ShafiulAzamHowlader, Md. Mostafa Jamal and GahangirHossain, “New Approch of Bangla Handwriting Recognition”, Proc. ICCIT’2003, Jahangirnagar University, Dhaka, Bangladesh.pp.370-373.

    [12]  Abdul Rahim Ahmad, Christian Viard-Gaudin, Marzuki Khalid, RubiyahYusof; “Online Handwriting Recognition using Support Vector Machine”, In Second International Conference on ArtificialIntelligence in Engineering & Technology, August 3-5 2004, Kota Kinabalu, Sabah, Malaysia.

    [13]  Verma B.K, “Handwritten Hindi Character Recognition Using Multilayer Perceptron and Radial Basis Function Neural Network”, IEEE International Conference on NeuralNetwork, 4, pp. 2111-2115, 1995.

    [14]  Ahmed Shah Mashiyat, Ahmed Shah Mehadi and KamrulHasanTalukder, “ Bangla off-line Handwritten Character Recognition Using Superimposed Matrices”.

    [15]  Homayoon S.M. Beigi, "An Overview of Handwriting Recognition," Proceedings of the 1st Annual Conference on Technological Advancements in Developing Countries, Columbia University, New York, July 24-25, 1993, pp. 30-46.

    [16]  [Nibaran Das, Brindaban Das, Ram Sarkar, SubhadipBasu, MahantapasKundu, MitaNasipuri, “Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier”, Journal of computing, volume 2, issue 2, February 2010, ISSN 2151-9617.

    [17]  [Mohammad Badiul Islam, MollahMasumBillahAzadi, Md. AbdurRahman and M. M. A. Hashem, “Bengali Handwritten Character Recognition using Modified Syntactic Method”, NCCPB-2005 © Independent University, Bangladesh.

    [18]  http://www.mathworks.com/help/toolbox/fuzzy/fp72.html#FP108

    [19]  http://www.kev.pulo.com.au/ai/fuzzyml_report/node3.html

    [20]  http://en.wikipedia.org/wiki/Support_vector_machine

    [21]  DENG Naiyang,TIANYingjie. Support Vector Machines Theory, Algorithms and Expand [M]. Science Press,2009