Handwritten Hindi Numeral Recognition Using Clustering Techniques

  • Authors

    • Sukriti Paul
    • Nisha P. Shetty
    2018-12-19
    https://doi.org/10.14419/ijet.v7i4.41.24516
  • Indian Script Recognition, Clustering, Joint Clustering, Devanagari numerals, K-means Clustering, Hierarchical Agglomerative Clustering, BIRCH Clustering

  • Abstract

    The problem of automated Hindi numeral recognition is a challenging task owing to the complexity of the script which is characterized by concavities, holes and curvatures. In case of handwritten numerals, the varying writing styles of individuals have to be considered. Our paper focuses at tackling the Hindi numeral recognition problem via various clustering techniques and evaluating them. Subsequently, we work on modifying the framework in Joint Unsupervised Learning (JULE) of Deep Representations and Image Clusters, with different convolutional neural network (CNN) architectures, to obtain normalized mutual information (NMI) results which are better than the state of the art results. Additionally, clustering results obtained on applying different de-noising and contrast adjustment techniques have been presented.

     

     

  • References

    1. [1] List of languages by number of native speakers in India https://en.wikipedia.org/wiki/List_of_languages_by_number_of_native_speakers_in_India.

      [2] Sethi, Ishwar & Chatterjee, B. Machine recognition of constrained hand printed Devanagari. Pattern Recognition. 9. 69-75. 10.1016/0031-3203(77)90017-6, 1977.

      [3] Pal, Umapada & Chaudhuri, Bidyut. Indian script character recognition-A survey. Pattern Recognition 37, 1887-1899. Pattern Recognition. 37. 1887-1899. 10.1016 /j.patcog. 2004.02.003.

      [4] Singh, Raghuraj & S Yadav, C & Verma, Prabhat & Yadav, Vibhash. (0002). Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network. International Journal of Computer Science & Communication. 1. 91-95.

      [5] Sandhya Arora and Debotosh Bhattacharjee and Mita Nasipuri and Latesh G. Malik and Mohantapash Kundu and Dipak Kumar Basu. Performance Comparison of SVM and ANN for Handwritten Devnagari Character Recognition. CoRR, vol. abs/1006.5902, 2010.

      [6] N. Sankaran and C. V. Jawahar. Recognition of printed Devanagari text using BLSTM Neural Network. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, pp.322-325, 2012.

      [7] I. K. Sethi and B. Chatterjee. Machine Recognition of Hand-printed Devnagri Numerals. IETE Journal of Research, volume 22, pp.532-535.

      [8] U. Bhattacharya, S.K. Parui, B. Shaw, K. Bhattacharya. Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition. Tenth International Workshop on Frontiers in Handwriting Recognition, 2006.

      [9] Patil, P. M. and Sontakke, T. R. Rotation, Scale and Translation Invariant Handwritten Devanagari Numeral Character Recognition Using General Fuzzy Neural Network. Pattern Recogntion, pp.2110–211, 2007.

      [10] Bajaj, Reena and Dey, Lipika and Chaudhury, Santanu. Devnagari numeral recognition by combining decision of multiple connectionist classifiers. Sadhana, pp. 59–72, 2002.

      [11] U. Bhattacharya and B. B. Chaudhuri. Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals. EEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 3, pp. 444-457, March 2009.

      [12] H. R. Mamatha, K. S. Murthy, A. V. Veeksha, P. S. Vokuda and M. Lakshmi. Recognition of Handwritten Kannada Numerals Using Directional Features and K-Means. 2011 International Conference on Computational Intelligence and Communication Networks, Gwalior, 2011, pp. 644-647.

      [13] Yoshinobu Hotta, Satoshi Naoi and Misako Suwa Handwritten Numeral Recognition Using Personal Handwriting Characteristics Based On Clustering Method. Applications of Computer Vision, 1996.WACV ’96., Proceedings 3rd IEEE Workshop on, Sarasota, FL, USA, 1996, pp. 284-289.

      [14] A. Gaur and S. Yadav. Handwritten Hindi character recognition using k-means clustering and SVM. 2015 4th International Symposium on Emerging Trends and Technologies in Libraries and Information Services, Noida, 2015, pp. 65-70.

      [15] Jianwei Yang and Devi Parikh and Dhruv Batra. Joint Unsupervised Learning of Deep Representations and Image Clusters. CoRR, vol.abs/1604.03628,2016.

      [16] Pant, Ashok Kumar and Panday, Sanjeeb Prasad and Joshi, Shashidhar Ram. Off-line Nepali handwritten character recognition using Multilayer Perceptron and Radial Basis Function neural networks. Third Asian Himalayas International Conference on Internet, 2012.

      [17] Zhang, T., Ramakrishnan, R. Livny, M. BIRCH: A New Data Clustering Algorithm and Its Applications. Data Mining and Knowledge Discovery (1997) 1: 141. https://doi.org/10.1023/A:1009783824328

  • Downloads

  • How to Cite

    Paul, S., & P. Shetty, N. (2018). Handwritten Hindi Numeral Recognition Using Clustering Techniques. International Journal of Engineering & Technology, 7(4.41), 145-162. https://doi.org/10.14419/ijet.v7i4.41.24516

    Received date: 2018-12-21

    Accepted date: 2018-12-21

    Published date: 2018-12-19