Pattern Classification of Handwritten Kannada Digits Using Customized CNN

  • Gopal D. Upadhye
  • U. V. Kulkarni
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1118)


In the area of pattern classification, handwritten digit classification is a challenging problem. Handwritten digits seem different due to writing styles and sizes. There is a wide scope of research on regional languages like Kannada. As Kannada digits symmetric as well as curvy, they are difficult to recognize accurately. Customized convolutional neural network architecture is proposed in this paper for Kannada digits’ classification which are handwritten. This provides automatic learning feature facility of handwritten digit and predicts its class. Layered model of customized CNN architecture is also given which shows flow of working of the proposed method. Large-sized dataset is unavailable for handwritten Kannada digits, so prepared dataset of 20,200 samples. Out of 20,200 total samples, 16,000 samples used for training and the remaining 4200 samples used for testing. The proposed method gives average 93.13% testing accuracy and 91.58% validation accuracy.


Pattern classification Convolutional neural network Cross validation 


  1. 1.
    Kavya, T.N., Pratibha, V., Priyadarshini, B.A., Vijaya, B.M., Vijayalakshmi, G.V.: Kannada characters and numerical recognition system using hybrid zone-wise feature extraction and fused classifier. Int. J. Eng. Res. Technol. 5(5) (2016)Google Scholar
  2. 2.
    Gurudath, K.P., Ravi, D.J.: Isolated bigits recognition in Kannada language. Int. J. Comput. Appl. (0975–8887) 140, 1–10 (2016)Google Scholar
  3. 3.
    Karthik, S., Murthy, K.S.: Handwritten Kannada Numerals Recognition Using Histogram of Oriented Gradient Descriptors and Support Vector Machines. Springer International Publishing Switzerland, vol. 2, pp. 51–57 (2015)Google Scholar
  4. 4.
    Killedar, S., Deshapande, S.: Kannada handwritten numerals recognition and translation using template matching. Int. J. Recent Technol. Mech. Electr. Eng. 2, 77–80 (2015)Google Scholar
  5. 5.
    Shettar, S., Basavaprasad, B., Bhagya, H. K.: Recognition of printed Kannada numerals by nearest neighbor method. In: Proceedings of the International Conference on Computational Systems for Health Sustainability, pp. 99–103 (2015)Google Scholar
  6. 6.
    Hallur, V.C., Hegadi, R.S.: Offline Kannada handwritten numeral recognition: holistic approach. In: Proceeding of Second International Conference on Emerging Research in Computing, Information, Communication and Applications, vol. 3, pp. 632–637 (2014)Google Scholar
  7. 7.
    Hallur, V.C., Hegadi, R.S.: Kannada handwritten digits recognition: neural network approach. Int. J. Sci. Res. (2013)Google Scholar
  8. 8.
    Mamatha, H.R., Srirangaprasad, S., Srikantamurthy, K.: Data fusion based framework for the recognition of isolated handwritten Kannada numerals. Int. J. Adv. Comput. Sci. Appl. 4, 174–182 (2013)Google Scholar
  9. 9.
    Dhandra, B.V., Mukarambi, G., Hangarge, M.: Zone based features for handwritten and printed mixed Kannada digits recognition. In: Proceeding of International Conference on VLSI, Communication Instrumentation, pp. 5–9 (2011)Google Scholar
  10. 10.
    Mukarambi, G., Dhandrab, V., Hangarge, M.: Recognition system for handwritten and printed Kannada numerals and vowels. Int. J. Mach. Intell. 3(4), 259–262 (2011)Google Scholar
  11. 11.
    Rajput, G.G., Horakeri, R., Chandrakant, S.: Printed and handwritten Kannada numeral recognition using crack codes and fourier descriptors plate. IJCA Spec. Issue Recent Trends Image Process. Pattern Recognit. 53–58 (2010)Google Scholar
  12. 12.
    Acharya, D., Subba Reddy, N.V., Makkithaya, K.: Multilevel classifiers in recognition of handwritten Kannada numerals. Int. J. Comput. Inf. Eng.2, 1908–1913 (2008)Google Scholar
  13. 13.
    Ganesh, A., Jadhav, A.R., Cibi Pragadeesh, K.A.: Deep learning approach for recognition of handwritten Kannada numerals. In: Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition, pp. 294–303 (2016)Google Scholar
  14. 14.
    Mane, D.T., Kulkarni, U.V.: Visualizing and understanding customized convolutional neural network for recognition of handwritten marathi numerals. Procedia Comput. Sci. 132, 1123–1137. 10.1016/j.procs.2018.05.027, 2018Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Gopal D. Upadhye
    • 1
  • U. V. Kulkarni
    • 1
  1. 1.Department of Computer Science and EngineeringShri Guru Gobind Singhji Institute of Engineering and TechnologyNandedIndia

Personalised recommendations