Abstract
Kannada is a Dravidian Language spoken by over 80 million people all over the world; Kannada script’s character recognition system has wide range applications in education, healthcare, finance and many more sectors. Building it involves many phases and makes it more challenging because of the nature of script including horizontal skews and curves. Although challenging, several attempts have been made in the past to develop methods to either avoid the intermediate steps or reduce the complexity involved, thereby effecting the time and cost factors. The objective of this work is to understand Why, achieving effective recognition rates using recent technology is still challenging? And Is it possible to overcome the existing challenges and drawbacks by retraining different deep neural networks, using different Transfer Learning techniques? Four different Transfer Learning techniques, two different pre-trained deep neural networks and different dataset were employed, resulting in an exceptional recognition rate of 92.5%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kunte, S., Samuel, R.D.S.: An OCR system for printed Kannada text using two-stage Multi-network classification approach employing Wavelet features. In: International Conference on Computational Intelligence and Multimedia Applications (ICCIMA), vol. 2, pp. 349–353. IEEE (2007)
Mamatha, H.R., Sucharitha, S., Srikanta Murthy, K.: Multi-font and multi-size kannada character recognition based on the curvelets and standard deviation. Int. J. Comput. Appl. 35, 1–8 (2011)
Deepu, K., Divya, G.: Review on optical character recognition for off-line devanagari handwritten characters and challenges. Int. J. Sci. Res. Comput. Sci. Eng. Inform. Technol. (IJSRCSEIT), 3, 1364–1367 (2018)
Prakash, K.C., Srikar, Y.M., Trishal, G., et al.: Optical character recognition for telugu: database, algorithm and application. In: 25th IEEE International Conference on Image Processing (ICIP), pp. 3963–3967. IEEE (2018)
Balan, P.S., Sunny, L.E.: Survey on feature extraction techniques in image processing. In: International Journal for Research in Applied Science & Engineering Technology (IJRASET), pp. 217–222 (2018)
Esmaeili, H., Phoka, T.: Transfer learning for leaf classification with convolutional neural networks. In: 15th International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 1–6. IEEE (2018)
Xia, X., Xu, C., Nan, B.: Inception-v3 for flower classification. In: 2nd International Conference on Image, Vision and Computing (ICIVC), pp. 783–787. IEEE (2017)
Chen-McCaig, Z., Hosennezhad, R., Bab-Hadiashar, A.: Convolutional neural network for texture recognition using transfer learning. In: International Conference on Control, Automation and Information Sciences (ICCAIS), pp. 187–192. IEEE (2017)
Alothman, B.: Similarity based instance transfer learning for botnet detection. Int. J. Intell. Comput. Res. (IJICR) 9(2018), 880–889 (2018)
Sun, W., Xu, Q.: A transfer learning for document categorization based on clustering. In: International Conference on Computer Science and Electronics Engineering, pp. 528–531. IEEE (2012)
Masood, S., Luthra, T., Sundriyal, H., Ahmed, M.: Identification of diabetic retinopathy in eye images using transfer learning. In: International Conference on Computing, Communication and Automation (ICCCA), pp. 1183–1187. IEEE (2017)
Tushar, A.K., Ashiquzzaman, A.K.M., Afrin, A., Islam, M.R.: A novel transfer learning approach upon hindi, arabic, and bangla numerals using convolutional neural networks. In: Computational Vision and Bio Inspired Computing, pp. 972–981. Springer, Cham (2018)
Hnoohom, N., Sumeth, Y.: Classification of dhamma esan characters by transfer learning of a deep neural network. In: 15th International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 1–5. IEEE (2018)
Cireşan, D.C., Meier, U., Schmidhuber, J.: Transfer learning for Latin and Chinese characters with deep neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2012)
Tensorflow Hub, How to retrain image classifier for new categories. https://www.tensorflow.org/hub/tutorials/image_retraining. Accessed 1 Jan 2020
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Reddy, P.R., Mamatha, H.R. (2021). Isolated Kannada Character Recognition Using Transfer Learning. In: Abraham, A., Piuri, V., Gandhi, N., Siarry, P., Kaklauskas, A., Madureira, A. (eds) Intelligent Systems Design and Applications. ISDA 2020. Advances in Intelligent Systems and Computing, vol 1351. Springer, Cham. https://doi.org/10.1007/978-3-030-71187-0_125
Download citation
DOI: https://doi.org/10.1007/978-3-030-71187-0_125
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71186-3
Online ISBN: 978-3-030-71187-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)