<

This Article Statistics
Viewed : 35 Downloaded : 31


 

Applying Capsule Network on Kannada-MNIST Handwritten Digit Dataset

Emine UÇAR, Murat UÇAR

Abstract

Convolutional neural networks (CNNs) are applied in many different fields such as image processing, natural language processing (NLP) and biomedical. In recent years, a new CNN architecture known as Capsule Network (Capsule-Net) has been developed to reduce some disadvantages of convolutional neural networks and improve the performance. Architecture of capsule networks is inspired by the human brain’s inverse graphics and hierarchical mapping concepts. In this study, the architecture and working of the capsule networks were examined and comparative analysis of Capsule Network and CNN on the new handwritten digits dataset called Kannada-MNIST were defined. Our experimental results show that the accuracy of capsule network model is better than the accuracy of CNNs.

Keywords

Capsule networks, deep learning, image processing, Kannada-MNIST.

Volume 4, No 3, SUPPLEMENT I of SYMPOSIUM ARTICLES, pp 84-90, 2019



Download full text   |   How to Cite   |   Download XML Files

References
  • Engelin M., (2018). CapsNet Comprehension of Objects in Different Rotational Views, A comparative study of capsule and convolutional networks, Degree Project in Computer Science and Engineering, Stockholm, Sweden.
  • Gulli, A. and Pal. S. (2017). “Deep Learning with Keras”. Packt Publishing Ltd, Birmingham - Mumbai, pp. 71-105, 2017.
  • Haque, S., Rabby, A.S., Islam, M.S., & Hossain, S.A. (2018). ShonkhaNet: A Dynamic Routing for Bangla Handwritten Digits Recognition Using Capsule Network. 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), 1-12.
  • Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. NIPS.
  • LeCun Y, Bengio Y, Hinton G. (2015). Deep learning. Nature, 521(7553):436–44.
  • Mandal, B., Dubey, S., Ghosh, S., Sarkhel, R., & Das, N. (2018). Handwritten Indic Character Recognition using Capsule Networks. 2018 IEEE Applied Signal Processing Conference (ASPCON), 304-308.
  • Mehta, A. and Parmar, V. D. (2019). A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN, International Journal of Computer Sciences and Engineering, 7(4), 105-108.
  • Mukhometzianov R. and Carrillo, J. (2018). “CapsNet comparative performance evaluation for image classification,” arXiv:1805.11195v1.
  • Nair, P.Q., Doshi, R., & Keselj, S. (2018). Pushing the Limits of Capsule Networks. Technical note.
  • Prabhu, V.U. (2019). Kannada-MNIST: A new handwritten digits dataset for the Kannada language. ArXiv, abs/1908.01242.
  • Sabour, S., Frosst, N., & Hinton, G. E. (2017). Dynamic routing between capsules. In Advances in neural information processing systems (pp. 3856-3866).
  • Srinivas S, Sarvadevabhatla RK, Mopuri KR, Prabhu N, Kruthiventi SS, Babu RV. (2017). An Introduction to Deep Convolutional Neural Nets for Computer Vision. In: Deep Learning for Medical Image Analysis, 25–52.