The week's pick
Random Articles
Reseach Article
Measuring Performance of Generative Adversarial Networks on Devanagari Script
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 176 - Number 33 |
| Year of Publication: 2020 |
| Authors: Amogh G. Warkhandkar, Baasit Sharief, Omkar B. Bhambure |
10.5120/ijca2020920393
|
Amogh G. Warkhandkar, Baasit Sharief, Omkar B. Bhambure . Measuring Performance of Generative Adversarial Networks on Devanagari Script. International Journal of Computer Applications. 176, 33 ( Jun 2020), 5-9. DOI=10.5120/ijca2020920393
Abstract
The working of neural networks following the adversarial philosophy to create a generative model is a fascinating field. Multiple papers have already explored the architectural aspect and proposed systems with potentially good results however, very few papers are available which implement it on a real-world example. Traditionally, people use the famous MNIST dataset as a Hello, World! example for implementing Generative Adversarial Networks (GAN). Instead of going the standard route of using handwritten digits, this paper uses the Devanagari script which has a more complex structure. As there is no conventional way of judging how well the generative models perform, three additional classifiers were built to judge the output of the GAN model. The following paper is an explanation of what this implementation has achieved.
References
- S. Acharya, A. K. Pant, and P. K. Gyawali. Deep learning based large scale handwritten devanagari character recognition. In 2015 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), pages 1–6, 2015.
- Abien Fred Agarap. Deep learning using rectified linear units (relu). CoRR, abs/1803.08375, 2018.
- Estevao Gedraite and M. Hadad. Investigation on the effect of a gaussian blur in image filtering and segmentation. pages 393–396, 01 2011.
- Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks, 2014.
- Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization, 2014.
- Jayanth Koushik. Understanding convolutional neural networks, 2016.
- Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, and Shixia Liu. Towards better analysis of deep convolutional neural networks, 2016.
- Chigozie Nwankpa, Winifred Ijomah, Anthony Gachagan, and Stephen Marshall. Activation functions: Comparison of trends in practice and research for deep learning. CoRR, abs/1811.03378, 2018.
- A.M Raid, Wael Khedr, Mohamed El-dosuky, and Mona Aoud. Image restoration based on morphological operations. International Journal of Computer Science, Engineering and Information Technology, 4:9–21, 07 2014.
- Sebastian Ruder. An overview of gradient descent optimization algorithms, 2016.
- Ravi Srisha and Am Khan. Morphological operations for image processing : Understanding and its applications. 12 2013.
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56):1929–1958, 2014.
- Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. Empirical evaluation of rectified activations in convolutional network. CoRR, abs/1505.00853, 2015.
- Jun Zhang and Jinglu Hu. Image segmentation based on 2d otsu method with histogram analysis. pages 105–108, 01 2008.
Index Terms
Keywords