# Enhanced CNN Classification Capability for Small Rice Disease Datasets Using Progressive WGAN-GP: Algorithms and Applications

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Dataset

## 3. Methodology

#### 3.1. GAN

#### 3.2. WGAN

#### 3.3. WGAN-GP

#### 3.4. Progressive Training

#### 3.5. Residual Block

#### 3.6. Progressive WGAN-GP

#### 3.6.1. Residual Block

#### 3.6.2. Upsampling

#### 3.6.3. Batch Normalization Layer

#### 3.6.4. LeakyReLU

#### 3.7. Traditional Image Data Augmentation

## 4. Experiment

#### 4.1. Experimental Setup

#### 4.2. Evaluation Metrics

#### 4.3. Training Process

#### 4.4. Performance of the Data Augmentation Model

## 5. Results and Discussion

#### 5.1. Generating Image Quality

#### 5.2. Performance of the Data Enhancement Model

## 6. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## References

- Huang, S.; Wang, P.; Yamaji, N.; Ma, J.F. Plant Nutrition for Human Nutrition: Hints from Rice Research and Future Perspectives. Mol. Plant
**2020**, 13, 825–835. [Google Scholar] [CrossRef] - Gayathri Devi, T.; Neelamegam, P. Image processing based rice plant leaves diseases in Thanjavur, Tamilnadu. Clust. Comput.
**2019**, 22, 13415–13428. [Google Scholar] [CrossRef] - Chawathe, S.S. Rice disease detection by image analysis. In Proceedings of the 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 6–8 January 2020; pp. 0524–0530. [Google Scholar]
- Sethy, P.K.; Barpanda, N.K.; Rath, A.K.; Behera, S.K. Deep feature based rice leaf disease identification using support vector machine. Comput. Electron. Agric.
**2020**, 175, 105527. [Google Scholar] [CrossRef] - Sulistyaningrum, D.; Rasyida, A.; Setiyono, B. Rice disease classification based on leaf image using multilevel Support Vector Machine (SVM). J. Phys. Conf. Ser.
**2020**, 1490, 012053. [Google Scholar] [CrossRef] - Adiyarta, K.; Zonyfar, C.; Fatimah, T. Identification of rice leaf disease based on rice leaf image features using the k-Nearest Neighbour (k-NN) technique. In Proceedings of the International Conference on IT, Communication and Technology for Better Life, ICT4BL, Bangkok, Thailand, 17–18 July 2019; pp. 160–165. [Google Scholar]
- Mekha, P.; Teeyasuksaet, N. Image Classification of Rice Leaf Diseases Using Random Forest Algorithm. In Proceedings of the 2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering, Cha-am, Thailand, 3–6 March 2021; pp. 165–169. [Google Scholar]
- Rasjava, A.R.; Sugiyarto, A.W.; Kurniasari, Y.; Ramadhan, S.Y. Detection of Rice Plants Diseases Using Convolutional Neural Network (CNN). In Proceedings of the International Conference on Science and Engineering, Male, Maldives, 14–16 January 2020; Volume 3, pp. 393–396. [Google Scholar]
- Zhang, X.; Qiao, Y.; Meng, F.; Fan, C.; Zhang, M. Identification of maize leaf diseases using improved deep convolutional neural networks. IEEE Access
**2018**, 6, 30370–30377. [Google Scholar] [CrossRef] - Swasono, D.I.; Tjandrasa, H.; Fathicah, C. Classification of tobacco leaf pests using VGG16 transfer learning. In Proceedings of the 2019 12th International Conference on Information & Communication Technology and System (ICTS), Surabaya, Indonesia, 18 July 2019; pp. 176–181. [Google Scholar]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature
**2015**, 521, 436–444. [Google Scholar] [CrossRef] [PubMed] - Kc, K.; Yin, Z.; Wu, M.; Wu, Z. Depthwise Separable Convolution Architectures for Plant Disease Classification. Comput. Electron. Agric.
**2019**, 165, 104948. [Google Scholar] [CrossRef] - Hossain, S.M.M.; Deb, K.; Dhar, P.K.; Koshiba, T. Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models. Symmetry
**2021**, 13, 511. [Google Scholar] [CrossRef] - Yakkundimath, R.; Saunshi, G.; Anami, B.; Palaiah, S. Classification of Rice Diseases Using Convolutional Neural Network Models. J. Inst. Eng. (India) Ser. B
**2022**, 103, 1047–1059. [Google Scholar] [CrossRef] - Liang, W.j.; Zhang, H.; Zhang, G.f.; Cao, H.x. Rice blast disease recognition using a deep convolutional neural network. Sci. Rep.
**2019**, 9, 1–10. [Google Scholar] [CrossRef] [Green Version] - Belkin, M.; Ma, S.; Mandal, S. To understand deep learning we need to understand kernel learning. In Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden, 10–15 July 2018; pp. 541–549. [Google Scholar]
- D’souza, R.N.; Huang, P.Y.; Yeh, F.C. Structural analysis and optimization of convolutional neural networks with a small sample size. Sci. Rep.
**2020**, 10, 834. [Google Scholar] [CrossRef] [Green Version] - Johnson, J.M.; Khoshgoftaar, T.M. Survey on deep learning with class imbalance. J. Big Data
**2019**, 6, 1–54. [Google Scholar] [CrossRef] [Green Version] - Zhang, R. Making Convolutional Networks Shift-Invariant Again. arXiv
**2019**. [Google Scholar] [CrossRef] - Goodfellow, I.J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial nets. Adv. Neural Inf. Process. Syst.
**2014**, 27, 1–9. [Google Scholar] - Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein Generative Adversarial Networks. In Proceedings of the International Conference on Machine Learning, Sydney, Australia, 6–11 August 2017. [Google Scholar]
- Gulrajani, I.; Ahmed, F.; Arjovsky, M.; Dumoulin, V.; Courville, A.C. Improved Training of Wasserstein GANs. In Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017; Volume 30. [Google Scholar]
- Abbas, A.; Jain, S.; Gour, M.; Vankudothu, S. Tomato plant disease detection using transfer learning with C-GAN synthetic images. Comput. Electron. Agric.
**2021**, 187, 106279. [Google Scholar] [CrossRef] - Bing, L.; Yong, X.; Daqiao, Z. Infrared Image Generation Algorithm Based on Conditional Generation Adversarial Networks. Acta Photonica Sin.
**2021**, 50, 1110004. [Google Scholar] - Nazki, H.; Lee, J.; Yoon, S.; Park, D.S. Image-to-image translation with GAN for synthetic data augmentation in plant disease datasets. Smart Media J.
**2019**, 8, 46–57. [Google Scholar] [CrossRef] - Yang, Q.; Lu, J.G.; Tang, X.H.; Gu, X.; Sheng, X.J.; Yang, R.H. Bearing small sample fault diagnosis based on InfoGAN and CNN. J. Ordnance Equip. Eng.
**2021**, 42, 235–240. [Google Scholar] - Liu, Y.; Zhou, Y.; Liu, X.; Dong, F.; Wang, C.; Wang, Z. Wasserstein GAN-based small-sample augmentation for new-generation artificial intelligence: A case study of cancer-staging data in biology. Engineering
**2019**, 5, 156–163. [Google Scholar] [CrossRef] - Sandfort, V.; Yan, K.; Pickhardt, P.J.; Summers, R.M. Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks. Sci. Rep.
**2019**, 9, 16884. [Google Scholar] [CrossRef] [Green Version] - Karras, T.; Aila, T.; Laine, S.; Lehtinen, J. Progressive growing of gans for improved quality, stability, and variation. arXiv
**2017**, arXiv:1710.10196. [Google Scholar] - Zhang, Z.; Gao, Q.; Liu, L.; He, Y. A High-Quality Rice Leaf Disease Image Data Augmentation Method Based on a Dual GAN. IEEE Access
**2023**, 11, 21176–21191. [Google Scholar] [CrossRef] - Lamba, S.; Baliyan, A.; Kukreja, V. A Novel GCL Hybrid Classification Model for Paddy Diseases. Int. J. Inf. Technol.
**2023**, 15, 1127–1136. [Google Scholar] [CrossRef] [PubMed] - Lamba, S.; Baliyan, A.; Kukreja, V. GAN Based Image Augmentation for Increased CNN Performance in Paddy Leaf Disease Classification. In Proceedings of the 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), Greater Noida, India, 28–29 April 2022; pp. 2054–2059. [Google Scholar] [CrossRef]
- Shayan, R. Rice Leafs. 2019. Available online: https://www.kaggle.com/shayanriyaz/riceleafs (accessed on 24 February 2023).
- Marsh. Rice Leaf Diseases Dataset. 2019. Available online: https://www.kaggle.com/vbookshelf/rice-leaf-diseases (accessed on 24 February 2023).
- Rajeshbhattacharjee. rice_diseases_using_cnn_and_svm. 2019. Available online: https://www.kaggle.com/rajeshbhattacharjee/rice-diseases-using-cnn-and-svm (accessed on 24 February 2023).
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Ding, W.; Taylor, G. Automatic moth detection from trap images for pest management. Comput. Electron. Agric.
**2016**, 123, 17–28. [Google Scholar] [CrossRef] [Green Version] - Dumoulin, V.; Visin, F. A guide to convolution arithmetic for deep learning. arXiv
**2016**, arXiv:1603.07285. [Google Scholar] - Ioffe, S.; Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the International Conference on Machine Learning, Lille, France, 6–11 July 2015; pp. 448–456. [Google Scholar]
- Ioffe, S.; Normalization, C.S.B. Accelerating deep network training by reducing internal covariate shift. arXiv
**2014**, arXiv:1502.03167. [Google Scholar] - Wang, S.H.; Muhammad, K.; Hong, J.; Sangaiah, A.K.; Zhang, Y.D. Alcoholism Identification via Convolutional Neural Network Based on Parametric ReLU, Dropout, and Batch Normalization. Neural Comput. Appl.
**2020**, 32, 665–680. [Google Scholar] [CrossRef] - Azulay, A.; Weiss, Y. Why Do Deep Convolutional Networks Generalize so Poorly to Small Image Transformations? arXiv
**2019**, arXiv:1805.12177. [Google Scholar] - Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Hochreiter, S. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017; Volume 30. [Google Scholar]
- Jiang, F.; Lu, Y.; Chen, Y.; Cai, D.; Li, G. Image recognition of four rice leaf diseases based on deep learning and support vector machine. Comput. Electron. Agric.
**2020**, 179, 105824. [Google Scholar] [CrossRef] - Jadhav, S.B.; Udupi, V.R.; Patil, S.B. Identification of plant diseases using convolutional neural networks. Int. J. Inf. Technol.
**2021**, 13, 2461–2470. [Google Scholar] [CrossRef] - Sethy, P.K.; Barpanda, N.K.; Rath, A.K.; Behera, S.K. Nitrogen deficiency prediction of rice crop based on convolutional neural network. J. Ambient. Intell. Humaniz. Comput.
**2020**, 11, 5703–5711. [Google Scholar] [CrossRef] - Hossain, S.M.M.; Tanjil, M.M.M.; Ali, M.A.B.; Islam, M.Z.; Islam, M.S.; Mobassirin, S.; Sarker, I.H.; Islam, S.M.R. Rice Leaf Diseases Recognition Using Convolutional Neural Networks. In Proceedings of the Advanced Data Mining and Applications, Foshan, China, 12–14 November 2020; Yang, X., Wang, C.D., Islam, M.S., Zhang, Z., Eds.; Lecture Notes in Computer Science. Springer: Cham, Switzerland; pp. 299–314. [Google Scholar] [CrossRef]
- Hu, J.; Jia, C.; Liu, H.; Yi, X.; Liu, Y. A survey on state estimation of complex dynamical networks. Int. J. Syst. Sci.
**2021**, 52, 3351–3367. [Google Scholar] [CrossRef] - Hu, J.; Zhang, H.; Liu, H.; Yu, X. A survey on sliding mode control for networked control systems. Int. J. Syst. Sci.
**2021**, 52, 1129–1147. [Google Scholar] [CrossRef] - Tan, H.; Shen, B.; Peng, K.; Liu, H. Robust recursive filtering for uncertain stochastic systems with amplify-and-forward relays. Int. J. Syst. Sci.
**2020**, 51, 1188–1199. [Google Scholar] [CrossRef] - Li, X.; Han, F.; Hou, N.; Dong, H.; Liu, H. Set-membership filtering for piecewise linear systems with censored measurements under Round-Robin protocol. Int. J. Syst. Sci.
**2020**, 51, 1578–1588. [Google Scholar] [CrossRef] - Li, Q.; Liang, J. Dissipativity of the stochastic Markovian switching CVNNs with randomly occurring uncertainties and general uncertain transition rates. Int. J. Syst. Sci.
**2020**, 51, 1102–1118. [Google Scholar] [CrossRef]

**Figure 9.**TIDA approach, where (

**a**) is the original image, (

**b**) rotation, (

**c**) panning, (

**d**) scaling, (

**e**) brightness adjustment, (

**f**) contrast adjustment, and (

**g**) adding noise.

Categories | Numbers |
---|---|

Blast | 1654 |

Brown Spot | 1570 |

Blight | 1396 |

Healthy | 2563 |

Categories | Train Dataset | Test Dataset |
---|---|---|

Blast | 1323 | 331 |

Brown Spot | 1256 | 314 |

Blight | 1116 | 280 |

Healthy | 2050 | 513 |

Layer Name | Activation Function | Output Tensor |
---|---|---|

Latent vector | - | 512 × 1 × 1 |

Residual block | LeakyReLu | 512 × 4 × 4 |

Upsample | - | 512 × 8 × 8 |

Residual block | LeakyReLu | 512 × 8 × 8 |

Upsample | - | 512 × 16 × 16 |

Residual block | LeakyReLu | 512 × 16 × 16 |

Upsample | - | 128 × 32 × 32 |

Residual block | LeakyReLu | 128 × 32 × 32 |

Upsample | - | 64 × 64 × 64 |

Residual block | LeakyReLu | 64 × 64 × 64 |

Upsample | - | 32 × 128 × 128 |

Residual block | LeakyReLu | 32 × 128 × 128 |

Upsample | - | 16 × 256 × 256 |

Residual block | LeakyReLu | 16 × 256 × 256 |

Conv 1 × 1 | - | 3 × 256 × 256 |

Layer Name | Activation Function | Output Tensor |
---|---|---|

Intput image | - | 3 × 256 × 256 |

Conv 1 × 1 | LeakyReLU | 16 × 256 × 256 |

Residual block | LeakyReLU | 32 × 256 × 256 |

Downsample | - | 32 × 128 × 128 |

Residual block | LeakyReLU | 64 × 128 × 128 |

Downsample | - | 64 × 64 × 64 |

Residual block | LeakyReLU | 128 × 64 × 64 |

Downsample | - | 128 × 32 × 32 |

Residual block | LeakyReLU | 256 × 32 × 32 |

Downsample | - | 256 × 16 × 16 |

Residual block | LeakyReLU | 512 × 16 × 16 |

Downsample | - | 512 × 8 × 8 |

Residual block | LeakyReLU | 512 × 8 × 8 |

Downsample | - | 512 × 4 × 4 |

Avg pool, fc 1, softmax | - | 1 × 1 × 1 |

Method | Blast | Brown Spot | Blight | Healthy | FID Score Average |
---|---|---|---|---|---|

WGAN | 118.42 | 133.71 | 137.51 | 131.84 | 130.37 |

DCGAN | 95.37 | 107.26 | 101.68 | 90.39 | 98.68 |

Dual GAN | 70.13 | 86.78 | 92.24 | 64.20 | 78.34 |

WGAN-GP | 75.18 | 84.96 | 79.33 | 72.61 | 78.02 |

PWGAN-GP | 62.11 | 71.24 | 74.38 | 60.73 | 67.12 |

Method | Training Time (h) |
---|---|

WGAN | 45 |

DCGAN | 52 |

WGAN-GP | 59 |

PWGAN-GP | 88 |

Dual GAN | 97 |

Level | Blast | Brown Spot | Blight | Healthy |
---|---|---|---|---|

X0 | 83.21 | 79.76 | 80.11 | 82.62 |

X1 | 88.48 | 85.81 | 87.83 | 91.97 |

X2 | 93.77 | 89.28 | 91.35 | 90.31 |

X3 | 90.52 | 88.31 | 89.7 | 88.27 |

Max. Improve | 10.56 | 9.52 | 11.24 | 9.35 |

Level | Blast | Brown Spot | Blight | Healthy |
---|---|---|---|---|

X0 | 83.62 | 82.53 | 82.73 | 84.17 |

X1 | 94.84 | 94.03 | 93.84 | 94.16 |

X2 | 96.26 | 94.85 | 94.91 | 95.37 |

X3 | 95.53 | 95.01 | 94.69 | 95.21 |

Max. Improve | 12.64 | 12.48 | 12.18 | 11.20 |

Level | Blast | Brown Spot | Blight | Healthy |
---|---|---|---|---|

X0 | 84.21 | 82.09 | 83.53 | 85.07 |

X1 | 96.77 | 94.74 | 95.48 | 96.81 |

X2 | 98.25 | 95.22 | 95.94 | 97.19 |

X3 | 97.63 | 94.44 | 94.23 | 96.98 |

Max. Improve | 14.04 | 13.13 | 12.41 | 12.18 |

Method | Blast | Brown Spot | Blight | Healthy | Avg. |
---|---|---|---|---|---|

Actual data | 83.21 | 79.76 | 80.11 | 82.62 | 81.03 |

TIDA | 88.15 | 88.04 | 88.71 | 89.16 | 88.27 |

PWGAN-GP | 93.77 | 89.28 | 91.35 | 90.31 | 91.47 |

Method | Blast | Brown Spot | Blight | Healthy | Avg. |
---|---|---|---|---|---|

Actual data | 83.62 | 82.53 | 82.73 | 84.17 | 82.96 |

TIDA | 91.44 | 90.57 | 91.43 | 92.46 | 91.48 |

PWGAN-GP | 96.26 | 94.85 | 94.91 | 95.37 | 95.34 |

Method | Blast | Brown Spot | Blight | Healthy | Avg. |
---|---|---|---|---|---|

Actual data | 84.21 | 82.09 | 83.53 | 85.07 | 83.28 |

TIDA | 93.12 | 93.31 | 93.18 | 93.83 | 93.36 |

PWGAN-GP | 98.25 | 95.22 | 95.94 | 97.19 | 96.47 |

Hyperparameter | Condition |
---|---|

learning rate | 0.001, 0.005, 0.01, 0.05, 0.1 |

batch size | 16, 32, 64, 128, 256 |

optimizer | SGD, Adam, RMSProp |

Dataset Type | Average Accuracy (%) |
---|---|

Balanced dataset | 98.04 |

Imbalanced dataset | 98.33 |

Categories | Numbers |
---|---|

Blast | 56 |

Brown Spot | 62 |

Blight | 60 |

Healthy | 60 |

Model | Average Accuracy (%) |
---|---|

ResNet-50 | 81.55 |

TIDA+ResNet-50 | 94.84 |

PWGAN-GP+ResNet-50 | 97.03 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Lu, Y.; Tao, X.; Zeng, N.; Du, J.; Shang, R.
Enhanced CNN Classification Capability for Small Rice Disease Datasets Using Progressive WGAN-GP: Algorithms and Applications. *Remote Sens.* **2023**, *15*, 1789.
https://doi.org/10.3390/rs15071789

**AMA Style**

Lu Y, Tao X, Zeng N, Du J, Shang R.
Enhanced CNN Classification Capability for Small Rice Disease Datasets Using Progressive WGAN-GP: Algorithms and Applications. *Remote Sensing*. 2023; 15(7):1789.
https://doi.org/10.3390/rs15071789

**Chicago/Turabian Style**

Lu, Yang, Xianpeng Tao, Nianyin Zeng, Jiaojiao Du, and Rou Shang.
2023. "Enhanced CNN Classification Capability for Small Rice Disease Datasets Using Progressive WGAN-GP: Algorithms and Applications" *Remote Sensing* 15, no. 7: 1789.
https://doi.org/10.3390/rs15071789