Data Augmentation using Adversarial Networks for Tea Diseases Detection

R. Sandra Yuwana (Research Center for Informatics Indonesian Institute of Sciences - LIPI)
Fani Fauziah (Research Institute for Tea and Cinchona (RITC) Indonesian Agency for Agricultural Research and Development)
Ana Heryana
Dikdik Krisnandi (Research Center for Informatics Indonesian Institute of Sciences - LIPI)
R. Budiarianto Suryo Kusumo (Research Center for Informatics Indonesian Institute of Sciences - LIPI)
Hilman F. Pardede (Research Center for Informatics Indonesian Institute of Sciences - LIPI)

Jurnal Elektronika dan Telekomunikasi
Vol 20, No 1 (2020)

Deep learning technology has a better result when trained using an abundant amount of data. However, collecting such data is expensive and time consuming.  On the other hand, limited data often be the inevitable condition. To increase the number of data, data augmentation is usually implemented.  By using it, the original data are transformed, by rotating, shifting, or both, to generate new data artificially. In this paper, generative adversarial networks (GAN) and deep convolutional GAN (DCGAN) are used for data augmentation. Both approaches are applied for diseases detection. The performance of the tea diseases detection on the augmented data is evaluated using various deep convolutional neural network (DCNN) including AlexNet, DenseNet, ResNet, and Xception.  The experimental results indicate that the highest GAN accuracy is obtained by DenseNet architecture, which is 88.84%, baselines accuracy on the same architecture is 86.30%. The results of DCGAN accuracy on the use of the same architecture show a similar trend, which is 88.86%.