Abstract—Cassava is an important Thai industrial crop. Thailand is a leader in cassava production; therefore, the large volume of cassava has been produced and exported from Thailand. However, cassava disease is the main factor to reduce cassava production and directly affects farmers' income. In this study, we aimed to introduce a novel method to automatic cassava disease classification by using deep learning algorithms. An input data was a collection of cassava leaves images containing five different classes, i.e., healthy, Cassava brown streak virus disease (cbsd), Cassava Bacterial Blight (cbb), Cassava green mite (cgm) and Cassava mosaic disease (cmd). Notwithstanding, we focused on the cbsd only in this study forasmuch as this disease has a high impact on the production. We conducted an experiment to evaluate method performance. Our system provided reasonable performance. The accuracy and F-measure of the system were 0.96. This is evidence that our system is applicable to efficiently classify the cassava diseases automatically. In future works, we will investigate an appropriate solution to classify other diseases of cassava.
 

Index Terms—Cassava disease, cbsd, Deep learning, Convolution Neural Networks, Classification

Cite: Isaman Sangbamrung, Panchalee Praneetpholkrang, and Sarunya Kanjanawattana, "A Novel Automatic Method for Cassava Disease Classification Using Deep Learning," Journal of Advances in Information Technology, Vol. 11, No. 4, pp. 241-248, November 2020. doi: 10.12720/jait.11.4.241-248

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.