Unsupervised Representation Learning of Image-Based Plant Disease with Deep Convolutional Generative Adversarial Networks

• Published in: Chinese Control Conference pp. 9159 - 9163
• Main Authors: Li, Jie, Jia, Junjie, Xu, Donglai
• Format: Conference Proceeding
• Language: English
• Published: Technical Committee on Control Theory, Chinese Association of Automation 01.07.2018
• Subjects: Deep Convolutional Generative Adversarial Networks; Economic indicators; Plant Disease; Unsupervised Representation Learning; XML
• ISSN: 1934-1768
• DOI: 10.23919/ChiCC.2018.8482813

Rapid identification of plant disease is essential for food security. Deep learning, the latest breakthrough in computer vision, is promising for plant disease severity classification, as the method avoids the labor-intensive feature engineering and threshold-based segmentation. Using a public dataset of 54,306 images of diseased and healthy plant leaves collected under controlled conditions, a deep convolutional neural network and unsupervised methods are used to identify 14 crop species and 26 diseases. The trained model achieves an accuracy of 89.83% on a held-out test set, demonstrating the feasibility of this approach.