The Plant Pathology Challenge 2020 data set to classify foliar disease of apples

• Published in: Applications in plant sciences Vol. 8; no. 9; pp. e11390 - n/a
• Main Authors: Thapa, Ranjita, Zhang, Kai, Snavely, Noah, Belongie, Serge, Khan, Awais
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.09.2020; John Wiley and Sons Inc; Wiley
• Subjects: Abiotic stress; Algorithms; apple orchards; Application; Classification; computer vision; convolutional neural network; Crowdsourcing; Cultivars; Digital cameras; Digital imaging; disease classification; Foliar diseases; Fruits; Infections; Learning algorithms; Machine learning; Neural networks; Orchards; Pathogens; Pattern recognition; Plant communities; Plant diseases; Plant sciences; Rust fungi; Scab; Smartphones; United States > US; apple orchards; disease classification; machine learning; convolutional neural network; computer vision
• ISSN: 2168-0450; 2168-0450
• DOI: 10.1002/aps3.11390

Premise Apple orchards in the United States are under constant threat from a large number of pathogens and insects. Appropriate and timely deployment of disease management depends on early disease detection. Incorrect and delayed diagnosis can result in either excessive or inadequate use of chemicals, with increased production costs and increased environmental and health impacts. Methods and Results We have manually captured 3651 high‐quality, real‐life symptom images of multiple apple foliar diseases, with variable illumination, angles, surfaces, and noise. A subset of images, expert‐annotated to create a pilot data set for apple scab, cedar apple rust, and healthy leaves, was made available to the Kaggle community for the Plant Pathology Challenge as part of the Fine‐Grained Visual Categorization (FGVC) workshop at the 2020 Computer Vision and Pattern Recognition conference (CVPR 2020). Participants were asked to use the image data set to train a machine learning model to classify disease categories and develop an algorithm for disease severity quantification. The top three area under the ROC curve (AUC) values submitted to the private leaderboard were 0.98445, 0.98182, and 0.98089. We also trained an off‐the‐shelf convolutional neural network on this data for disease classification and achieved 97% accuracy on a held‐out test set. Discussion This data set will contribute toward development and deployment of machine learning–based automated plant disease classification algorithms to ultimately realize fast and accurate disease detection. We will continue to add images to the pilot data set for a larger, more comprehensive expert‐annotated data set for future Kaggle competitions and to explore more advanced methods for disease classification and quantification.