Creative Approaches Towards Development of Computing and Multidisciplinary IT Solutions for Society

17Identification and Classification of Plant Leaf Diseases Using Data Augmentation and Deep Convolutional Neural Networks

Phong Bui Hai^1*, Nguyen Ngoc Bao², Nguyen Canh Thai³, Pham Hong Phuc⁴, Nguyen Quang Minh⁴, Le Chi Luan⁵, Nguyen Quang Trung⁶ and Pham Van Khuong⁷

¹Hanoi Architectural University, Hanoi, Vietnam

²University of Massachusetts Amherst, Amherst, USA

³The National Mathematics and Science College, Westwood Way, Coventry Warwickshire, UK

⁴High School for Gifted Students, Vietnam National University, Hanoi, Vietnam

⁵University of Transport Technology, Hanoi, Vietnam

⁶Vietnam Youth Academy, Hanoi, Vietnam

⁷BKStar Center, Hanoi, Vietnam

Abstract

In agriculture, the early and accurate identification of plant diseases is an important step in increasing crop yield. Leaf disease detection is one of the most widely used methods for identifying plant diseases. In recent years, automatic and accurate classification of plant leaf diseases has attracted increasing research attention. With the emergence of deep neural networks (DNN), the identification and classification of plant leaf diseases have achieved competitive results. This study proposes a method based on data augmentation techniques and advanced deep neural network models to improve the accuracy of the identification and classification of plant leaf diseases. First, augmentation techniques using image processing have been applied to efficiently train DNN models. Then, the advanced DNN models were fine-tuned to improve ...