Real-time detection and identification of plant leaf diseases using convolutional neural networks on an embedded platform

• Published in: The Visual computer Vol. 38; no. 8; pp. 2923 - 2938
• Main Authors: Gajjar, Ruchi, Gajjar, Nagendra, Thakor, Vaibhavkumar Jigneshkumar, Patel, Nikhilkumar Pareshbhai, Ruparelia, Stavan
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2022; Springer Nature B.V
• Subjects: Accuracy; Agricultural production; Artificial Intelligence; Artificial neural networks; Cameras; Chlorophyll; Classification; Computer Graphics; Computer Science; Corn; Crop diseases; Datasets; Field tests; Identification; Image Processing and Computer Vision; Leaves; Legumes; Localization; Machine learning; Medical diagnosis; Neural networks; Original Article; Pathogens; Plant diseases; Real time; Rice; Real-time detection; Crop diseases identification; Machine Learning; Convolutional neural network; Precision Agriculture; Embedded Platform
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-021-02164-9

Early identification of crop disease can aid the farmers to take timely precautions and countermeasures for its removal. In this paper, a real-time system to identify the type of disease present in a crop based on leaf images using machine learning is proposed. A deep convolutional neural network architecture is proposed to classify the crop disease, and a single shot detector is used for identification and localization of the leaf. These models are deployed on an embedded hardware, Nvidia Jetson TX1, for real-time in-field plant disease detection and identification. The disease classification accuracy achieved is around 96.88%, and the classification results are compared with existing convolutional neural network architectures. Also, the high success rate of the proposed system in the actual field test makes the proposed system a completely deployable system.