FieldPlant: A Dataset of Field Plant Images for Plant Disease Detection and Classification With Deep Learning

Abstract

The Food and Agriculture Organization of the United Nations suggests increasing the food supply by 70% to feed the world population by 2050, although approximately one third of all food is wasted because of plant diseases or disorders. To achieve this goal, researchers have proposed many deep learning models to help farmers detect diseases in their crops as efficiently as possible to avoid yield declines. These models are usually trained on personal or public plant disease datasets such as PlantVillage or PlantDoc. PlantVillage is composed of laboratory images captured under laboratory conditions, with one leaf each and a uniform background. The models trained on this dataset have very low accuracies when running on field images with complex backgrounds and multiple leaves per image. To solve this problem, PlantDoc was built using 2,569 field images downloaded from the Internet and annotated to identify the individual leaves. However, this dataset includes some laboratory images and the absence of plant pathologists during the annotation process may have resulted in misclassification. In this study, FieldPlant is suggested as a dataset that includes 5,170 plant disease images collected directly from plantations. Manual annotation of individual leaves on each image was performed under the supervision of plant pathologists to ensure process quality. This resulted in 8,629 individual annotated leaves across the 27 disease classes. We ran various benchmarks on this dataset to evaluate state-of-the-art classification and object detection models and found that classification tasks on FieldPlant outperformed those on PlantDoc.

Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion

“…To validate improved model detection performance on tomato leaf diseases in complex environments and generalizability to diseases of other crops, this paper conducts training and testing on tomato leaf disease dataset, PlantDoc dataset and FieldPlant ( Moupojou et al, 2023 ) dataset. Given the high speed and accuracy of the YOLO series in real-time detection, YOLOX, YOLOv5, YOLOv6, YOLOv7, YOLOv8 ( Jocher et al, 2023 ) and improved YOLOv6 were selected for comparative experiments.…”

Automated Plant Disease Detection Using Deep Learning

“…[14] Nikolaos Ploskas explores machine learning and deep learning techniques for plant disease classification and detection using datasets comprising apple leaf images, achieving high accuracy but lacking fine-grained spatial details in classification. [15] Emerson Ajith Jubilson compares multiple deep learning models for plant leaf disease detection and classification, achieving 99.69% accuracy, yet facing limitations such as high parameters and slow detection.…”

Crop Disease Detection using Computer Vision

“…The FieldPlant dataset [12] serves as an invaluable resource for researchers and agriculturists, offering an extensive col-lection of real-world data related to crop health and disease prevalence. By examining the dataset, we gain a deeper understanding of the prevalence, distribution, and character-istics of common crop diseases, which are instrumental for the development of effective mitigation strategies.…”

“…An extensive plant disease dataset [12] was introduced containing 5,170 meticulously annotated field leaf images gathered from the plantations in Cameroon. This dataset is centered around diverse diseases found in three tropical crops: corn, cassava, and tomato.…”