Using deep transfer learning for image-based plant disease identification

Chen, Junde; Chen, Jinxiu; Zhang, Defu; Sun, Yuhao; Nanehkaran, Yaser Ahangari

doi:10.1016/j.compag.2020.105393

Cited by 692 publications

(289 citation statements)

References 26 publications

Supporting

Mentioning

277

Contrasting

Unclassified

Order By: Relevance

“…The technique is very sensitive to the selected threshold. A modified VGGNet pre-trained on ImageNet using two inception modules is introduced to detect plant disease [55]. Inception v3 pre-trained on ImageNet is also used to detect the incidence of cassava disease [56].…”

Section: Related Workmentioning

confidence: 99%

Automatic Plant Counting and Location Based on a Few-Shot Learning Technique

Karami

Crawford

Delp

2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Plant counting and location are essential for both plant breeding experiments and production agriculture. Stand count indicates the overall emergence of plants compared to the number of seeds that were planted, while location provides information on the associated variability within a plot or geographic area of a field. Deep learning has been successfully applied in various application domains, including plant phenotyping. This paper proposes the use of deep learning techniques, more specifically, anchor-free detectors, to identify and count maize plants in RGB images acquired from Unmanned Aerial Vehicles (UAV). The results were obtained using a modified CenterNet architecture, with validation performed against manual human annotation. Experimental results demonstrated an overall precision >95% for examples where training and testing were performed on the same field. Few-shot learning was also explored, where the trained network was a) directly applied to the fields in other geographic areas and b) updated using small quantities of training data from the other locations.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Plant Counting and Location Based on a Few-Shot Learning Technique

Karami

Crawford

Delp

2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, the research on tomato diseases classification belongs to FGVC. Although deep learning has facilitated the study of many computer vision classification tasks in the agricultural field [5]- [11], we have not found some FGVC study in the field of agricultural crop disease image classification. At present, because it is difficult to find and locate regions with judgment value and abundant informativeness in crop health/diseases images, many researchers still focus on coarse-grained crop image classification.…”

Section: Introductionmentioning

confidence: 92%

Self-Supervised Collaborative Multi-Network for Fine-Grained Visual Categorization of Tomato Diseases

Yang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Artificial recognition of tomato diseases is often time-consuming, laborious and subjective. For tomato disease images, it is difficult to find small discriminative features between different tomato diseases, which can bring challenges to fine-grained visual categorization of tomato leaf-based images. Therefore, we propose a novel model, which consists of 3 networks, including a Location network, a Feedback network, and a Classification network, named LFC-Net. At the same time, a self-supervision mechanism is proposed in the model, which can effectively detect informative regions of tomato image without the need for manual annotation such as bounding boxes/parts. Based on the consideration of the consistency between category of the image and informativeness of the image, we design a novel training paradigm. The Location network of the model first detects informative regions in the tomato image, and optimizes iterations under the guidance of the Feedback network. Then, the Classification network uses informative regions proposed by the Location network and the full image of the tomato for classification. Our model can be regarded as a multi-network collaboration, and networks can progress together. Compared with the pre-trained model on ImageNet, our model achieves the most advanced performance in the tomato dataset, with accuracy up to 99.7%. This work demonstrates that our model has a high accuracy and has the potential to be applied to other vegetable and fruit datasets, which can provide a reference for the prevention and control of tomato diseases. INDEX TERMS Fine-grained visual categorization, multi-network, self-supervised, tomato diseases This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

show abstract

“…The availability of large, multi-labelled and well-annotated dataset repositories eliminates the need for researchers to collect massive datasets in different real conditions and environments that would need the oversight of agricultural specialists to be interpreted. Transfer learning allows a CNN model to acquire weights from another model that has already been pre-trained on a large labelled dataset [ 79 , 80 , 81 ]. The pre-trained model’s parameters must be fine-tuned, and the final layer is replaced with a new layer for convenient transfer of the weights to the proposed new model and the new classes in the target dataset.…”

Section: Feature Representation In Deep Classifiersmentioning

confidence: 99%

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Hasan

Yusuf

Alzubaidi

2020

Plants

151

View full text Add to dashboard Cite

Deep learning (DL) represents the golden era in the machine learning (ML) domain, and it has gradually become the leading approach in many fields. It is currently playing a vital role in the early detection and classification of plant diseases. The use of ML techniques in this field is viewed as having brought considerable improvement in cultivation productivity sectors, particularly with the recent emergence of DL, which seems to have increased accuracy levels. Recently, many DL architectures have been implemented accompanying visualisation techniques that are essential for determining symptoms and classifying plant diseases. This review investigates and analyses the most recent methods, developed over three years leading up to 2020, for training, augmentation, feature fusion and extraction, recognising and counting crops, and detecting plant diseases, including how these methods can be harnessed to feed deep classifiers and their effects on classifier accuracy.

show abstract

Using deep transfer learning for image-based plant disease identification

Cited by 692 publications

References 26 publications

Automatic Plant Counting and Location Based on a Few-Shot Learning Technique

Automatic Plant Counting and Location Based on a Few-Shot Learning Technique

Self-Supervised Collaborative Multi-Network for Fine-Grained Visual Categorization of Tomato Diseases

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Contact Info

Product

Resources

About