Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network

Kim, Byoungjun; Han, Young Taek; Park, Jonghan; Lee, Joonwhoan

doi:10.3389/fpls.2020.559172

Cited by 29 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No official accuracy is reported; rather, it is concluded that SVM has a higher recognition rate than the neural network when used as a classifier. Next, the dataset of Byoungjun et al [ 4 ] report a basic mAP of 83.13% using Faster R-CNN with pre-trained ImageNet weights. Improvement is made using a cascaded architecture and pre-trained weights from PlantCLEF dataset.…”

Section: Resultsmentioning

confidence: 99%

“…The literature indicates a scarcity of datasets pertaining to the instance segmentation of different kinds of strawberry diseases. Although various models have been developed to perform object detection for multiple diseases in strawberries [ 4 , 47 ], there is much to be desired when it comes to datasets allowing fine-grained instance segmentation of multiple diseases and pests in strawberries. In an attempt to fill that void, we introduce a new dataset that allows users to segment seven different kinds of strawberry diseases.…”

Section: Methodsmentioning

confidence: 99%

“…Next, the images taken are processed using automatic detection systems. (2) Robots perform surveillance in the entirety of the greenhouse and collect required photos autonomously, which are subsequently processed by an automatic disease detection system [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN

Afzaal

Bhattarai

Pandeya

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Plant diseases must be identified at the earliest stage for pursuing appropriate treatment procedures and reducing economic and quality losses. There is an indispensable need for low-cost and highly accurate approaches for diagnosing plant diseases. Deep neural networks have achieved state-of-the-art performance in numerous aspects of human life including the agriculture sector. The current state of the literature indicates that there are a limited number of datasets available for autonomous strawberry disease and pest detection that allow fine-grained instance segmentation. To this end, we introduce a novel dataset comprised of 2500 images of seven kinds of strawberry diseases, which allows developing deep learning-based autonomous detection systems to segment strawberry diseases under complex background conditions. As a baseline for future works, we propose a model based on the Mask R-CNN architecture that effectively performs instance segmentation for these seven diseases. We use a ResNet backbone along with following a systematic approach to data augmentation that allows for segmentation of the target diseases under complex environmental conditions, achieving a final mean average precision of 82.43%.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN

Afzaal

Bhattarai

Pandeya

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this situation, Faster R-CNN or its variants, such as cascaded Faster R-CNN, would be a better choice. Note that the classification approach for monitoring diseases is hard to automatize ( Kim et al, 2021 ); this is because the image-containing symptoms of the disease should be manually located to take pictures and then fed into the classification-based monitoring system. However, it is still an important way to identify known and unknown diseases or disorders.…”

Section: Related Workmentioning

confidence: 99%

Deep Metric Learning-Based Strawberry Disease Detection With Unknowns

2022

Self Cite

View full text Add to dashboard Cite

There has been substantial research that has achieved significant advancements in plant disease detection based on deep object detection models. However, with unknown diseases, it is difficult to find a practical solution for plant disease detection. This study proposes a simple but effective strawberry disease detection scheme with unknown diseases that can provide applicable performance in the real field. In the proposed scheme, the known strawberry diseases are detected with deep metric learning (DML)-based classifiers along with the unknown diseases that have certain symptoms. The pipeline of our proposed scheme consists of two stages: the first is object detection with known disease classes, while the second is a DML-based post-filtering stage. The second stage has two different types of classifiers: one is softmax classifiers that are only for known diseases and the K-nearest neighbor (K-NN) classifier for both known and unknown diseases. In the training of the first stage and the DML-based softmax classifier, we only use the known samples of the strawberry disease. Then, we include the known (a priori) and the known unknown training samples to construct the K-NN classifier. The final decisions regarding known diseases are made from the combined results of the two classifiers, while unknowns are detected from the K-NN classifier. The experimental results show that the DML-based post-filter is effective at improving the performance of known disease detection in terms of mAP. Furthermore, the separate DML-based K-NN classifier provides high recall and precision for known and unknown diseases and achieve 97.8% accuracy, meaning it could be exploited as a Region of Interest (ROI) classifier. For the real field data, the proposed scheme achieves a high mAP of 93.7% to detect known classes of strawberry disease, and it also achieves reasonable results for unknowns. This implies that the proposed scheme can be applied to identify disease-like symptoms caused by real known and unknown diseases or disorders for any kind of plant.

show abstract

“…Sharpe et al (2020) uses YOLOv3 to perform goosegrass detection in strawberry and tomato plants. Kim et al (2020) proposed a two-stage cascade disease detection model applied to strawberry plants. Afonso et al (2020) extended the use of deep learning for tomato fruit detection and counting in greenhouses.…”

Section: Plant Disease Recognitionmentioning

confidence: 99%

Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques

et al. 2021

View full text Add to dashboard Cite

Recent advances in automatic recognition systems based on deep learning technology have shown the potential to provide environmental-friendly plant disease monitoring. These systems are able to reliably distinguish plant anomalies under varying environmental conditions as the basis for plant intervention using methods such as classification or detection. However, they often show a performance decay when applied under new field conditions and unseen data. Therefore, in this article, we propose an approach based on the concept of open-set domain adaptation to the task of plant disease recognition to allow existing systems to operate in new environments with unseen conditions and farms. Our system specifically copes diagnosis as an open set learning problem, and mainly operates in the target domain by exploiting a precise estimation of unknown data while maintaining the performance of the known classes. The main framework consists of two modules based on deep learning that perform bounding box detection and open set self and across domain adaptation. The detector is built based on our previous filter bank architecture for plant diseases recognition and enforces domain adaptation from the source to the target domain, by constraining data to be classified as one of the target classes or labeled as unknown otherwise. We perform an extensive evaluation on our tomato plant diseases dataset with three different domain farms, which indicates that our approach can efficiently cope with changes of new field environments during field-testing and observe consistent gains from explicit modeling of unseen data.

show abstract

Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network

Cited by 29 publications

References 35 publications

An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN

An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN

Deep Metric Learning-Based Strawberry Disease Detection With Unknowns

Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques

Contact Info

Product

Resources

About