“…Their approach relied on spectral vegetation indices and SVMs, and 97% accuracy was achieved by the final model on the validation dataset. Aditya Sinha et al [21] in their study, summarized widespread approaches and methodologies utilized for the discovery, quantification, and division of diseases by previous researchers to know the scope of modification. S. Ramesh et al [22] created their dataset for crop disease detection.…”
The automatic detection of diseases in plants is necessary, as it reduces the tedious work of monitoring large farms and it will detect the disease at an early stage of its occurrence to minimize further degradation of plants. Besides the decline of plant health, a country’s economy is highly affected by this scenario due to lower production. The current approach to identify diseases by an expert is slow and non-optimal for large farms. Our proposed model is an ensemble of pre-trained DenseNet121, EfficientNetB7, and EfficientNet NoisyStudent, which aims to classify leaves of apple trees into one of the following categories: healthy, apple scab, apple cedar rust, and multiple diseases, using its images. Various Image Augmentation techniques are included in this research to increase the dataset size, and subsequentially, the model’s accuracy increases. Our proposed model achieves an accuracy of 96.25% on the validation dataset. The proposed model can identify leaves with multiple diseases with 90% accuracy. Our proposed model achieved a good performance on different metrics and can be deployed in the agricultural domain to identify plant health accurately and timely.
“…Their approach relied on spectral vegetation indices and SVMs, and 97% accuracy was achieved by the final model on the validation dataset. Aditya Sinha et al [21] in their study, summarized widespread approaches and methodologies utilized for the discovery, quantification, and division of diseases by previous researchers to know the scope of modification. S. Ramesh et al [22] created their dataset for crop disease detection.…”
The automatic detection of diseases in plants is necessary, as it reduces the tedious work of monitoring large farms and it will detect the disease at an early stage of its occurrence to minimize further degradation of plants. Besides the decline of plant health, a country’s economy is highly affected by this scenario due to lower production. The current approach to identify diseases by an expert is slow and non-optimal for large farms. Our proposed model is an ensemble of pre-trained DenseNet121, EfficientNetB7, and EfficientNet NoisyStudent, which aims to classify leaves of apple trees into one of the following categories: healthy, apple scab, apple cedar rust, and multiple diseases, using its images. Various Image Augmentation techniques are included in this research to increase the dataset size, and subsequentially, the model’s accuracy increases. Our proposed model achieves an accuracy of 96.25% on the validation dataset. The proposed model can identify leaves with multiple diseases with 90% accuracy. Our proposed model achieved a good performance on different metrics and can be deployed in the agricultural domain to identify plant health accurately and timely.
“…Recent developments in machine learning approaches in the agriculture sector are up-and-coming. They have been receiving significant interest from academia [2,3,6,7], industries [1,10], and governments [13,14]. This section reviews some of the existing work supporting the detection of crop diseases using different machine learning approaches.…”
Section: Related Workmentioning
confidence: 99%
“…Plant diseases [1], pest infestation [2], weed pressure [3], and nutrient deficiencies [4] are some of the grand challenges for any agricultural producer, at any location and for whatever commodities or size of the operation is dealing daily. It is crucial that farmers would know the existence of such challenges in their operations on a timely basis.…”
Section: Introductionmentioning
confidence: 99%
“…Machine Learning (ML) coupled with computer vision [7,8] have already enabled game-changing precision agriculture capabilities by providing the ability to optimize farm returns [9], preserve natural resources [10], reduce unnecessary use of fertilizers [1], and identify disease in crops and animals from remotely sensed imagery [11]. Imagine a smart mobile-based system that farmers can use to identify the different types of plant diseases with high accuracy.…”
Plant diseases are one of the grand challenges that face the agriculture sector worldwide. In the United States, crop diseases cause losses of one-third of crop production annually. Despite the importance, crop disease diagnosis is challenging for limited-resources farmers if performed through optical observation of plant leaves’ symptoms. Therefore, there is an urgent need for markedly improved detection, monitoring, and prediction of crop diseases to reduce crop agriculture losses. Computer vision empowered with Machine Learning (ML) has tremendous promise for improving crop monitoring at scale in this context. This paper presents an ML-powered mobile-based system to automate the plant leaf disease diagnosis process. The developed system uses Convolutional Neural networks (CNN) as an underlying deep learning engine for classifying 38 disease categories. We collected an imagery dataset containing 96,206 images of plant leaves of healthy and infected plants for training, validating, and testing the CNN model. The user interface is developed as an Android mobile app, allowing farmers to capture a photo of the infected plant leaves. It then displays the disease category along with the confidence percentage. It is expected that this system would create a better opportunity for farmers to keep their crops healthy and eliminate the use of wrong fertilizers that could stress the plants. Finally, we evaluated our system using various performance metrics such as classification accuracy and processing time. We found that our model achieves an overall classification accuracy of 94% in recognizing the most common 38 disease classes in 14 crop species.
“…In recent years, plant diseases and pest identification has attracted wide attention from academia and agriculture, and become a research hotspot in the field of computer vision. After more than 10 years of development, a large number of plant diseases and pests identification models have been proposed at home and abroad, and very high accuracy has been achieved under the limited simulation conditions (Singh et al, 2018;Geetharamani and Arun Pandian, 2019;Shekhawat and Sinha, 2020), and even surpasses the ability of human vision.…”
Background: In view of the existence of light shadow, branches occlusion, and leaves overlapping conditions in the real natural environment, problems such as slow detection speed, low detection accuracy, high missed detection rate, and poor robustness in plant diseases and pests detection technology arise.Results: Based on YOLOv3-tiny network architecture, to reduce layer-by-layer loss of information during network transmission, and to learn from the idea of inverse-residual block, this study proposes a YOLOv3-tiny-IRB algorithm to optimize its feature extraction network, improve the gradient disappearance phenomenon during network deepening, avoid feature information loss, and realize network multilayer feature multiplexing and fusion. The network is trained by the methods of expanding datasets and multiscale strategies to obtain the optimal weight model.Conclusion: The experimental results show that when the method is tested on the self-built tomato diseases and pests dataset, and while ensuring the detection speed (206 frame rate per second), the mean Average precision (mAP) under three conditions: (a) deep separation, (b) debris occlusion, and (c) leaves overlapping are 98.3, 92.1, and 90.2%, respectively. Compared with the current mainstream object detection methods, the proposed method improves the detection accuracy of tomato diseases and pests under conditions of occlusion and overlapping in real natural environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.