A review of deep learning techniques used in agriculture

Ecological Informatics, Год журнала: 2023, Номер 77, С. 102217 - 102217

Опубликована: Июль 18, 2023

Язык: Английский

---

Leaf disease detection using machine learning and deep learning: Review and challenges

Applied Soft Computing, Год журнала: 2023, Номер 145, С. 110534 - 110534

Опубликована: Июнь 22, 2023

Язык: Английский

---

A Systematic Literature Review on Plant Disease Detection: Motivations, Classification Techniques, Datasets, Challenges, and Future Trends

IEEE Access, Год журнала: 2023, Номер 11, С. 59174 - 59203

Опубликована: Янв. 1, 2023

Plant pests and diseases are a significant threat to almost all major types of plants global food security. Traditional inspection across different plant fields is time-consuming impractical for wider plantation size, thus reducing crop production. Therefore, many smart agricultural practices deployed control pests. Most these approaches, example, use vision-based artificial intelligence (AI), machine learning (ML), or deep (DL) methods models provide disease detection solutions. However, existing open issues must be considered addressed before AI can used. In this study, we conduct systematic literature review (SLR) present detailed survey the studies employing data collection techniques publicly available datasets. To begin review, 1349 papers were chosen from five academic databases, namely Springer, IEEE Xplore, Scopus, Google Scholar, ACM library. After deploying comprehensive screening process, 176 final based on importance method. Several crops, including grapes, rice, apples, cucumbers, maize, tomatoes, wheat, potatoes, have tested mainly hyperspectral imagery vision-centered approaches. Support Vector Machines (SVMs) Logistic regression (LR) classifiers demonstrated an increased accuracy in experiments compared traditional classifiers. Besides image taxonomy, localization depicted approaches as bottle neck detection. Cognitive CNNs with attention mechanisms transfer showing increasing trend. There no standard model performance assessment though majority accuracy, recall, precision, F1 Score, confusion matrix. The 11 datasets laboratory in-field based, 9 available. Some laboratory-based considerably small, making them experiments. Finally, there need avail fewer parameters, implementable small devices large accommodating several crops robust models.

Язык: Английский

---

Systematic study on deep learning-based plant disease detection or classification

Artificial Intelligence Review, Год журнала: 2023, Номер 56(12), С. 14955 - 15052

Опубликована: Июнь 14, 2023

Язык: Английский

---

DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification

Computers and Electronics in Agriculture, Год журнала: 2023, Номер 216, С. 108481 - 108481

Опубликована: Дек. 6, 2023

Язык: Английский

---

YOLOV5-CBAM-C3TR: an optimized model based on transformer module and attention mechanism for apple leaf disease detection

Frontiers in Plant Science, Год журнала: 2024, Номер 14

Опубликована: Янв. 15, 2024

Apple trees face various challenges during cultivation. leaves, as the key part of apple tree for photosynthesis, occupy most area tree. Diseases leaves can hinder healthy growth and cause huge economic losses to fruit growers. The prerequisite precise control leaf diseases is timely accurate detection different on leaves. Traditional methods relying manual have problems such limited accuracy slow speed. In this study, both attention mechanism module containing transformer encoder were innovatively introduced into YOLOV5, resulting in YOLOV5-CBAM-C3TR disease detection. datasets used experiment uniformly RGB images. To better evaluate effectiveness YOLOV5-CBAM-C3TR, model was compared with target models SSD, YOLOV3, YOLOV4, YOLOV5. results showed that achieved [email protected], precision, recall 73.4%, 70.9%, 69.5% three including Alternaria blotch, Grey spot, Rust. Compared original mAP 0.5increased by 8.25% a small change number parameters. addition, achieve an average 92.4% detecting 208 randomly selected samples. Notably, 93.1% 89.6% two very similar Blotch Spot, respectively. proposed paper has been applied first time, also strong recognition ability identifying diseases, which expected promote further development technology.

Язык: Английский

---

Plant Leaf Disease Detection, Classification, and Diagnosis Using Computer Vision and Artificial Intelligence: A Review

IEEE Access, Год журнала: 2024, Номер 12, С. 37443 - 37469

Опубликована: Янв. 1, 2024

Agriculture is the ultimate imperative and primary source of origin to furnish domestic income for multifarious countries. The disease caused in plants due various pathogens like viruses, fungi, bacteria liable considerable monetary losses agriculture corporation across world. security crops concerning quality quantity crucial monitor plants. Thus, recognition plant essential. syndrome noticeable distinct parts Nonetheless, commonly infection detected leaves Computer vision, deep learning, few-shot soft computing techniques are utilized by investigators automatically identify via leaf images. These also benefit farmers achieving expeditious appropriate actions avoid a reduction crops. application these can avert disadvantage factious selection features, extraction boost speed technology efficiency research. Also, certain molecular have been established prevent mitigate pathogenic threat. Hence, this review helps investigator detect using machine learning few shot provide diagnosis disease. Moreover, some future works classification discussed.

Язык: Английский

---

A hybrid Framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer

Complex & Intelligent Systems, Год журнала: 2025, Номер 11(2)

Опубликована: Янв. 15, 2025

Recently, scientists have widely utilized Artificial Intelligence (AI) approaches in intelligent agriculture to increase the productivity of sector and overcome a wide range problems. Detection classification plant diseases is challenging problem due vast numbers plants worldwide numerous that negatively affect production different crops. Early detection accurate goal any AI-based system. This paper proposes hybrid framework improve accuracy for leaf significantly. proposed model leverages strength Convolutional Neural Networks (CNNs) Vision Transformers (ViT), where an ensemble model, which consists well-known CNN architectures VGG16, Inception-V3, DenseNet20, used extract robust global features. Then, ViT local features detect precisely. The performance evaluated using two publicly available datasets (Apple Corn). Each dataset four classes. successfully detects classifies multi-class outperforms similar recently published methods, achieved rate 99.24% 98% apple corn datasets.

Язык: Английский

---

Hyperparameter Optimization for Tomato Leaf Disease Recognition Based on YOLOv11m

Plants, Год журнала: 2025, Номер 14(5), С. 653 - 653

Опубликована: Фев. 21, 2025

The automated recognition of disease in tomato leaves can greatly enhance yield and allow farmers to manage challenges more efficiently. This study investigates the performance YOLOv11 for leaf recognition. All accessible versions were first fine-tuned on an improved dataset consisting a healthy class 10 classes. YOLOv11m was selected further hyperparameter optimization based its evaluation metrics. It achieved fitness score 0.98885, with precision 0.99104, recall 0.98597, [email protected] 0.99197. model underwent rigorous using one-factor-at-a-time (OFAT) algorithm, focus essential parameters such as batch size, learning rate, optimizer, weight decay, momentum, dropout, epochs. Subsequently, random search (RS) 100 configurations performed results OFAT. Among them, C47 demonstrated 0.99268 (a 0.39% improvement), 0.99190 (0.09%), 0.99348 (0.76%), 0.99262 (0.07%). suggest that final works efficiently is capable accurately detecting identifying diseases, making it suitable practical farming applications.

Язык: Английский

---

LeafConvNeXt: Enhancing plant disease classification for the future of unmanned farming

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 233, С. 110165 - 110165

Опубликована: Март 6, 2025

Язык: Английский

---