Image‐based crop disease detection using machine learning

Plant Pathology, Год журнала: 2024, Номер unknown

Опубликована: Сен. 27, 2024

Abstract Crop disease detection is important due to its significant impact on agricultural productivity and global food security. Traditional methods often rely labour‐intensive field surveys manual inspection, which are time‐consuming prone human error. In recent years, the advent of imaging technologies coupled with machine learning (ML) algorithms has offered a promising solution this problem, enabling rapid accurate identification crop diseases. Previous studies have demonstrated potential image‐based techniques in detecting various diseases, showcasing their ability capture subtle visual cues indicative pathogen infection or physiological stress. However, rapidly evolving, advancements sensor technology, data analytics artificial intelligence (AI) continually expanding capabilities these systems. This review paper consolidates existing literature using ML, providing comprehensive overview cutting‐edge methodologies. Synthesizing findings from diverse offers insights into effectiveness different platforms, contextual integration applicability ML across types environmental conditions. The importance lies bridge gap between research practice, offering valuable guidance researchers practitioners.

Язык: Английский

---

Nutritional composition analysis in food images: an innovative Swin Transformer approach

Frontiers in Nutrition, Год журнала: 2024, Номер 11

Опубликована: Окт. 14, 2024

Accurate recognition of nutritional components in food is crucial for dietary management and health monitoring. Current methods often rely on traditional chemical analysis techniques, which are time-consuming, require destructive sampling, not suitable large-scale or real-time applications. Therefore, there a pressing need efficient, non-destructive, accurate to identify quantify nutrients food. In this study, we propose novel deep learning model that integrates EfficientNet, Swin Transformer, Feature Pyramid Network (FPN) enhance the accuracy efficiency nutrient recognition. Our combines strengths EfficientNet feature extraction, Transformer capturing long-range dependencies, FPN multi-scale fusion. Experimental results demonstrate our significantly outperforms existing methods. On Nutrition5k dataset, it achieves Top-1 79.50% Mean Absolute Percentage Error (MAPE) calorie prediction 14.72%. ChinaMartFood109 80.25% MAPE 15.21%. These highlight model's robustness adaptability across diverse images, providing reliable efficient tool rapid, non-destructive detection. This advancement supports better enhances understanding nutrition, potentially leading more effective monitoring

Язык: Английский

---

Classification of hazelnut varieties based on bigtransfer deep learning model

European Food Research and Technology, Год журнала: 2024, Номер 250(5), С. 1433 - 1442

Опубликована: Фев. 27, 2024

Abstract Hazelnut is an agricultural product that contributes greatly to the economy of countries where it grown. The human factor plays a major role in hazelnut classification. typical approach involves manual inspection each sample by experts, process both labor-intensive and time-consuming, often suffers from limited sensitivity. deep learning techniques are extremely important classification detection products. Deep has great potential sector. This technology can improve quality, increase productivity, offer farmers ability classify detect their produce more effectively. for sustainability efficiency industry. In this paper aims application algorithms streamline classification, reducing need labor, time, cost sorting process. study utilized images three different varieties: Giresun, Ordu, Van, comprising dataset 1165 1324 1138 Van hazelnuts. open-access dataset. study, experiments were carried out on determination varieties with BigTransfer (BiT)-M R50 × 1, BiT-M R101 3 R152 4 models. models, including big transfer was employed task involved 3627 nut resulted remarkable accuracy 99.49% model. These innovative methods also lead patentable products devices various industries, thereby boosting economic value country.

Язык: Английский

---

Algorithms for Plant Monitoring Applications: A Comprehensive Review

Algorithms, Год журнала: 2025, Номер 18(2), С. 84 - 84

Опубликована: Фев. 5, 2025

Many sciences exploit algorithms in a large variety of applications. In agronomy, amounts agricultural data are handled by adopting procedures for optimization, clustering, or automatic learning. this particular field, the number scientific papers has significantly increased recent years, triggered scientists using artificial intelligence, comprising deep learning and machine methods bots, to process crop, plant, leaf images. Moreover, many other examples can be found, with different applied plant diseases phenology. This paper reviews publications which have appeared past three analyzing used classifying agronomic aims crops applied. Starting from broad selection 6060 papers, we subsequently refined search, reducing 358 research articles 30 comprehensive reviews. By summarizing advantages applying analyses, propose guide farming practitioners, agronomists, researchers, policymakers regarding best practices, challenges, visions counteract effects climate change, promoting transition towards more sustainable, productive, cost-effective encouraging introduction smart technologies.

Язык: Английский

---

Advancing Legume Quality Assessment Through Machine Learning: Current Trends and Future Directions

Journal of Food Composition and Analysis, Год журнала: 2025, Номер unknown, С. 107532 - 107532

Опубликована: Март 1, 2025

Язык: Английский

---

Deep Learning-Based Classification of Black Gram Plant Leaf Diseases: A Comparative Study

Proceedings of the International Conference on Advanced Technologies, Год журнала: 2023, Номер unknown

Опубликована: Авг. 19, 2023

The escalating incidence of plant diseases presents considerable obstacles to the agricultural domain, resulting in substantial reductions crop yield and posing a threat food security. To address pressing concern Black Gram Plant Leaf Diseases (BPLD), this research endeavors tackle disease classification through application deep learning methodology. approach leverages comprehensive dataset that encompasses Anthracnose, Crinkle, Powdery Mildew, Yellow Mosaic diseases, all which affect black gram crop. By employing advanced technique, we aim contribute valuable insights combat BPLD effectively. Our applies models, including Darknet-53, ResNet-101, GoogLeNet, EfficientNet-B0, classify diseases. Darknet-53 achieved 98.51% accuracy, followed by ResNet-101 (97.51%), GoogLeNet (96.52%), EfficientNet-B0 (77.61%). These findings demonstrate potential for accurate identification, benefiting agriculture. study provides comparative analysis models Disease (BPLD) classification, revealing as superior performers. Implementing these real-world scenarios holds promise early detection intervention, reducing losses. high accuracy signifies significant progress automating recognition, sector.

Язык: Английский

---

Optimizing Anthracnose Severity Grading in Green Beans with CNN-LSTM Integration

Опубликована: Май 24, 2024

Язык: Английский

---

The Effectiveness of Deep Learning Methods on Groundnut Disease Detection

Proceedings of the International Conference on Advanced Technologies, Год журнала: 2023, Номер unknown

Опубликована: Авг. 19, 2023

Early detection of plant diseases in the agricultural sector is considered an important goal to increase productivity and minimize damage. This study deals with use deep learning methods realize automatic leaf peanut plants explicability model heatmap visualizations formed during diseases. In study, a dataset containing 3058 images 5 classes enriched diseased healthy samples leaves was used. The explainability property has also been studied understand why models detect particular disease. decision processes models, which are usually described as "magic box", were visualized method this study. By highlighting pixels that effective detecting visualization, decision-making process tried be made understandable. results show have high performance diseases, obtained by visualization reliable tool for specialists producers. Thanks visual explanations provided model, level confidence increased provided. constitutes step towards increasing efficiency applications providing more efficient approach disease management investigating impact field plants.

Язык: Английский

---

Progressive Expression of Bean Leaf Lesions: A Comprehensive Analysis Using Spatio-Temporal Disease Classification Solutions Based on CNN and LSTM Networks

Опубликована: Фев. 9, 2024

The appearance of Bean leaf lesions can lead to major damage and losses in crop production, requiring innovative approaches for early detection. This study proposes a new hybrid Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) model bean lesion detection, especially the classification severity levels. It is based on highly maintained database with 7000 images representing at different stages. proposed presents high overall accuracy 98.52% which highlights its ability distinguish each four levels – mild, moderate, severe, critical. architecture comprises CNN extract features from spatial awareness LSTM temporal detection that captures how pattern changes over time. evaluation performance parameters such as precision, recall, F1-score helps augment analysis conducted since they provide insights into what works well within further development. addition confusion matrix depicts forecast more specifically classes present where good or needs attention. Not only does this add state-of-the-art disease crops but also contributes towards wider discussion utilizing artificial intelligence applied precision agriculture, reasonable decision making, reliable management.

Язык: Английский

---

An Integrated GoogleNet with Convolutional Neural Networks Model for Multiclass Bean Leaf Lesion Detection

Опубликована: Март 14, 2024

Язык: Английский

---