Detection and identification of plant leaf diseases using YOLOv4

Frontiers in Plant Science, Год журнала: 2024, Номер 15

Опубликована: Апрель 22, 2024

Detecting plant leaf diseases accurately and promptly is essential for reducing economic consequences maximizing crop yield. However, farmers’ dependence on conventional manual techniques presents a difficulty in pinpointing particular diseases. This research investigates the utilization of YOLOv4 algorithm detecting identifying study uses comprehensive Plant Village Dataset, which includes over fifty thousand photos healthy diseased leaves from fourteen different species, to develop advanced disease prediction systems agriculture. Data augmentation including histogram equalization horizontal flip were used improve dataset strengthen model’s resilience. A assessment was conducted, involved comparing its performance with established target identification methods Densenet, Alexanet, neural networks. When dataset, it achieved an impressive accuracy 99.99%. The evaluation criteria, accuracy, precision, recall, f1-score, consistently showed high value 0.99, confirming effectiveness proposed methodology. study’s results demonstrate substantial advancements detection underscore capabilities as sophisticated tool accurate prediction. These developments have significant significance everyone agriculture, researchers, farmers, providing improved capacities control protection.

Язык: Английский

---

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

---

Enhancing Corn Pest and Disease Recognition through Deep Learning: A Comprehensive Analysis

Agronomy, Год журнала: 2023, Номер 13(9), С. 2242 - 2242

Опубликована: Авг. 27, 2023

Pests and diseases significantly impact the quality yield of maize. As a result, it is crucial to conduct disease diagnosis identification for timely intervention treatment maize pests diseases, ultimately enhancing economic efficiency production. In this study, we present an enhanced pest model based on ResNet50. The objective was achieve efficient accurate diseases. By utilizing convolution pooling operations extracting shallow-edge features compressing data, introduced additional effective channels (environment–cognition–action) into residual network module. This step addressed issue degradation, establishes connections between channels, facilitated extraction deep features. Finally, experimental validation performed 96.02% recognition accuracy using ResNet50 model. study successfully achieved various including leaf blight, Helminthosporium maydis, gray spot, rust disease, stem borer, corn armyworm. These results offer valuable insights intelligent control management

Язык: Английский

---

A robust and light-weight transfer learning-based architecture for accurate detection of leaf diseases across multiple plants using less amount of images

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

Опубликована: Янв. 11, 2024

Leaf diseases are a global threat to crop production and food preservation. Detecting these is crucial for effective management. We introduce LeafDoc-Net, robust, lightweight transfer-learning architecture accurately detecting leaf across multiple plant species, even with limited image data. Our approach concatenates two pre-trained classification deep learning-based models, DenseNet121 MobileNetV2. enhance an attention-based transition mechanism average pooling layers, while MobileNetV2 benefits from adding attention module layers. deepen the extra-dense layers featuring swish activation batch normalization resulting in more robust accurate model diagnosing leaf-related diseases. LeafDoc-Net evaluated on distinct datasets, focused cassava wheat diseases, demonstrating superior performance compared existing models accuracy, precision, recall, AUC metrics. To gain deeper insights into model’s performance, we utilize Grad-CAM++.

Язык: Английский

---

YOLOv5s-BiPCNeXt, a Lightweight Model for Detecting Disease in Eggplant Leaves

Plants, Год журнала: 2024, Номер 13(16), С. 2303 - 2303

Опубликована: Авг. 19, 2024

Ensuring the healthy growth of eggplants requires precise detection leaf diseases, which can significantly boost yield and economic income. Improving efficiency plant disease identification in natural scenes is currently a crucial issue. This study aims to provide an efficient method suitable for scenes. A lightweight model, YOLOv5s-BiPCNeXt, proposed. model utilizes MobileNeXt backbone reduce network parameters computational complexity includes C3-BiPC neck module. Additionally, multi-scale cross-spatial attention mechanism (EMA) integrated into network, nearest neighbor interpolation algorithm replaced with content-aware feature recombination operator (CARAFE), enhancing model's ability perceive multidimensional information extract multiscale features improving spatial resolution map. These improvements enhance accuracy eggplant leaves, effectively reducing missed incorrect detections caused by complex backgrounds localization small lesions at early stages brown spot powdery mildew diseases. Experimental results show that YOLOv5s-BiPCNeXt achieves average precision (AP) 94.9% disease, 95.0% mildew, 99.5% leaves. Deployed on Jetson Orin Nano edge device, attains recognition speed 26 FPS (Frame Per Second), meeting real-time requirements. Compared other algorithms, demonstrates superior overall performance, accurately detecting diseases under conditions offering valuable technical support prevention treatment

Язык: Английский

---

Research on identification method of peanut pests and diseases based on lightweight LSCDNet model

Phytopathology, Год журнала: 2024, Номер 114(9), С. 2162 - 2175

Опубликована: Май 29, 2024

Timely and accurate identification of peanut pests diseases, coupled with effective countermeasures, is pivotal for ensuring high-quality efficient production. Despite the prevalence diseases in cultivation, challenges such as minute disease spots, elusive nature pests, intricate environmental conditions often lead to diminished accuracy efficiency. Moreover, continuous monitoring health real-world agricultural settings demands solutions that are computationally efficient. Traditional deep learning models require substantial computational resources, limiting their practical applicability. In response these challenges, we introduce LSCDNet (Lightweight Sandglass Coordinate Attention Network), a streamlined model derived from DenseNet. preserves only transition layers reduce feature map dimensionality, simplifying model's complexity. The inclusion sandglass block bolsters features extraction capabilities, mitigating potential information loss due dimensionality reduction. Additionally, incorporation coordinate attention addresses issues related positional during extraction. Experimental results showcase achieved impressive metrics accuracy, precision, recall, Fl score 96.67, 98.05, 95.56, 96.79%, respectively, while maintaining compact parameter count merely 0.59 million. When compared established MobileNetV1, MobileNetV2, NASNetMobile, DenseNet-121, InceptionV3, X-ception, outperformed gains 2.65, 4.87, 8.71, 5.04, 6.32, 8.2%, accompanied by substantially fewer parameters. Lastly, deployed on Raspberry Pi testing application an average recognition 85.36%, thereby meeting operational requirements.

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

---

Drone‐based polarization imaging system for leaf spot severity determination in peanut plants

The Plant Phenome Journal, Год журнала: 2025, Номер 8(1)

Опубликована: Фев. 21, 2025

Abstract In this study, we introduce a new approach for enhancing peanut phenotyping through polarization imaging platform. With leaf spot disease posing significant threats to ( Arachis hypogae L.) crops, our research addresses the need accurate and efficient detection methods. Polarization offers unique advantages over more traditional spectral solutions. correlates strongly with geometric properties of an object, such as surface roughness or its orientation relative sensor light source. Leveraging drone‐based system, conducted extensive field trials, collecting approximately 30,184 images two growing seasons locations. Images were processed panchromatic (400–800 nm wavelengths) degree linear (DOLP) compared conventional red, green, blue (RGB) imagery against visual severity scores (modified nine‐point scale). Results indicated that when attempting determine ground truth infection severity, DOLP alone provided 1.34 root mean square error, RGB 1.09 error accuracy, both modalities 1.03 indicating adding capability can enhance augment scoring pipelines. We expect may allow phenotypic models mitigate—or leverage—confounding factors related leaf's without 3D imaging.

Язык: Английский

---

Intelligent Plant Disease Diagnosis Using Deep Neural Networks

Lecture notes in electrical engineering, Год журнала: 2025, Номер unknown, С. 419 - 428

Опубликована: Янв. 1, 2025

---

Application of artificial intelligence for identification of peanut maturity using climatic variables and vegetation indices

Precision Agriculture, Год журнала: 2025, Номер 26(3)

Опубликована: Апрель 4, 2025

Язык: Английский

---