Plant Disease Detection and Classification Using Machine Learning Algorithm

The wide scale prevalence of diseases in agricultural crops affects both the production quality and quantity of agricultural products at local to regional scale. More often than not, the diseases remain unidentified causing huge distress to the farmers while threatening national food security. In order to circumvent this problem, early diagnosis of diseases using a fast and reliable method is beneficial. Plant disease identification from images captured by digital cameras is an area of active research. Use of various machine learning algorithms for plant disease classification and the evolution of deep convolutional neural network (CNN) based architectures have further enhanced the plant disease classification accuracy. In this context, an automated computer vision-based plant disease detection and classification scheme from plant and leaf’s photographs will be highly desirable. Although, there exist a few techniques currently used in an adhoc fashion for plant disease detection and/or classification, a systematic study to evaluate their usage and efficacy on actual plant data has largely remained unexplored.The aim of this paper is to evaluate various CNN based state-of-the-art transfer learning architectures like GoogLeNet, AlexNet, VGG16 and ResNet50V2 models for plant disease detection and classification. The models were tested on popular publicly available three plant disease benchmark database such as PlantVillage Dataset, New Plant Disease Dataset and Plant Pathology Dataset. Various validation metrics such as Precision, Recall, F1 score and overall accuracy were used to evaluate the final results of the experiments, which revealed that VGG16 rendered highest accuracy of 96.6%, 98.5% and 89% on the three dataset respectively, outperforming all other state-of-the-art models.

Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's “Zero Hunger,” “Climate Action,” and “Responsible Consumption and Production” sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.

The detection and classification of plant diseases are crucial to ensuring food security and maximizing agricultural productivity. Traditional methods of plant disease identification are time-consuming and labor-intensive, necessitating the adoption of more efficient and accurate techniques. In recent years, advancements in machine learning have led to the development of robust methods for automated plant disease detection. This research paper presents a novel approach for plantdisease detection using Convolutional Neural Networks (CNNs). CNNs have demonstrated exceptional performance in image recognition tasks, making them a promising choice for detecting diseases in plant images. The proposed system utilizes a pre- processed dataset of plant images, comprising both healthy and diseased samples, to train the CNN model. Keywords—Plant disease and detection, convolutional neural networks, deep learning architectures, feature extraction, classifier methods

With the rapid development of precision agriculture and smart agriculture, the need to build an automatic identification and detection system for diseases and insect pests is increasing. Using computers to correctly label plant diseases and insect pests is an important prerequisite for achieving accurate classification of plant diseases and insect pests and ensuring system performance. In order to improve the accuracy of computer classification of plant pests and diseases, this paper proposes an automatic pest identification method based on the Vision Transformer (ViT). In order to avoid training overfitting, the plant diseases and insect pests data sets are enhanced by methods such as Histogram Equalization, Laplacian, Gamma Transformation, CLAHE, Retinex-SSR, and Retinex-MSR. Then use the enhanced data set to train the constructed ViT neural network, so as to realize the automatic classification of plant diseases and insect pests. The simulation results show that the constructed ViT network has a test recognition accuracy rate of 96.71% on the plant disease and insect pest public data set Plant_Village, which is about 1.00% higher than the Plant disease and pest identification method based on traditional convolutional neural networks such as GoogleNet and EfficentNetV2.

To identify the recent advancements in the development of plant disease detection and classification system based on Machine Learning (ML) and Deep Learning (DL) models. In this study, we have collected more than 45 papers published during the year 2017-2020 from the peer-reviewed journals of different databases such as Scopus and Web of Science analogous to the keywords such as plant disease identification, recognition, and classification using ML and DL algorithms. An organized way of analysis of various plant disease classification models has been shown in well-formed tables. In this paper, we have conducted a systematic literature study on the applications of the state-of-the-art ML and DL algorithms such as Support Vector Machine (SVM), Neural Network (NN), K-Nearest Neighbor (KNN), Naïve Bayes (NB), other few popular ML algorithms and AlexNet, GoogLeNet, VGGNet, and other few popular DL algorithms respectively for plant disease categorization. Each stated algorithm is characterized through the corresponding processing methods such as image segmentation, feature extraction, along with the standardized experimental-setup metrics such as total number of training/testing dataset employed, number of diseases under considerations, type of classifier utilized, and the percentage of classification accuracy. This work will be a beneficial resource for researchers to recognize any particular type of plant diseases through data-driven approaches. The development of mobile-based applications using the studied ML/DL approaches will surely increase agricultural productivity.

In recent years, the rapid advancement of computer vision and machine learning techniques has revolutionized the field of agriculture by enabling automated detection and classification of plant diseases. This work presents a comprehensive approach for the efficient segmentation and multi-class classification of heterogeneous plant disease and non-disease images. The proposed methodology combines multi-level thresholding-based filtering, feature ranking, leaf feature segmentation, and ensemble classification to achieve high accuracy in disease recognition. In the initial stage, multi-level thresholding-based filtering is applied to enhance image quality and reduce noise, facilitating more precise disease pattern extraction. Subsequently, feature ranking methods are employed to select the most discriminative features from the pre-processed images. These features play a pivotal role in distinguishing between various plant diseases and healthy leaves. Experimental results on a multi-modal plant disease and non- disease images demonstrate the superiority of our proposed method in terms of accuracy and efficiency.

<span id="docs-internal-guid-01580d49-7fff-6f2a-70d1-7893ec0a6e14"><span>Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68% precision, 99.84% F-1 score, and 99.81% accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases.</span></span>

A review on machine learning and deep learning image-based plant disease classification for industrial farming systems

Traditional plant disease diagnosis methods are mostly based on expert diagnosis, which easily leads to the backwardness of crop disease control and field management. In this paper, to improve the speed and accuracy of disease classification, a plant disease detection and classification method based on the optimized lightweight YOLOv5 model is proposed. We propose an IASM mechanism to improve the accuracy and efficiency of the model, to achieve model weight reduction through Ghostnet and WBF structure, and to combine BiFPN and fast normalization fusion for weighted feature fusion to speed up the learning efficiency of each feature layer. To verify the effect of the optimized model, we conducted a performance comparison test and ablation test between the optimized model and other mainstream models. The results show that the operation time and accuracy of the optimized model are 11.8% and 3.98% higher than the original model, respectively, while F1 score reaches 92.65%, which highlight statistical metrics better than the current mainstream models. Moreover, the classification accuracy rate on the self-made dataset reaches 92.57%, indicating the effectiveness of the plant disease classification model proposed in this paper, and the transfer learning ability of the model can be used to expand the application scope in the future.

In recent years, intelligent plant disease detection has become an essential task in agriculture for ensuring crop health and improving yield. Detection and classification of plant diseases remain a challenging problem due to the vast numbers of plants species worldwide and the numerous diseases that negatively affect crop production. However, existing Deep Learning (DL) methods are used for plant disease detection and classification suffer from overfitting, limited robustness, and lack of interpretability. To overcome these issues, this paper proposes a Hybrid Vision Graph Neural Network with Ontology-Driven Knowledge Graph Embedding (HV-GNN-OKGE) method for effective plant disease detection and classification. The HV-GNN method captures both local and global structural features through isotropic and pyramid layers. While the ontology-driven embedding integrates semantic relationships among plant species, symptoms, and diseases to enrich classification with domain knowledge. The performance of the proposed HV-GNN-OKGE method is evaluated using two publicly available datasets: Plant Leaf Dataset (4,590 images, 22 classes) and PlantVillage (2,052 images, 2 classes) are used for training and evaluation, with preprocessing techniques including augmentation, resizing, and normalization to enhance image quality. Experimental results demonstrate that the proposed HV-GNN-OKGE achieves an accuracy of 99.95%, significantly outperforming existing deep learning models in plant disease detection and classification.

Smart agriculture utilizes modern technologies to increase crop productivity. The productivity of agricultural crops has to be elevated for food security for the ever-increasing global population. The production of agricultural crops is largely affected due to increasing infestation of diseases and pests in addition to abiotic stresses. Early detection and management of diseases hold key to tackling the challenge. The disease pest infestation can be controlled by applying pesticides and insecticides. But numerous negative health effects that have been associated with chemical pesticides have been well documented. The increasing computational technology and recent advances in deep learning have paved the way for rapid disease diagnosis and management. Here we have discussed the automatic detection and classification of plant diseases as well as their severity through Image Processing. The detection of disease and its degree of severity from images is based on colour, texture and shape and gives a fast and accurate solution through the use of smart computational tools. DNNs (Deep Neural Networks) and CNNs (Convolutional Neural Networks) are effective in the detection, recognition and classification of plant diseases towards an automated solution for the large-scale agricultural industry.

The automatic detection, visualization, and classification of plant diseases through image datasets are key challenges for precision and smart farming. The technological solutions proposed so far highlight the supremacy of the Internet of Things in data collection, storage, and communication, and deep learning models in automatic feature extraction and feature selection. Therefore, the integration of these technologies is emerging as a key tool for the monitoring, data capturing, prediction, detection, visualization, and classification of plant diseases from crop images. This manuscript presents a rigorous review of the Internet of Things and deep learning models employed for plant disease monitoring and classification. The review encompasses the unique strengths and limitations of different architectures. It highlights the research gaps identified from the related works proposed in the literature. It also presents a comparison of the performance of different deep learning models on publicly available datasets. The comparison gives insights into the selection of the optimum deep learning models according to the size of the dataset, expected response time, and resources available for computation and storage. This review is important in terms of developing optimized and hybrid models for plant disease classification.

Plant disease detection is a critical task in agriculture, essential for ensuring crop health and productivity. Traditional methods in this context are often labor-intensive and prone to errors, highlighting the need for automated solutions. While computer vision-based solutions have been successfully deployed in recent years for plant disease identification and localization tasks, these often operate independently, leading to suboptimal performance. It is essential to develop an integrated solution combining these two tasks for improved efficiency and accuracy. This research proposes the innovative Plant Disease Localization and Classification model based on Vision Transformer (PDLC-ViT), which integrates co-scale, co-attention, and cross-attention mechanisms and a ViT, within a Multi-Task Learning (MTL) framework. The model was trained and evaluated on the Plant Village dataset. Key hyperparameters, including learning rate, batch size, dropout ratio, and regularization factor, were optimized through a thorough grid search. Early stopping based on validation loss was employed to prevent overfitting. The PDLC-ViT model demonstrated significant improvements in plant disease localization and classification tasks. The integration of co-scale, co-attention, and cross-attention mechanisms allowed the model to capture multi-scale dependencies and enhance feature learning, leading to superior performance compared to existing models. The PDLC-ViT model evaluated on two public datasets achieved an accuracy of 99.97%, a Mean Average Precision (MAP) of 99.18%, and a Mean Average Recall (MAR) of 99.11%. These results underscore the model's exceptional precision and recall, highlighting its robustness and reliability in detecting and classifying plant diseases. The PDLC-ViT model sets a new benchmark in plant disease detection, offering a reliable and advanced tool for agricultural applications. Its ability to integrate localization and classification tasks within an MTL framework promotes timely and accurate disease management, contributing to sustainable agriculture and food security.

Plant phenotyping and Precision agriculture are information- and technology-oriented fields with specific challenges and demands for the detection and diagnosis of plant disease. Precision agriculture can be referred as a crop management method related to the spatial and temporal variability in soil and crop factors within a field. Accurate and early diagnosis and detection of plant diseases were major factors in plant production and the reduction in quantitative and qualitative losses in crop yield. Advancement of automatic disease detection and classification system is significantly explored in precision agriculture. In recent times, research workers have investigated numerous cultures leveraging dissimilar parts of a plant. This article develops a new Deep Learning-based Automated Plant Disease Detection and Classification (DL-APDDC) Model for Precision Agriculture. The presented DL-APDDC algorithm concentrates on the recognition and classification of plant diseases in leaf and fruit regions. In the initial stage, the leaf and fruit regions are extracted by the use of U2Net-based background removal. Next, the Adam optimizer with SqueezeNet model is exploited as feature extractor, and the hyperparameters are tuned by Adam optimizer. Finally, the extreme gradient boosting (XGBoost) classifier performs classification of plant diseases. The experimental validation of the DL-APDDC technique is tested on benchmark plant disease dataset. The simulation values indicated the enhanced outcomes of the DL-APDDC approach over other models.

The agricultural production rate plays a pivotal role in the economic development of a country. However, plant diseases are the most significant impediment to the production and quality of food. The identification of plant diseases at an early stage is crucial for global health and wellbeing. The traditional diagnosis process involves visual assessment of an individual plant by a pathologist through on-site visits. However, manual examination for crop diseases is restricted because of less accuracy and the small accessibility of human resources. To tackle such issues, there is a demand to design automated approaches capable of efficiently detecting and categorizing numerous plant diseases. Precise identification and classification of plant diseases is a tedious job due because of the occurrence of low-intensity information in the image background and foreground, the huge color resemblance in the healthy and diseased plant areas, the occurrence of noise in the samples, and changes in the position, chrominance, structure, and size of plant leaves. To tackle the above-mentioned problems, we have introduced a robust plant disease classification system by introducing a Custom CenterNet framework with DenseNet-77 as a base network. The presented method follows three steps. In the first step, annotations are developed to get the region of interest. Secondly, an improved CenterNet is introduced in which DenseNet-77 is proposed for deep keypoints extraction. Finally, the one-stage detector CenterNet is used to detect and categorize several plant diseases. To conduct the performance analysis, we have used the PlantVillage Kaggle database, which is the standard dataset for plant diseases and challenges in terms of intensity variations, color changes, and differences found in the shapes and sizes of leaves. Both the qualitative and quantitative analysis confirms that the presented method is more proficient and reliable to identify and classify plant diseases than other latest approaches.