Transfer learning-based deep ensemble neural network for plant leaf disease detection

Agricultural development is a critical strategy for promoting prosperity and addressing the challenge of feeding nearly 10 billion people by 2050. Plant diseases can significantly impact food production, reducing both quantity and diversity. Therefore, early detection of plant diseases through automatic detection methods based on deep learning can improve food production quality and reduce economic losses. While previous models have been implemented for a single type of plant to ensure high accuracy, they require high-quality images for proper classification and are not effective with low-resolution images. To address these limitations, this paper proposes the use of pre-trained model based on convolutional neural networks (CNN) for plant disease detection. The focus is on fine-tuning the hyperparameters of popular pre-trained model such as EfficientNetV2S, to achieve higher accuracy in detecting plant diseases in lower resolution images, crowded and misleading backgrounds, shadows on leaves, different textures, and changes in brightness. The study utilized the Plant Diseases Dataset, which includes infected and uninfected crop leaves comprising 38 classes. In pursuit of improving the adaptability and robustness of our neural networks, we intentionally exposed them to a deliberately noisy training dataset. This strategic move followed the modification of the Plant Diseases Dataset, tailored to better suit the demands of our training process. Our objective was to enhance the network's ability to generalize effectively and perform robustly in real-world scenarios. This approach represents a critical step in our study's overarching goal of advancing plant disease detection, especially in challenging conditions, and underscores the importance of dataset optimization in deep learning applications.

Chapter 2 - Current status of plant diseases and food security

Among the major occupational sectors around the world, agriculture has the highest level of involvement. Every year, this sector faces a substantial loss in production and profit due to a large number of diseases in crops and plants. If those diseases are not detected early and taken measures for prevention, it can bring about a devastating result that can financially burden agriculture personnel. Traditional methods of detecting diseases in plants and crops offer high accuracy. However, the procedure is time-consuming, which might be insidious in most cases. Crop diseases need to be detected and cured as soon as possible as most diseases are highly contagious among crops and plants. In this paper, we have used the transfer learning approach with three pre-trained models: EfficientNetV2L, MobileNetV2, and ResNet152V2, to detect various plant diseases. We have proposed a framework to detect 38 types of leaf diseases in 14 different plants, compared the three pre-trained models based on various quantitative performance evaluation parameters, and demonstrated that EfficientNetV2L performed best with 99.63% accuracy. In the end, Explainable Artificial Intelligence (XAI) technique: LIME has been implemented in our model to understand the insight view of the model EfficeintNetV2L's for such prediction. It is used to make our model's predictions more reliable and gives a clear explanation about the reason of such decision.

Plant diseases have a direct impact on the productivity of crops, and therefore the early detection of diseases is crucial.

A review on automated plant disease detection: motivation, limitations, challenges, and recent advancements for future research

The agricultural sector contributes significantly to the gross domestic product of emerging nations. One of the primary factors that reduce agricultural productivity is plant diseases. Detecting plant diseases is a crucial step requiring attention for a productive economy and agriculture. Traditional techniques of crop disease detection are laborious and time-consuming, requiring a great deal of skill and effort. Academicians, researchers and practitioners have recently shown a great interest in the new area of automatic plant disease identification. As soon as they arise on plant leaves, early detection of plant diseases can be aided by machine learning (ML) and deep learning (DL). A comprehensive analysis has been conducted in this review paper to assess the viability to identify plant diseases applying machine learning models. This paper also considers the illnesses and viruses that affect different crops: black gram, chickpea, mungbean and potato. A detailed procedure has been done to recognise and classify plant diseases. The analysis of various ML and DL algorithms adopted by researchers to classify diseases has been explained. Finally, challenges are highlighted to recognise and classify plant diseases utilising ML and DL algorithms, particularly in legume crops. Developing and integrating real-time datasets on plant diseases using advanced models is the future for monitoring, detecting and managing plant ailments.

Agricultural production is one of the main sources of income in most countries. Enormous losses will be incurred if agricultural product is disturbed by plant disease. The key to reduce losses in agricultural product output and quantity is early detection of plant diseases. A diseased plant usually reflecting its disease by showing symptoms on its leaves. A potato leaf disease classification technique by using image processing and artificial neural network method is proposed in this study. The method can be used to determine the potato leaf is either healthy or diseased. With the aid of this technique, farmers can save time and cost in their farming activities. The main goal of this study is to detect potato plant (Solanum tuberosum L.) disease using image processing techniques. The K-Means clustering algorithm is used to segment the disease in potato leaf image. The segmented features of potato leaf disease are then extracted by using Gray Level Co-occurrence Matrix (GLCM) and these features are then fed into ANN for classification. With the proposed system, classification accuracy obtained is 94%.

<p class="Normal1">Medicinal plants have been found and utilized in traditional medical practices from ancient times. Many medicinal plants play a vital role in curating many life threatening diseases. Very few of the medicinal herbs are commercially cultivated. Many plant diseases are there which destroys these medicinal plants. Early detection of plant diseases can prevent the huge loss of these medicinal plants. Here, we presented a hybrid model that makes use of SVM along with the traditional convolutional neural network (CNN) for predicting <em>Basil</em> plants leaves diseases. We transformed the conventional CNN model by adding a classification layer Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) after feature extraction and this approach tends to perform better than traditional CNN as we make the dataset balanced by data augmentation and SVN and KNN tend to perform better in case of balanced samples. CNN is used for training, SVM/KNN is used for classification. The advantages of CNN and SVM are used in proposed the CNN and SVM and KNN model. It is assumed that such a combined model would incorporate the benefits of CNN and SVM. Here, we identified the four types of diseases that affect <em>basil</em> plant leaves as Leaf spot, Downy mildew, Fusarium wilt, Fungal, and Healthy. Since there isn’t a standard dataset for <em>basil</em> leaves, we created our own 803 picture data set and used various machine learning techniques to train and evaluate the model. However, over other existing algorithms, our hybrid model i.e., CNN+SVM has produced more accurate results. For five classes of <em>basil</em> plant leaves, the proposed model produced 95.02% accuracy of for leaf diseases.</p>

Early detection of plant disease is a challenging research topic in crop protection and precision agriculture. Progress in remote sensing, embedded sensors and AI has enabled researchers to develop innovative data processing algorithms and models to predict plant disease symptoms. However, continuous research is required to update and develop new solutions for detecting plant disease early in the infection. It requires extensive experimentation and timelapse collection of data with different imaging sensors, platforms, plant samples, and environmental conditions before developing a robust model. This paper proposes a conceptual design of an apparatus that can be used for data collection from different imaging sensors to perform high-throughput phenotyping and analysis for early plant disease diagnosis. The paper includes two different design concepts for two distinct scenarios of data collection, 1. on-field standalone device; and 2. laboratory desktop apparatus. Each design is explained with various operational and technical considerations, an electronic block diagram and a mechanical 3D sketch. The paper aims to provide a generic design of an apparatus to enable researchers worldwide to carry out phenotypic studies and develop innovative solutions to benefit the end-user, i.e., the farmer, and reduce global economic and environmental losses.

Plant diseases have a huge impact on agricultural productivity and global food security. Rapid Identification and timely control of these diseases are crucial in order to reduce yield loss. During recent years deep learning techniques have demonstrated very promising results with regard to automating the detection of plants diseases from leaf images. Transfer learning, one of the popular approaches of deep learning, has been extensively employed to leverage large scale pre trained models and adapt them to new tasks with limited data. This paper presents a study on the application of transfer learning in the detection of plant leaf conditions diseases. A transfer learning approach is proposed where a pre trained convolutional neural. The purpose of this is fine-tuning a CNN model on plant-leaf images for the classification of various diseases.

Abstract. Plant diseases are a critical barrier to agricultural sustainability, contributing to annual crop losses of 30–40% in some regions. Such diseases arise from diverse pathogens, including fungi, bacteria, and viruses, and can severely degrade crop yield and quality if undetected. Early diagnosis is crucial for timely intervention, reduced pesticide use, and long-term soil health. Traditional approaches, which rely on manual visual inspection of leaves, remain slow, subjective, and impractical for monitoring large or remote farms. In recent years, the convergence of artificial intelligence (AI), computer vision, and image-based analysis has enabled automated disease detection systems that are both scalable and real-time. Classical techniques first employed color, texture, and shape descriptors combined with machine learning models such as Support Vector Machines (SVM), k-Nearest Neighbor (KNN), and Random Forests. These methods achieved moderate success but struggled with variability in lighting, background, and leaf orientation. The introduction of deep learning, particularly Convolutional Neural Networks (CNNs), transformed plant disease detection by allowing end-to-end feature learning directly from raw images. Modern lightweight architectures like MobileNet and EfficientNet further enhance deployability on mobile and edge devices. In parallel, segmentation-assisted and hybrid models improve robustness under complex field conditions. This review consolidates these developments, evaluating methods in terms of accuracy, generalization, computational efficiency, and field-readiness. It also identifies persistent challenges—such as limited annotated datasets and the opaque decision-making of deep models—and highlights future directions in explainable AI, multi-modal sensing, and IoT-integrated precision agriculture.

Application of Artificial intelligence (AI) in agriculture sector plays an important role to enhance the yields by predicting and detecting the plant diseases and improving health of the crop. The early detection of plant diseases is crucial and helpful to the farmers to minimize the crop loss and ensure healthy crop. However, the traditional manual methods, are time consuming, error-prone, and inefficient for large-scale farming. Adopting recent technologies in Artificial Intelligence (AI) and Deep Learning, particularly Convolutional Neural Networks (CNNs) in the recent years have revolutionized the automation process of plant disease detection. However, singlemodal approaches depend on only RGB images often fail to capture critical physiological and biochemical changes in plants. To overcome these limitations, we propose a Single-Stream CNN in Multi-Modal Plant Disease Detection, integrating RGB, thermal, and hyperspectral imaging into a unified model. Unlike traditional multistream architectures that increase computational complexity, our model processes multi-modal data as a single 4-channel input tensor, optimizing feature fusion while maintaining computational efficiency. The proposed architecture, based on a Modified VGG-16 CNN model, which enhances disease detection accuracy by leveraging complementary information from different imaging modalities. Experimental evaluations demonstrate significant improvements in classification accuracy compared to RGB-only models. Furthermore, our model is optimized for real-time deployment on edge computing devices, making it scalable for precision agriculture applications, including automated greenhouse monitoring, drone-based crop surveillance, and IoTintegrated farming systems. This research work highlights the transformative potential of AI-driven multi-modal plant disease detection, flagging the way for more efficient, cost-effective, and scalable agricultural solutions.

In agriculture, early detection of plant diseases is essential to avoid irretrievable damage to crops. However, accurate plant disease diagnosis is usually performed by professionals with high precision instruments which is both expensive and time consuming. To tackle this problem, an image recognition method based on multiple classifier integration is described. The method is composed of three parts. Firstly, a public dataset of diseased and healthy plant leaves is adopted. Secondly, three types of convolutional neural network (CNN) models are fine tuned to classify different diseases of plants and evaluated separately. Finally, the three models are integrated and evaluated for accurately diagnosing plant diseases. Experiment result shows the correctness and efficiency of the approach with a best accuracy of 99.92% on split test set.

Plant diseases have the potential to damage the livelihoods of farmers and impede their capacity to generate an adequate quantity of food. Diagnosis and early detection of plant diseases are critical for their effective management and control. Leaf analysis shows great potential as a method for forecasting disease stages due to its ability to detect subtle alterations in leaf physiology and appearance that may occur prior to the onset of conspicuous symptoms. By utilizing the algorithms of machine learning and deep learning, it is possible to classify characteristics extracted from photographs of leaves into distinct disease stages. Recent studies have demonstrated the potential of these algorithms, as they have achieved remarkable accuracy in disease stage prediction despite having limited training data. The integration of machine learning and deep learning techniques with foliage analysis holds promise for revolutionizing plant disease management through the provision of timely identification, accurate diagnosis, and customized treatment. In order to formulate efficacious disease management strategies, precise determination of the developmental stage of plant diseases is imperative. Scholars are presently devising novel approaches to identify the stages of plant diseases by employing diverse methodologies, including spectroscopy, machine learning, and image processing. This can benefit producers in substantial economic and environmental ways, as well as contribute to the improvement of food security. The primary investigation comprises an assortment of articles spanning the years 2014 to 2023. After evaluating various search strategies, a total of 117 research publications were identified, of which 43 were pertinent. The article examines numerous developments in deep learning research. In addition, it will facilitate the assessment of the present and prospective state of plant disease research by employing deep learning methodologies.

It is a very difficult task in agriculture to identify crop diseases in a timely and precise manner. Plant diseases are the principal causes of a significant decrease in crop production quality and quantity. In order to prevent damage to the entire plant, early detection of plant diseases is crucial. Numerous deep learning neural network models have been devised to address this issue. However, it requires more computation and consumes more time. This technique seeks to distinguish between a plant’s healthy and diseased leaves. In this study, we've demonstrated how we utilized MATLAB to transform an image into a hex file, and then.hex file is fed as final input in Vivado for classification. This paper proposes an architecture for plant disease detection based on the CNN algorithm, and its implementation on FPGAs (Field Programmable Gate Arrays).