Abstract - We present a comprehensive study exploring quantum machine learning (QML) approaches for plant disease detection from leaf images and compare them against well-established classical counterparts. Specifically, we implement and analyze Quantum Support Vector Machines (QSVMs) vs classical SVMs, and Quantum Convolutional Neural Networks (QCNNs) vs classical CNNs. Using the widely used PlantVillage and complementary field datasets, we describe image preprocessing, classical baseline architectures, quantum data-encoding strategies, circuit-level QSVM and QCNN designs for near-term quantum devices, and hybrid training procedures. Where possible, we review literature-reported performance and propose a reproducible experimental pipeline for empirical evaluation on simulated/noisy quantum backends. We discuss expected strengths and limitations of quantum approaches (expressivity, kernel advantages, resource constraints), provide detailed evaluation metrics and ablations, and propose directions for real-device experiments and field deployment. Key takeaways: QSVM/quantum-kernel methods can provide superior separability on certain feature maps and small-to-medium-sized datasets, while QCNNs show promise as compact feature extractors for hybrid pipelines — but both approaches currently require careful circuit design and error-mitigation to outperform well-tuned classical models in realistic field settings. Key Words: QCNN, Plant Disease, SVM, CNN, QSVM
Abstract - We present a comprehensive study exploring quantum machine learning (QML) approaches for plant disease detection from leaf images and compare them against well-established classical counterparts. Specifically, we implement and analyze Quantum Support Vector Machines (QSVMs) vs classical SVMs, and Quantum Convolutional Neural Networks (QCNNs) vs classical CNNs. Using the widely used PlantVillage and complementary field datasets, we describe image preprocessing, classical baseline architectures, quantum data-encoding strategies, circuit-level QSVM and QCNN designs for near-term quantum devices, and hybrid training procedures. Where possible, we review literature-reported performance and propose a reproducible experimental pipeline for empirical evaluation on simulated/noisy quantum backends. We discuss expected strengths and limitations of quantum approaches (expressivity, kernel advantages, resource constraints), provide detailed evaluation metrics and ablations, and propose directions for real-device experiments and field deployment. Key takeaways: QSVM/quantum-kernel methods can provide superior separability on certain feature maps and small-to-medium-sized datasets, while QCNNs show promise as compact feature extractors for hybrid pipelines — but both approaches currently require careful circuit design and error-mitigation to outperform well-tuned classical models in realistic field settings. Key Words: QCNN, Plant Disease, SVM, CNN, QSVM
Accurate image classification is vital in smart agriculture, where early detection of plant diseases can boost crop yield and sustainability. While traditional Convolutional Neural Networks (CNNs) perform well, they face computational and scalability issues as dataset sizes grow. To address this, we propose a quantum-enhanced deep learning framework that combines the Quantum Fourier Transform (QFT) for image preprocessing with a Quantum Convolutional Neural Network (QCNN) for classification. QFT transforms images into the frequency domain, highlighting disease-related features and reducing background noise, while QCNN leverages quantum principles like superposition and entanglement for faster and more efficient feature learning. We evaluated four architectures—classical CNN, QCNN, CNN+QFT, and the hybrid QCNN+QFT—on coffee leaf datasets containing 2,000, 5,000, and 12,000 images. Across all dataset sizes, QCNN+QFT consistently achieved the highest accuracy and lowest training times. On the largest dataset, it reached 98.87% accuracy in 25.46 seconds per epoch, compared to the CNN’s 85.13% in 638.39 seconds. For 5,000 images, it achieved 94.78% in 11.30 seconds, outperforming CNN’s 83.42% in 215.57 seconds. Even on 2,000 images, it scored 90.06% in 2.12 seconds versus CNN’s 79.23% in 67.48 seconds. While QCNN and CNN+QFT also improved over the classical CNN, neither matched the hybrid’s superior balance of speed and accuracy, demonstrating its potential for scalable, real-time plant disease detection.
In modern agriculture, high crop yields and food security depend on early and accurate identification of plant diseases. Deep learning (DL) models like convolutional neural networks (CNNs) have successfully classified plant disease using leaf images. Classical models are adequate for small-scale applications but inefficient for large-scale applications because of their high processing requirements and difficulty in handling highdimensional data. To overcome these challenges, this study proposes the Quantum Convolutional Neural Network (QCNN) by leveraging the Cirq library to introduce quantum circuit simulation. The QCNN model is trained on the Kaggle coffee plant dataset and JMuBEN Mendeley. Quantum Fourier transforms (QFT) are used to preprocess the input images for enhanced quality and to find regions of interest (ROI) for disease lesions. The empirical results prove that the QCNN has drastically improved the model's performance in each phase of the epoch when compared with the traditional CNN model. In the training phase, the QCNN accomplished 96.98 %, whereas the CNN achieved 88.95 % for 150 epochs. Similarly, an effective performance is accomplished during the testing phase by QCNN with 95.89% in comparison with the CNN performance of 85.77 %. Hence, this work emphasizes the power of QCNN in faster training and analytical capabilities using entanglement and superposition in the quantum domain.
Recently, there has been growing attention on combining quantum machine learning (QML) with classical deep learning approaches as computational techniques are key to improving the performance of image classification tasks.This study presents a hybrid approach that uses ResNet-50 (Residual Network) for feature extraction and Quantum Support Vector Machines (QSVM) for classification in the context of potato disease detection. Classical machine learning as well as deep learning models often struggle with high-dimensional and complex datasets necessitating advanced techniques like quantum computing to improve classification efficiency.In our research, we use ResNet-50 to extract deep feature representations from RGB images of potato diseases. These features are then subjected to dimensionality reduction using PCA (Principal Component Analysis). The resulting features are processed through QSVM models which apply various quantum feature maps—such as ZZ, Z and Pauli-X to transform classical data into quantum states. To assess the model’s performance we compared it with classical ML such as Support Vector Machine (SVM) and Random Forest (RF) using 5-fold stratified cross-validation for a comprehensive evaluation. The experimental results demonstrate that the Z-feature map-based QSVM outperforms classical models achieving an accuracy of 99.23% surpassing both SVM and RF models.This research highlights the advantages of integrating quantum computing into image classification and also provides disease detection solution into the potential of hybrid quantum-classical model.
This paper presents a systematic empirical benchmarking of quantum machine learning (QML) applications within the under-explored domain of agricultural image classification. The authors implement and evaluate four hybrid quantum-classical architectures—including variational quantum classifiers (VQC), quanvolutional neural networks (QNN), and a ResNet-50 combined with a Quantum Support Vector Machine (QSVM)—against a purely classical EfficientNet baseline. The architectures are tested on three agricultural disease datasets: potato tuber disease, jujube insect pests, and paddy leaf rust. The experimental findings reveal that the ResNet-50+QSVM hybrid model achieves the optimal balance of classification accuracy and training stability, reaching a 93.4% mean accuracy. Crucially, the hybrid QSVM demonstrates extreme sample efficiency by requiring 41% fewer labeled training samples than the classical EfficientNet baseline to cross a 90% accuracy threshold, showing the capability of quantum feature maps in low-data regimes.
Abstract Well-known quantum machine learning techniques, specifically quantum kernel-assisted support vector machines (QSVMs) and quantum convolutional neural networks (QCNNs), are applied to the binary classification of pulsars. In this comparative study, it is illustrated with simulations that both quantum methods successfully achieve effective classification of the HTRU-2 data set that connects pulsar class labels to eight separate features. While QCNNs are superior in terms of training and prediction speed compared to QSVMs, the preference shifts toward QSVMs when the present noisy NISQ-era devices are incorporated into the comparison. QSVMs demonstrate superior overall performance compared to QCNNs when assessed using binary classification performance metrics. Classical methods are implemented to serve as a benchmark for comparison with the quantum approaches.
Detecting plant diseases is a crucial component of precision agriculture, necessary for maintaining economic viability, sustainable farming practices, food security, and preventing economic losses. Deep learning models such as Capsule Attention Networks, DenseNets, and Convolutional Neural Networks have demonstrated state-of-the-art performance in leaf-image-based disease classification. However, large-scale practical implementation in resource-constrained environments remains challenging due to overfitting, environmental insensitivity, extended training times, and high computational cost, along with the absence of a sustainable framework for real-world deployment. Emerging quantum neural networks (QNNs), integrated with quantum-influenced optimization algorithms, offer promising avenues to enhance practical applicability. Their capabilities for high-dimensional feature mapping, entanglement, and superposition improve generalization and convergence in hybrid models that combine quantum layers with classical architectures. Incorporating quantum modules into DenseNets, attention mechanisms, capsule networks, and other hybrid systems may further enhance accuracy, enable robust disease segmentation, and reduce training time. Nonetheless, challenges remain regarding real-time deployment on edge devices, efficient data encoding, limited explainability of quantum-driven features, and hardware constraints. This survey reviews classical, hybrid, and quantum-enhanced approaches, provides comparative insights, and identifies research gaps toward developing scalable, interpretable, and dependable frameworks for plant disease detection and diagnosis.