Processing Digital media such images is a crucial step for any image classification task such as surface defect detection or any deep learning task which include Digital Media Processing. Ensuring the detail capturing of each and every feature of the input image from each and every pixel is must in order to build a robust system with minimal error or no error. While it may not be possible and causes the struggle for classical computing methods to efficiently capture and process complex patterns and subtle details. Utilising quantum computing for digital image processing gives an advantage over classical methods as it operates on high dimensional space and leverages quantum parallelism to explore numerous possibilities simultaneously. This enable the extraction of more complex features that might be otherwise missed improving the model’s capability to flag defects with greater accuracy and efficiency. Quantum computing’s potential to enhance feature extraction can significantly boost the performance of classification models, leading to dependable and precise surface defect detection.
Processing Digital media such images is a crucial step for any image classification task such as surface defect detection or any deep learning task which include Digital Media Processing. Ensuring the detail capturing of each and every feature of the input image from each and every pixel is must in order to build a robust system with minimal error or no error. While it may not be possible and causes the struggle for classical computing methods to efficiently capture and process complex patterns and subtle details. Utilising quantum computing for digital image processing gives an advantage over classical methods as it operates on high dimensional space and leverages quantum parallelism to explore numerous possibilities simultaneously. This enable the extraction of more complex features that might be otherwise missed improving the model’s capability to flag defects with greater accuracy and efficiency. Quantum computing’s potential to enhance feature extraction can significantly boost the performance of classification models, leading to dependable and precise surface defect detection.
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.
As manufacturing systems advance toward higher throughput, tighter tolerances, and increasingly complex quality requirements, traditional defect detection and quality assurance methods struggle to scale effectively. Quantum Machine Learning (QML) offers a new computational paradigm capable of capturing high-dimensional feature interactions, accelerating pattern recognition, and improving anomaly detection in industrial environments. This study investigates the integration of quantum kernel methods, variational quantum classifiers, and hybrid quantum–classical neural architectures for real-time defect identification across optical, acoustic, and sensor-rich inspection systems. The proposed framework leverages the expressivity of quantum feature spaces to enhance classification fidelity while maintaining compatibility with existing digital manufacturing pipelines. Experimental simulations demonstrate that QML models achieve notable improvements in detecting subtle surface irregularities, micro-defects, and non-linear process deviations when compared to conventional deep learning baselines. These findings underscore the potential of quantum-enhanced analytics to redefine quality assurance strategies in high-throughput manufacturing, enabling earlier defect localization, lower false-negative rates, and more resilient production workflows.
In order to leverage quantum computers for machine learning tasks such as image classification, careful consideration is required: NISQ-era quantum computers have limitations, which include noise, scalability, read-in and read-out times, and gate operation times. Therefore, strategies should be devised to mitigate the impact that complex datasets can have on the overall efficiency of a quantum machine learning pipeline. This may otherwise lead to excessive resource demands or increased noise. We apply a classical feature extraction method using a ResNet10-inspired convolutional autoencoder to both reduce the dimensionality of the dataset and extract abstract and meaningful features before feeding them into a quantum machine learning block. The quantum block of choice is a quantum-enhanced support vector machine (QSVM), as support vector machines typically do not require large sample sizes to identify patterns in data and have short-depth quantum circuits, which limits the impact of noise. The autoencoder is trained to extract meaningful features through image reconstruction, aiming to minimize the mean squared error across a training set. Three image datasets are used to illustrate the pipeline: HTRU-1, MNIST, and CIFAR-10. We also include a quantum-enhanced one-class support vector machine (QOCSVM) for the highly unbalanced HTRU-1 set, as well as classical machine learning results to serve as a benchmark. Finally, the HTRU-2 dataset is also included to serve as a benchmark for a dataset with well-correlated features. The autoencoder achieved near-perfect reconstruction and high classification accuracy for MNIST, while CIFAR-10 showed poorer performance due to image complexity, and HTRU-1 struggled because of dataset imbalance. This highlights the need for a balance between dimensionality reduction through classical feature extraction and prediction performance using quantum methods.
The emergence of deep vision models such as convolutional neural networks and vision transformers has revolutionized computer vision, enabling significant advancements in image classification, object detection, and segmentation. In parallel, the rapid development of quantum computing has spurred interest in quantum machine learning (QML), which integrates the strengths of quantum computation with the representational power of deep learning. In QML, parameterized quantum circuits offer the potential to capture complex image features, define complex decision boundaries, and provide other computational advantages. This paper investigates hybrid quantum-classical vision architectures, with a focus on hybrid quantum-classical convolutional neural networks and hybrid quantum-classical vision transformers. These hybrid models explore both quantum pre-processing and post-processing of data, respectively, where quantum circuits are strategically integrated into the data pipeline to enhance model performance. Our results suggest that these hybrid models can enhance accuracy and computational efficiency in vision-related tasks, even with the constraints of current noisy intermediate-scale quantum devices.
Brain tumor detection is a vital and challenging task in medical diagnosis, requiring highly precise and efficient methods to improve patient treatment outcomes. Traditional approaches rely on classical machine learning and deep learning techniques, which, while effective to a degree, often struggle with capturing the complex and high-dimensional patterns present in medical imaging data. A significant limitation of these conventional methods is their inability to process and analyze intricate features efficiently, which can impact diagnostic accuracy. To address these challenges, this work proposes a novel Quantum Convolutional Neural Network (QCNN) framework that combines quantum computing principles, via quantum circuits, with classical machine learning architectures implemented through tools like PyTorch and PennyLane. This hybrid approach enhances feature extraction and classification capabilities, leading to superior performance. Experimental results demonstrate that the QCNN model achieves an improved accuracy of 90 percent on the test dataset, surpassing traditional methods and showing promise for advancing brain tumor detection technology. This improvement is supported by consistent decreases in training and validation loss during model training, highlighting the robustness and efficacy of the quantum-enhanced model.
Image classification has become a fundamental task in computer vision with applications in areas such as medical imaging, agriculture, environmental monitoring, and automated surveillance. Traditional machine learning techniques have achieved reasonable performance in classification tasks; however, they often struggle when dealing with high-dimensional and complex image datasets. Deep learning models, particularly Convolutional Neural Networks (CNNs), have significantly improved image classification performance by automatically learning hierarchical feature representations. Despite these advancements, classical deep learning models may still face challenges related to computational complexity and large-scale data processing.In recent years, quantum machine learning has emerged as a promising paradigm that combines principles of quantum computing with classical machine learning techniques to enhance computational efficiency and model performance. This study proposes a hybrid quantum–classical framework for image classification that integrates a deep residual network (ResNet-50) with a Quantum Support Vector Machine (QSVM). The ResNet-50 model is employed as a feature extraction mechanism to capture high-level visual representations from image data. The extracted features are then reduced in dimensionality using Principal Component Analysis (PCA) to simplify the feature space and improve computational efficiency.The reduced feature vectors are subsequently classified using a QSVM model that utilizes quantum feature maps to encode classical data into quantum states. Various quantum feature maps are explored to evaluate their impact on classification performance. Experimental results demonstrate that the hybrid quantum–classical approach achieves higher classification accuracy compared to conventional machine learning models such as Support Vector Machines and Random Forest classifiers. The proposed framework highlights the potential of combining classical deep learning architectures with quantum machine learning algorithms to address complex image classification challenges. This hybrid approach provides an efficient and scalable solution for advanced image analysis tasks and demonstrates the growing potential of quantum computing in artificial intelligence applications.