Abstract In digital image processing, feature extraction occupies a very important position, which is related to the effect of image classification or recognition. At present, effective quantum feature extraction methods are relatively lacking. And the current feature extraction methods are mainly devoted to the extraction of basic features of images, failing to consider the global features of classical images and the global features of quantum images comprehensively. In this paper, we propose a dual quantum image feature extraction method named PSQIFE, which focuses on the global energy representation of images by constructing dual quantum image global features. The representation of the global features of the dual quantum image is obtained by quantum superposition of two parts of quantum state features. In this paper, quantum image reconstruction and quantum image fidelity tests are performed on the extracted global features by 9 classes of classical images, and the overall fidelity is above 95%. In addition, the effectiveness of PSQIFE dual quantum image feature extraction method is verified by comparing the image classification test with convolutional feature extraction method on Mnist dataset. The method has some reference significance for the research of quantum image feature extraction and classification.
Abstract In digital image processing, feature extraction occupies a very important position, which is related to the effect of image classification or recognition. At present, effective quantum feature extraction methods are relatively lacking. And the current feature extraction methods are mainly devoted to the extraction of basic features of images, failing to consider the global features of classical images and the global features of quantum images comprehensively. In this paper, we propose a dual quantum image feature extraction method named PSQIFE, which focuses on the global energy representation of images by constructing dual quantum image global features. The representation of the global features of the dual quantum image is obtained by quantum superposition of two parts of quantum state features. In this paper, quantum image reconstruction and quantum image fidelity tests are performed on the extracted global features by 9 classes of classical images, and the overall fidelity is above 95%. In addition, the effectiveness of PSQIFE dual quantum image feature extraction method is verified by comparing the image classification test with convolutional feature extraction method on Mnist dataset. The method has some reference significance for the research of quantum image feature extraction and classification.
Quantum neural networks (QNNs) are becoming increasingly recognized as a viable method for addressing complex challenges in image classification. Feature extraction is a vital component in digital image processing since it significantly impacts the accuracy and success of picture classification and identification tasks. Nevertheless, there is a conspicuous absence of efficient quantum feature extraction methods, as current approaches mostly concentrate on rudimentary picture features rather than thoroughly addressing both the overall characteristics of classical and quantum images. In order to fill this need, this research study presents a new and innovative method for extracting image features termed image global features (IGF), which focuses on representing the overall energy of images by creating dual quantum image global features. This method utilizes the quantum superposition of two quantum state characteristics to depict the overall characteristics of two quantum images. The suggested method underwent thorough testing using quantum picture reconstruction and fidelity assessments on nine categories of classical images, resulting in an overall fidelity over 97%. Moreover, the efficacy of the IGF technique is confirmed by contrasting its performance in picture categorization assignments with the convolutional feature extraction technique on the MNIST dataset, showcasing its better capabilities.
Image classification is a fundamental task in computer vision. Although classical convolutional neural networks are particularly effective at extracting local spatial features, they are inherently limited in their ability to capture global frequency-domain information. To address this limitation, this paper introduces a hybrid model that couples a classical convolutional feature extraction branch with a quantum feature extraction branch built upon the quantum Fourier transform. The quantum branch maps the input into a low-dimensional representation and processes it through a sequence of quantum encoding, the quantum Fourier transform, a variational quantum circuit, and the inverse quantum Fourier transform; the resulting quantum features are concatenated with the classical features and jointly used for the final classification. Ablation studies quantify the individual contribution of each quantum component, and systematic experiments on the MNIST, Fashion-MNIST, and CIFAR-10 benchmark datasets, conducted over multiple independent random seeds on a strictly held-out test set, show that the complete architecture consistently outperforms its purely classical counterparts. All results and comparative analyses are presented in the experimental section.
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.
Classical images are converted into quantum image representations before quantum image classification. Reducing the number of input qubits is critical in quantum neural network (QNN)–based image classification since it reduces the search space of optimal solution during training. Thus, this paper proposes an image classification method using quantum neural networks. Multiple discriminant analysis (MDA) extracts task-aware image features for classification. The proposed shallow quantum neural network-based model exhibits higher classification accuracy with a small number of parameters. Experimental results show that the proposed method achieves higher 4-, 6-, 8-, and 10-class classification accuracy despite using a small number of input qubits and a small number of parameters on the MNIST dataset, being compared with the existing quantum-based method and CNN-based method.
Creating and using quantum algorithms that might perform better than those of conventional computers is the aim of the emerging field of quantum research. QIP has attracted a lot of interest in the last decade. However, the lack of the quantum feature extraction method limits the interpretation of quantum images. FE is the process of extracting relevant details from raw data. Feature extraction is a crucial component of DIP since it significantly affects the accuracy and efficacy of image identification and classification tasks. Features are essential in the field of image processing. It makes it possible for the content of the photographs to be represented as accurately as possible. Before features are obtained, the image is subjected to a variety of image processing procedures, including scaling, filtering, and grey conversion. The features that will be useful for image recognition and classification are then obtained using feature extraction techniques. The purpose of this study was to demonstrate how well the feature extraction technique can be applied to attain high algorithm performance, which in turn improves performance metrics: mean, skewness, contrast, standard deviation, and root mean square error with 125, 4.60, 0.35, 33, and 0.55. This article explains raw data image preprocessing and the quantum feature technique. The results show how effective and superior the proposed method is. We wrap up by providing an overview of this work, pointing out some important discoveries, and outlining potential directions for further research.
Convolutional Neural Networks (CNNs) have exposed robust results for classifying images in data analytics. On the other hand, the effectiveness of these models is often limited by their substantial computational complexities, particularly when dealing with features represented in complex mathematical environments, multi class image classification, and especially when dealing with complex nonlinear relationships between features, which need to be addressed for transparent decision-making processes. This study developed a Quantum-Enhanced Convolutional Neural Network (Q-CNN) model, which incorporates traditional convolution-based feature extraction, Quantum Feature Encoding, and quantum processing. The developed model applies a quantum encoding mechanism to map classical features to quantum states for alternative feature representations and classification purposes. Experimental results show that the Q-CNN outperformed the standard CNN, reaching 97% training and validation accuracy compared to 94%, and lowering training and validation losses from 17% and 18% to 9% and 11%, respectively. Furthermore, precision, recall, and F1-score were increased from 90%, 88%, and 89% to 92%, 94%, and 93%, respectively. These findings demonstrate the potential effectiveness of quantum feature encoding for image classification tasks and provide a structured framework for enriched feature representation in convolution-based image processing models.