Quantum image processing, as a convergence of quantum computing and image processing, necessitates extensive research into quantum image representations (QIRs), which are among the most significant topics shaping the field of quantum computing (QC) due to their potential opportunities and challenges. This study introduces a novel QIR model based on the hue, saturation, and intensity (HSI) colour model. Our model advances image encoding by uniquely integrating an adjacency matrix to capture spatial pixel relationships with a Fourier transform (FT) representation for pixel intensity. Based on the HSI color space, AFQIRHSI uses a dual-entanglement structure; one state links the adjacency and intensity information, while another efficiently encodes hue and saturation. Named the adjacency Fourier quantum image representation of HSI (AFQIRHSI), this model utilises [Formula: see text] qubits to store a colour digital image of size [Formula: see text]. AFQIRHSI enhances storage capacity by factors of four and two compared to earlier models, such as QIRHSI and EQIRHSI. In this paper, we also present several quantum image operations, including complement colour transformation [Formula: see text], global colour transformation [Formula: see text], quantum image retrieval [Formula: see text], and quantum image detection (QED). Comparative analyses of various quantum image representations are provided, highlighting their similarities and differences. AFQIRHSI offers a robust foundation for advanced quantum image processing applications, particularly in medical imaging and AI-based image classification.

Scientific ReportsNov 17, 20253 citations

QueenNet: Quantum-Enhanced Neural Network for Hyperspectral Image Classification

Qingwang Wang, Shunyuan Wang, Yinxing Zhang +3 more

Hyperspectral image (HSI) classification is a critical task in the field of remote sensing. Existing deep learning models have made significant progress in HSI classification, but often suffer from parameter redundancy and insufficient noise robustness when handling the high-dimensional nonlinear spatial-spectral information. Recently, quantum computing have garnered significant attention in modeling higher-order correlations with remarkable parameter efficiency. Inspired by this, we propose a QUantum-Enhanced nEural Network (QueenNet) for HSI classification. QueenNet comprises three primary modules, including Quantum Encoding (QE), Quantum Convolution (QC), and Quantum Measurement (QM). Specifically, QE maps HSI into an hyper high-dimensional Hilbert space, encoding it as a quantum states. QC performs HSI feature extraction and transformation using quantum circuits composed of parameterized quantum gate sequences, which effectively enhances the model's ability to capture joint spatial-spectral features while suppressing spectral noise. QM introduces nonlinear feature extraction operations and decodes the HSI features of quantum states back into classic interpretable probability distributions for classification. QueenNet effectively alleviate the limitations of existing HSI classification deep learning models by leveraging the high-dimensional feature representation advantages of quantum computing, introducing a novel paradigm to HSI classification. Extensive experiments on three benchmark datasets demonstrate that QueenNet achieves an order-of-magnitude reduction in model parameters while surpassing the classification performance of state-of-the-art methods.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingJan 1, 20262 citations