![[2407.12506] Classification and reconstruction for single-pixel imaging with classical and quantum neural networks](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2407.12506] Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
Summary
This article explores the use of classical and quantum neural networks for single-pixel imaging, demonstrating effective classification and reconstruction techniques with competitive accuracy rates.
Why It Matters
The research highlights advancements in imaging technologies, particularly in challenging spectral ranges where traditional cameras struggle. It underscores the potential of integrating quantum machine learning with classical approaches, paving the way for future innovations in imaging applications.
Key Takeaways
- Single-pixel cameras can effectively image outside the visible spectrum.
- Classical neural networks achieved 96% accuracy on the MNIST dataset, while quantum networks showed competitive results.
- Image reconstruction demonstrated significant challenges for quantum neural networks, indicating areas for future research.
Quantum Physics arXiv:2407.12506 (quant-ph) [Submitted on 17 Jul 2024 (v1), last revised 24 Feb 2026 (this version, v3)] Title:Classification and reconstruction for single-pixel imaging with classical and quantum neural networks Authors:Sofya Manko, Dmitry Frolovtsev View a PDF of the paper titled Classification and reconstruction for single-pixel imaging with classical and quantum neural networks, by Sofya Manko and Dmitry Frolovtsev View PDF HTML (experimental) Abstract:Single-pixel cameras are an effective solution for imaging outside the visible spectrum, where traditional CMOS/CCD cameras have challenges. When combined with machine learning, they can analyze images quickly enough for practical applications. Solving the problem of high-dimensional single-pixel visualization can potentially be accelerated via quantum machine learning, thereby expanding the range of practical problems. In this work, we simulated a single-pixel imaging experiment using Hadamard basis patterns, where images from the MNIST handwritten digit dataset and FashionMNIST items of clothing dataset were used as objects. There were selected 64 measurements with maximum variance (6% of the number of pixels in the image). We created algorithms for classifying and reconstructing images based on these measurements using classical fully-connected neural networks and parameterized quantum circuits. Classical and quantum classifiers showed the best accuracies of 96% and 95% for MNIST and 84% and 81% for Fa...
