Even though ghost imaging (GI), an unconventional imaging method, has received increased attention by researchers during the last decades, imaging speed is still not satisfactory. Once the data-acquisition method and the system parameters are determined, only the processing method has the potential to accelerate image-processing significantly. However, both the basic correlation method and the compressed sensing algorithm, which are often used for ghost imaging, have their own problems. To overcome these challenges, a novel deep learning ghost imaging method is proposed in this paper. We modified the convolutional neural network that is commonly used in deep learning to fit the characteristics of ghost imaging. This modified network can be referred to as ghost imaging convolutional neural network. Our simulations and experiments confirm that, using this new method, a target image can be obtained faster and more accurate at low sampling rate compared with conventional GI method.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5915577 | PMC |
| http://dx.doi.org/10.1038/s41598-018-24731-2 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
In this study, a novel precise reconstruction method was proposed for ghost imaging. In traditional ghost imaging (TGI), image quality deteriorates in proportion to the ℓ norm of the observed object. However, the proposed method reduces the effective ℓ norm by filtering an unknown direct current component and an arbitrary alternating current component derived from a pre-measured rough image.
View Article and Find Full Text PDFSynthetic aperture X-ray ghost imaging (SAXGI) is proposed to achieve megapixel X-ray ghost imaging together with a reduced number of measurements. As the bucket detector array is artificially generated by post-pixel-binning of the images collected with the same detector as that in the reference arm, the unique advantages of SAXGI are not verified experimentally. In this paper, we developed a systematic solution of the experimental implementation of SAXGI, with the automatic interchange of 2× and 20× optical magnification of the detector for object and reference signal acquisition respectively, together with electronic pixel-binning of the detector.
View Article and Find Full Text PDFGhost holography has attracted notable applied interest in the modern quantitative imaging applications with the futuristic features of complex field recovery in the diversified imaging scenarios. However, the utilization of digital holography in ghost frame works introduces space bandwidth or time bandwidth restrictions in the implementation of the technique in applied domains. Here, we propose and demonstrate a quantitative ghost phase imaging approach with holographic ghost diffraction scheme in combination with the phase-shifting technique.
View Article and Find Full Text PDFSpatial anti-bunching, in contrast to the well-known bunching behavior observed in classical light sources, describes a situation where photons tend to avoid each other in space, resulting in a reduced probability of detecting two or more photons in proximity. This anti-bunching effect, a hallmark of nonclassical light, signifies a deviation from classical intensity fluctuations and has been observed not only in free electrons and entangled photon pairs but also in chaotic-thermal light. This work investigates the generation mechanism of spatial anti-bunching correlation in random light fields, leveraging the wandering of light centers to induce a second-order coherence degree below unity.
View Article and Find Full Text PDFMetallofullerenol Gd@C(OH) preserves human erythrocyte plasma membrane integrity from AAPH-induced oxidative stress: molecular mechanisms and antioxidant activity.
Free Radic Biol Med
January 2025
Department of Oncobiology and Epigenetics, Faculty of Biology and Environmental Protection, University of Lodz, Pomorska 141/143, 90-236 Lodz, Poland; Military Institute of Medicine - National Research Institute, Szaserow 128, 04-141 Warsaw, Poland. Electronic address:
Metallofullerenols and fullerenols have attracted attention due to their remarkable ability to interact with various biologically relevant molecules, paving the way for biomedical applications, ranging from medical imaging techniques to drug carriers, acting with increased efficiency and reduced side effects. In this work, we investigated the effects of two fullerene derivatives, Gd@C(OH) and C(OH), on erythrocyte membrane components under oxidative stress conditions induced by 2,2'-azobis(2-amidinopropane) dihydrochloride (AAPH) as a source of peroxyl radicals. The results demonstrated that gadolinium encapsulation within the fullerene cage enhanced the electron affinity of Gd@C(OH), resulting in stronger antioxidant activity.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!