Abstract
SummaryThe development of ultrafast detectors for electron microscopy (EM) opens a new door to exploring dynamics of nanomaterials; however, it raises grand challenges for big data processing and storage. Here, we combine deep learning and temporal compressive sensing (TCS) to propose a novel EM big data compression strategy. Specifically, TCS is employed to compress sequential EM images into a single compressed measurement; an end-to-end deep learning network is leveraged to reconstruct the original images. Owing to the significantly improved compression efficiency and built-in denoising capability of the deep learning framework over conventional JPEG compression, compressed videos with a compression ratio of up to 30 can be reconstructed with high fidelity. Using this approach, considerable encoding power, memory, and transmission bandwidth can be saved, allowing it to be deployed to existing detectors. We anticipate the proposed technique will have far-reaching applications in edge computing for EM and other imaging techniques.
Highlights
Electron microscopy (EM), as one of the most powerful tools nowadays in probing materials’ structure and chemistry, has extensive applications in biology, physics, chemistry, and materials science owing to its high spatial resolution and chemical sensitivity.[1]
Peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) evaluations show that the temporal compressive sensing-deep learning (TCSDL) framework exhibits superior performance over the conventional JPEG compression method
Compressive sensing (CS),28–30as an efficient signal processing technique, has been widely used in EM for data acquisition and reconstruction. It has been wildly used in capturing high-dimensional data, such as videos[31,32,33,34] and hyperspectral images.[35,36,37,38,39,40]
Summary
Electron microscopy (EM), as one of the most powerful tools nowadays in probing materials’ structure and chemistry, has extensive applications in biology, physics, chemistry, and materials science owing to its high spatial resolution and chemical sensitivity.[1] EM provides rich, directly resolved information about the structure and dynamics of phenomena, spanning from the atomic scale to micrometer scale, which are of great fundamental and practical significance to society.[2] Driven by the recent advances in computer science and electron microscopes, EM techniques, especially in situ transmission electron microscopy (TEM),[3,4,5,6,7,8,9,10] electron tomography,[11,12,13,14,15,16,17,18,19,20,21,22] four-dimensional scanning transmission electron microscopy (4D-STEM),[23,24,25] and EM image processing[26,27] become more and more dependent on big data processing and storage. Peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) evaluations show that the temporal compressive sensing-deep learning (TCSDL) framework exhibits superior performance over the conventional JPEG compression method
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
