We present a hybrid image classifier by feature-sensitive image upconversion, single pixel photodetection, and deep learning, aiming at fast processing of high-resolution images. It uses partial Fourier transform to extract the images' signature features in both the original and Fourier domains, thereby significantly increasing the classification accuracy and robustness. Tested on the Modified National Institute of Standards and Technology handwritten digit images and verified by simulation, it boosts accuracy from 81.25% (by Fourier-domain processing) to 99.23%, and achieves 83% accuracy for highly contaminated images whose signal-to-noise ratio is only -17. Our approach could prove useful for fast lidar data processing, high-resolution image recognition, occluded target identification, and atmosphere monitoring.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OL.420388 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Relaxometry and contrast-free cerebral microvascular quantification using balanced steady-state free precession MR fingerprinting.
Magn Reson Med
January 2025
Université Grenoble Alpes, INSERM, U1216, Grenoble Institute Neurosciences, GIN, Grenoble, France.
Purpose: This study proposes a novel, contrast-free Magnetic Resonance Fingerprinting (MRF) method using balanced Steady-State Free Precession (bSSFP) sequences for the quantification of cerebral blood volume (CBV), vessel radius (R), and relaxometry parameters (T , T , T *) in the brain.
Methods: The technique leverages the sensitivity of bSSFP sequences to intra-voxel frequency distributions in both transient and steady-state regimes. A dictionary-matching process is employed, using simulations of realistic mouse microvascular networks to generate the MRF dictionary.
Remote sensing image Super-resolution reconstruction by fusing multi-scale receptive fields and hybrid transformer.
Sci Rep
January 2025
School of Electronics and Information, Xijing University, Xi'an, 710123, China.
To enhance high-frequency perceptual information and texture details in remote sensing images and address the challenges of super-resolution reconstruction algorithms during training, particularly the issue of missing details, this paper proposes an improved remote sensing image super-resolution reconstruction model. The generator network of the model employs multi-scale convolutional kernels to extract image features and utilizes a multi-head self-attention mechanism to dynamically fuse these features, significantly improving the ability to capture both fine details and global information in remote sensing images. Additionally, the model introduces a multi-stage Hybrid Transformer structure, which processes features at different resolutions progressively, from low resolution to high resolution, substantially enhancing reconstruction quality and detail recovery.
View Article and Find Full Text PDFAutomated 3D semantic segmentation of PCB X-ray CT images and netlist extraction.
Sci Rep
January 2025
University of Connecticut, Storrs, CT, USA.
Printed Circuit Board (PCB) design reconstruction is essential for addressing part obsolescence, intellectual property recovery, compliance, quality assurance, and enhancing national capabilities. Traditional methods for PCB design extraction, both non-geometry-based and geometry-based, have limitations in accuracy, efficiency, and scalability. This paper presents an automated approach, combining image processing and machine learning, to achieve 3D semantic segmentation of PCB X-ray Computed Tomography (X-ray CT) images and subsequent netlist extraction.
View Article and Find Full Text PDFUnraveling the Stoichiometric Interactions and Synergism between Ligand-Protected Gold Nanoparticles and Proteins.
J Am Chem Soc
January 2025
Department of Chemical and Biomolecular Engineering, National University of Singapore, 4 Engineering Drive 4, Singapore 117585, Singapore.
Nanomaterials that engage in well-defined and tunable interactions with proteins are pivotal for the development of advanced applications. Achieving a precise molecular-level understanding of nano-bio interactions is essential for establishing these interactions. However, such an understanding remains challenging and elusive.
View Article and Find Full Text PDFLocally Specific Genome-Wide Signatures of Adaptation to Environmental Variation at High Resolution in an Alpine Plant.
Mol Ecol
January 2025
Swiss Federal Research Institute for Forest, Snow and Landscape Research, Birmensdorf, Switzerland.
Microevolutionary processes shape adaptive responses to heterogeneous environments, where these effects vary both among and within species. However, it remains largely unknown to which degree signatures of adaptation to environmental drivers can be detected based on the choice of spatial scale and genomic marker. We studied signatures of local adaptation across two levels of spatial extents, investigating complementary types of genomic variants-single-nucleotide polymorphisms (SNPs) and polymorphic transposable elements (TEs)-in populations of the alpine model plant species Arabis alpina .
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!