Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “image compression”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Identifying Outliers in AI-based Image Compression

Image compression using artificial intelligence (AI) is becoming increasingly prevalent across various fields, including scientific research. Scientific instruments can generate hundreds of images per second, and effectively compressing these images with high compression ratios is crucial for facilitating scientific discoveries. However, automatically detecting outlier cases, where compression may not have succeeded or where interesting scientific phenomena are present, poses a significant challenge. To address this, we have developed a methodology based on unsupervised machine learning techniques for detecting outlier compressed images. This methodology utilizes metrics such as peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), structural texture similarity index measure (STSIM), and deep image and structural texture similarity index (DISTS). We have evaluated our methodology on several unlabeled datasets, including microscopy and x-ray images, and have successfully identified multiple outlier images using our proposed approach. Furthermore, our approach has enabled us to identify image semantics that are valuable for post-experiment analysis by scientists.

Data Analysis↗
DOE OSTI2023

Out of distribution evaluation for neural image compression

Official code for the NeurIPS 2023 paper "Neural Image Compression: Generalization, Robustness, and Spectral Biases". This code can be used to: - Computing spectral distortion errors of images compressed with traditional codes or neural image compression models (as proposed in the aformentioned paper) - Visualize power spectral densities and fourier heatmaps (as proposed in the aformentioned paper) - Train and test a variety of neural image compression models

Lieberman, KelseyA↗
DOE OSTI2023

Neural Image Compression: Generalization, Robustness, and Spectral Biases

Recent advances in neural image compression (NIC) have resulted in models which are starting to outperform traditional codecs. While this has led to growing excitement about using these methods in real-world applications, the successful adoption of any machine learning system (including NIC) in the wild requires it to generalize (and be robust) to unseen distribution shifts at deployment time. Unfortunately, current research lacks comprehensive datasets and informative tools to evaluate and understand compression performance in real-world settings. To bridge this crucial gap, first, this paper presents a comprehensive benchmark suite to evaluate the out-of-distribution (OOD) performance of image compression methods. Specifically, we design CLIC-C and Kodak-C by introducing 15 common corruptions to popular CLIC and Kodak benchmarks. Next, we propose spectrally inspired introspection tools to gain a deeper understanding of errors introduced by image compression methods as well as their OOD performance. To this end, we carry out a detailed performance comparison of the classical codec with various variants of NIC (e.g., original, variable rate, pruned), revealing intriguing findings that challenge our current understanding of the strengths and limitations of NIC. Finally, we corroborate our empirical findings with theoretical analysis, providing an in-depth view of the OOD performance of NIC. Our benchmarks, spectral introspection tools, and findings provide a crucial bridge to the real-world adoption of NIC. We hope that our work will propel future efforts in designing more robust and generalizable NIC methods.

neural networks, Variational Autoencoder, robustne↗
DOE OSTI2021

Generative Patch Priors for Practical Compressive Image Recovery

In this work, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a pre-trained generator, GPP can recover a wide variety of natural images using a pre-trained patch generator. Additionally, GPP retains the benefits of generative priors like high reconstruction quality at extremely low sensing rates, while also being much more generally applicable. We show that GPP outperforms several unsupervised and supervised techniques on three different sensing models – linear compressive sensing with known, and unknown calibration settings, and the non-linear phase retrieval problem. Finally, we propose an alternating optimization strategy using GPP for joint calibration-and-reconstruction which performs favorably against several baselines on a real world, uncalibrated compressive sensing dataset. The code and models for GPP are available on github.

compressed sensing↗
DOE OSTI2020

Generalized Optimization of High-Capacity Compressive Imaging Systems

One of the greatest challenges in applying compressive sensing (CS) signal processing techniques to electromagnetic imaging applications is designing a sensing matrix that has good reconstruction capabilities. Compressive reflector antennas (CRAs) are a class of antennas that have been shown to provide enhanced image reconstruction performance over traditional reflector antennas (TRAs) when CS techniques are employed. In this article, we present a unified CRA design method, which considers both the sensing capacity and efficiency of the antenna and can be used for both compressive imaging and multiple-input multiple-output (MIMO) communication applications. The unified design method is assessed for a CRA configuration in which dielectric scatterers are added to the surface of a TRA. The design results demonstrate the ability of the unified design method to enhance the CS reconstruction capabilities of the CRA.

42 ENGINEERING↗
DOE OSTI2020

A Resonant Metamaterial Line Array for Ultrasound Compressive Imaging

Abstract Acoustic metamaterials have been proposed for numerous applications including subwavelength imaging, impedance matching, and lensing. Yet, their application in compressive sensing and imaging has not been fully investigated. When metamaterials are used as resonators at certain frequencies, they can generate random radiation patterns in the transmitted waves from the transducers and received waves from a target. Compressive sensing favors such randomness inasmuch as it can increase incoherence by decreasing the amount of mutual information between any two different measurements. This study aims at assessing whether the use of resonating metamaterial unit cells in a single-layered non-optimized array between a number of ultrasound transceivers and targets can improve the sensing capacity, point-spread function of the sensing array (their beam focusing ability), and imaging performance in point-like target detection. The theoretical results are promising and can open the way for more efficient metamaterial designs with the aim of enhancing ultrasound imaging with lower number of transceivers compared to the regular systems.

Acoustics↗
DOE OSTI2021

GPU-based Image Compression for Efficient Compositing in Distributed Rendering Applications

Visualizations of large-scale data sets are often created on graphics clusters that distribute the rendering task amongst many processes. When using real-time GPU-based graphics algorithms, the most time-consuming aspect of distributed rendering is typically the com-positing phase - combining all partial images from each rendering process into the final visualization. Compo siting requires image data to be copied off the GPU and sent over a network to other processes. While compression has been utilized in existing distributed rendering compositors to reduce the data being sent over the network, this compression tends to occur after the raw images are transferred from the GPU to main memory. In this paper, we present work that leverages OpenGL / CUDA interoperability to compress raw images on the GPU prior to transferring the data to main memory. This approach can significantly reduce the device-to-host data transfer time, thus enabling more efficient compositing of images generated by distributed rendering applications.

Lipinksi, Riley↗
DOE OSTI2024

Integrated photonic encoder for low power and high-speed image processing

Abstract Modern lens designs are capable of resolving greater than 10 gigapixels, while advances in camera frame-rate and hyperspectral imaging have made data acquisition rates of Terapixel/second a real possibility. The main bottlenecks preventing such high data-rate systems are power consumption and data storage. In this work, we show that analog photonic encoders could address this challenge, enabling high-speed image compression using orders-of-magnitude lower power than digital electronics. Our approach relies on a silicon-photonics front-end to compress raw image data, foregoing energy-intensive image conditioning and reducing data storage requirements. The compression scheme uses a passive disordered photonic structure to perform kernel-type random projections of the raw image data with minimal power consumption and low latency. A back-end neural network can then reconstruct the original images with structural similarity exceeding 90%. This scheme has the potential to process data streams exceeding Terapixel/second using less than 100 fJ/pixel, providing a path to ultra-high-resolution data and image acquisition systems.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Quantum pixel representations and compression for N-dimensional images

Abstract We introduce a novel and uniform framework for quantum pixel representations that overarches many of the most popular representations proposed in the recent literature, such as (I)FRQI, (I)NEQR, MCRQI, and (I)NCQI. The proposed QPIXL framework results in more efficient circuit implementations and significantly reduces the gate complexity for all considered quantum pixel representations. Our method scales linearly in the number of pixels and does not use ancilla qubits. Furthermore, the circuits only consist of $$R_y$$ R y gates and $$\text {CNOT}$$ CNOT gates making them practical in the NISQ era. Additionally, we propose a circuit and image compression algorithm that is shown to be highly effective, being able to reduce the necessary gates to prepare an FRQI state for example scientific images by up to 90% without sacrificing image quality. Our algorithms are made publicly available as part of , a Quantum Image Pixel Library.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Development of an MEMS ultrasonic microphone array system and its application to compressed wavefield imaging of concrete

Abstract Although contactless ultrasonic wavefield imaging shows potential for effective nondestructive inspection of various engineering materials, it has been rarely applied to concrete materials owing to technical challenges including low signal-to-noise ratio (SNR) caused by inherent heterogeneity of concrete. This paper presents development of a multi-channel MEMS ultrasonic microphone array system and its application to compressed wavefield imaging of concrete materials. The developed multi-channel MEMS ultrasonic microphone array system contains eight MEMS ultrasonic microphone elements and a signal conditioning circuit that enables measurements of ultrasonic signals with high SNR. A compressed sensing approach, based on the multiple measurement vector (MMV) concept, is applied to reconstruct a full dense ultrasonic wavefield data from sparsely sampled ultrasonic wavefield data. Experiments are carried out on a laboratory concrete sample to verify the performance of the developed MEMS microphone array system and proposed compressed sensing approach and then large-scale concrete samples to demonstrate practical application. The experimental results demonstrate that the developed MEMS microphone array system provides high-quality (SNR > 20 dB) ultrasonic data collected from concrete elements; furthermore, the proposed compressed sensing approach provides accurate reconstruction of dense wavefield data, as determined by peak signal-to-noise ratio (PSNR), from sparsely measured wavefield data with compression ratios up to 85% and PSNR above 25 dB in data collected form realistic large-scale concrete samples. By combining the MEMS array system and compressed sensing approach, the total ultrasonic data acquisition time needed to produce dense wavefield data can be significantly reduced.

Instruments & Instrumentation↗
DOE OSTI2022

Self‐gated, dynamic contrast‐enhanced magnetic resonance imaging with compressed‐sensing reconstruction for evaluating endothelial permeability in the aortic root of atherosclerotic mice

High‐risk atherosclerotic plaques are characterized by active inflammation and abundant leaky microvessels. We present a self‐gated, dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) acquisition with compressed sensing reconstruction and apply it to assess longitudinal changes in endothelial permeability in the aortic root of Apoe −/− atherosclerotic mice during natural disease progression. Twenty‐four, 8‐week‐old, female Apoe −/− mice were divided into four groups (n = 6 each) and imaged with self‐gated DCE‐MRI at 4, 8, 12, and 16 weeks after high‐fat diet initiation, and then euthanized for CD68 immunohistochemistry for macrophages. Eight additional mice were kept on a high‐fat diet and imaged longitudinally at the same time points. Aortic‐root pseudo‐concentration curves were analyzed using a validated piecewise linear model. Contrast agent wash‐in and washout slopes ( b 1 and b 2 ) were measured as surrogates of aortic root endothelial permeability and compared with macrophage density by immunohistochemistry. b 2 , indicating contrast agent washout, was significantly higher in mice kept on an high‐fat diet for longer periods of time ( p = 0.03). Group comparison revealed significant differences between mice on a high‐fat diet for 4 versus 16 weeks ( p = 0.03). Macrophage density also significantly increased with diet duration ( p = 0.009). Spearman correlation between b 2 from DCE‐MRI and macrophage density indicated a weak relationship between the two parameters (r = 0.28, p = 0.20). Validated piecewise linear modeling of the DCE‐MRI data showed that the aortic root contrast agent washout rate is significantly different during disease progression. Further development of this technique from a single‐slice to a 3D acquisition may enable better investigation of the relationship between in vivo imaging of endothelial permeability and atherosclerotic plaques' genetic, molecular, and cellular makeup in this important model of disease.

Calcagno, Claudia↗
DOE OSTI2024

Zero-Power Analog Optical Processing

The motivation behind this research is the growing challenge of handling the massive amounts of data generated by modern imaging systems. Conventional digital image processing techniques are struggling to keep pace with the demands of high-resolution and high-speed imaging systems for remote sensing due to their high-power consumption and data storage requirements. We present a novel approach based on analog photonics to address this challenge. The proposed system utilizes a silicon-photonics-based image encoder positioned after image formation and initial optical-to-electrical conversion. The photonic encoder compresses image data using a passive disordered photonic structure to perform kernel-type random projections of the raw data. The compressed data is then processed by a back-end neural network, which reconstructs the original image with high fidelity (structural similarity exceeding 90%). Our proposed approach has the potential to compress images with ~ 1000X lower power consumption compared to digital approaches with data rates exceeding 1 terapixel/second.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Fast Algorithms for Scientific Data Compression

Many scientific simulations and experiments generate terabytes to petabytes of data daily, necessitating data compression techniques. Unlike video and image compression, scientists require methods that accurately preserve primary data (PD) and derived quantities of interest (QoIs). In our previous work, we demonstrated the effectiveness of hybrid compression techniques that combine machine learning with traditional approaches. This paper presents innovative computational techniques aimed at expediting the compression pipeline. Our experiments, conducted on two distinct platforms with a large-scale XGC-based fusion simulation, demonstrate that the overhead incurred by these new approaches is less than one percent of the computational resources needed for the simulation.

Banerjee, Tania↗
DOE OSTI2022

Super-resolution and segmentation deep learning for breast cancer histopathology image analysis

Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

All Optical Neural Networks for Low Power Edge Computing

We developed a simplistic physics-based model of an all-optical neural network that mimics the encoder part of an autoencoder neural network for image compression. Our approach relies on the generation of a MATLAB-based model for both data compression and decompression and utilizes MATLAB's built-in autoencoder networks in combination with simple propagation of optical fields between layers constituting phase elements via Fourier transform. We optimize the phase elements using the particle swarm optimization technique and using our model, we demonstrate a compression ratio of 25% for 2828-pixel input images containing numeric digits from 0 to 9.

97 MATHEMATICS AND COMPUTING↗