Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “image generation”

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 919 records · Page 51
All sourcesNASA NTRSDOE OSTI
NASA NTRS1990

Photometric narrowband CCD imaging of comets P/Brorsen-Metcalf and Austin (1989c1)

Simultaneous wide-field CCD images and conventional aperture photometry were obtained of Comets P/Brorsen/Metcalf (1989o) and Austin (1989c1). These data allow direct testing of absolute calibration of the CCD images and the ability to generate full-come, continuum-subtracted emission band images. Preliminary photometric calibration for a portion of the Brorsen-Metcalf observations yields reduced emission band and continuum fluxes which agree to within about 10 percent with those from the photoelectric observations. Conventional photometry of Comet Austin shows unusual variations among the production rates of the different species as a function of heliocentric distance.

Schleicher, David G.↗
NASA NTRS2001

Hyperspectral Image Classification using a Self-Organizing Map

The use of hyperspectral data to determine the abundance of constituents in a certain portion of the Earth's surface relies on the capability of imaging spectrometers to provide a large amount of information at each pixel of a certain scene. Today, hyperspectral imaging sensors are capable of generating unprecedented volumes of radiometric data. The Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), for example, routinely produces image cubes with 224 spectral bands. This undoubtedly opens a wide range of new possibilities, but the analysis of such a massive amount of information is not an easy task. In fact, most of the existing algorithms devoted to analyzing multispectral images are not applicable in the hyperspectral domain, because of the size and high dimensionality of the images. The application of neural networks to perform unsupervised classification of hyperspectral data has been tested by several authors and also by us in some previous work. We have also focused on analyzing the intrinsic capability of neural networks to parallelize the whole hyperspectral unmixing process. The results shown in this work indicate that neural network models are able to find clusters of closely related hyperspectral signatures, and thus can be used as a powerful tool to achieve the desired classification. The present work discusses the possibility of using a Self Organizing neural network to perform unsupervised classification of hyperspectral images. In sections 3 and 4, the topology of the proposed neural network and the training algorithm are respectively described. Section 5 provides the results we have obtained after applying the proposed methodology to real hyperspectral data, described in section 2. Different parameters in the learning stage have been modified in order to obtain a detailed description of their influence on the final results. Finally, in section 6 we provide the conclusions at which we have arrived.

Martinez, P.↗
NASA NTRS1992

Automatic rule generation for high-level vision

A new fuzzy set based technique that was developed for decision making is discussed. It is a method to generate fuzzy decision rules automatically for image analysis. This paper proposes a method to generate rule-based approaches to solve problems such as autonomous navigation and image understanding automatically from training data. The proposed method is also capable of filtering out irrelevant features and criteria from the rules.

Rhee, Frank Chung-Hoon↗
DOE OSTI2025

Automated Scoring of Morphological Changes in Images of Pentaerythritol Tetranitrate

Recent advances in characterization techniques that generate large datasets of material microstructure images require robust, automated image-processing. We applied an unsupervised anomaly detection method called feature anomaly detection system (FADS) to automatically detect and quantify microstructure changes in images of the explosive pentaerythritol tetranitrate (PETN) aged at various temperatures. We demonstrated the FADS approach on two-dimensional images extracted from computed tomography scans, but the same technique can be readily applied to other imaging modalities. FADS calculates anomaly scores on the basis of differences in filter activations of nominal and test data in pretrained convolutional neural networks. The FADS scores successfully differentiated between pristine PETN and PETN aged at a temperature where material coarsening occurred. Morphological metric analysis of segmented images verified observed trends in FADS scores as a function of aging temperature and aging time, specifically by calculating volume fractions, specific boundary lengths, two-point correlation functions, and local thicknesses. Here, the FADS technique has two important advantages compared to traditional morphological analysis: First, it uses grayscale images as input, rather than images that are segmented to separate the appropriate phases; and second, FADS scores capture any type of changes among image sets, rather than requiring prior knowledge or selection of a relevant set of metrics.

Accelerated aging↗
DOE OSTI2020

Multimodal imaging and machine learning to enhance microscope images of shale

A machine learning based image processing workflow is presented to enhance shale source rock microscopic images obtained using diverse imaging platforms. Images were acquired from a 30 μm diameter cylindrical Vaca Muerta shale sample using both nondestructive Transmission X-Ray Microscopy (TXM, alternately referred to as nano computed tomography) and destructive Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM). Output cross-sectional images from each modality were aligned using a combination of manual and automated registration techniques to create a registered image dataset. We then apply this dataset for two image processing tasks: prediction of image cross sections with SEM-like resolution from nondestructive TXM data and repair of charged region artifacts (localized accumulation of electrons) within SEM images. The image processing algorithms for both tasks use deep learning models, specifically image-to-image Convolutional Neural Networks (CNNs) and conditional Generative Adversarial Networks (cGANs). In the image enhancement tasks, we are able to achieve significant qualitative and quantitative improvement in TXM images. Here, the best model reaches an average Peak Signal to Noise Ratio (PSNR) of 15.8 dB. Conditioning on TXM data is also shown to reduce artifacts from SEM charging, achieving an average PSNR of 25.8 dB. Furthermore, our results suggest that properly trained and validated networks are capable of significant enhancement of images obtained using nondestructive techniques, thereby improving interpretation of two- and three-dimensional images while preserving samples for future use.

58 GEOSCIENCES↗
DOE OSTI2024

CryoSegNet: accurate cryo-EM protein particle picking by integrating the foundational AI image segmentation model and attention-gated U-Net

Picking protein particles in cryo-electron microscopy (cryo-EM) micrographs is a crucial step in the cryo-EM-based structure determination. However, existing methods trained on a limited amount of cryo-EM data still cannot accurately pick protein particles from noisy cryo-EM images. The general foundational artificial intelligence–based image segmentation model such as Meta’s Segment Anything Model (SAM) cannot segment protein particles well because their training data do not include cryo-EM images. Here, we present a novel approach (CryoSegNet) of integrating an attention-gated U-shape network (U-Net) specially designed and trained for cryo-EM particle picking and the SAM. The U-Net is first trained on a large cryo-EM image dataset and then used to generate input from original cryo-EM images for SAM to make particle pickings. CryoSegNet shows both high precision and recall in segmenting protein particles from cryo-EM micrographs, irrespective of protein type, shape and size. On several independent datasets of various protein types, CryoSegNet outperforms two top machine learning particle pickers crYOLO and Topaz as well as SAM itself. The average resolution of density maps reconstructed from the particles picked by CryoSegNet is 3.33 Å, 7% better than 3.58 Å of Topaz and 14% better than 3.87 Å of crYOLO. It is publicly available at https://github.com/jianlin-cheng/CryoSegNet

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1988

Digital enhancement of flow field images

Most photographs of experimentally generated fluid flow fields have inherently poor photographic quality, specifically low contrast. Thus, there is a need to establish a process for quickly and accurately enhancing these photographs to provide improved versions for physical interpretation, analysis, and publication. A sequence of digital image processing techniques which have been demonstrated to effectively enhance such photographs is described.

Kudlinski, Robert A.↗
NASA NTRS2015

Retinal Image Quality Assessment for Spaceflight-Induced Vision Impairment Study

Long-term exposure to space microgravity poses significant risks for visual impairment. Evidence suggests such vision changes are linked to cephalad fluid shifts, prompting a need to directly quantify microgravity-induced retinal vascular changes. The quality of retinal images used for such vascular remodeling analysis, however, is dependent on imaging methodology. For our exploratory study, we hypothesized that retinal images captured using fluorescein imaging methodologies would be of higher quality in comparison to images captured without fluorescein. A semi-automated image quality assessment was developed using Vessel Generation Analysis (VESGEN) software and MATLAB® image analysis toolboxes. An analysis of ten images found that the fluorescein imaging modality provided a 36% increase in overall image quality (two-tailed p=0.089) in comparison to nonfluorescein imaging techniques.

retina↗
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↗
NASA NTRS1972

NASTRAN data generation and management using interactive graphics

A method of using an interactive graphics device to generate a large portion of the input bulk data with visual checks of the structure and the card images is described. The generation starts from GRID and PBAR cards. The visual checks result from a three-dimensional display of the model in any rotated position. By detailing the steps, the time saving and cost effectiveness of this method may be judged, and its potential as a useful tool for the structural analyst may be established.

Smootkatow, M.↗
NASA NTRS2015

Impact Induced Delamination Detection and Quantification With Guided Wavefield Analysis

This paper studies impact induced delamination detection and quantification by using guided wavefield data and spatial wavenumber imaging. The complex geometry impact-like delamination is created through a quasi-static indentation on a CFRP plate. To detect and quantify the impact delamination in the CFRP plate, PZT-SLDV sensing and spatial wavenumber imaging are performed. In the PZT-SLDV sensing, the guided waves are generated from the PZT, and the high spatial resolution guided wavefields are measured by the SLDV. The guided wavefield data acquired from the PZT-SLDV sensing represent guided wave propagation in the composite laminate and include guided wave interaction with the delamination damage. The measured guided wavefields are analyzed through the spatial wavenumber imaging method, which generates an image containing the dominant local wavenumber at each spatial location. The spatial wavenumber imaging result for the simple single layer Teflon insert delamination provided quantitative information on delamination damage size and location. The location of delamination damage is indicated by the area with larger wavenumbers in the spatial wavenumber image. The impact-like delamination results only partially agreed with the damage size and shape. The results also demonstrated the dependence on excitation frequency. Future work will further investigate the accuracy of the wavenumber imaging method for real composite damage and the dependence on frequency of excitation.

Tian, Zhenhua↗
NASA NTRS1998

NGST: Exploring the Fossil Record of Galaxy Formation

During this grant period the investigator has accomplished the following: developed and researched the science case for high resolution optical imaging with NGST (Next Generation Space Telescope); presented to the ASWG (Ad-Hoc Science Working Group) on the use of NGST to image and measure the proper motions of white dwarf stars that could account for the MACHO events toward the LMC (Large Magellanic Cloud); wrote proposals for the Design Reference Mission. Three proposals have been written on the following topics: Measuring the faint end of the white dwarf luminosity function to get an independent measure of the age of the oldest stars, measurement of the stellar luminosity function over the full range of age, abundance, and population type, and deep imaging of Local Group halos to measure the relative ages of the oldest stars in the Milky Way and other galaxies; he has introduced simulations of crowded field stellar photometry on a hypothetical population in the M31 halo. Using a physically correct luminosity function and a surface brightness of 24.5 mag/sq. arcsec, NGST imaging in 10 hours easily measures the turnoff and reaches 3 mags down the main sequence in the halo of M31; and has delivered talks at the NGST workshop in Liege, and at the meeting in Paris entitled "Connecting the Distant Universe with the Local Fossil Record".

Rich, R. Michael↗
NASA NTRS1997

Atmospheric Correction of Satellite Imagery Using Modtran 3.5 Code

When performing satellite remote sensing of the earth in the solar spectrum, atmospheric scattering and absorption effects provide the sensors corrupted information about the target's radiance characteristics. We are faced with the problem of reconstructing the signal that was reflected from the target, from the data sensed by the remote sensing instrument. This article presents a method for simulating radiance characteristic curves of satellite images using a MODTRAN 3.5 band model (BM) code to solve the radiative transfer equation (RTE), and proposes a method for the implementation of an adaptive system for automated atmospheric corrections. The simulation procedure is carried out as follows: (1) for each satellite digital image a radiance characteristic curve is obtained by performing a digital number (DN) to radiance conversion, (2) using MODTRAN 3.5 a simulation of the images characteristic curves is generated, (3) the output of the code is processed to generate radiance characteristic curves for the simulated cases. The simulation algorithm was used to simulate Landsat Thematic Mapper (TM) images for two types of locations: the ocean surface, and a forest surface. The simulation procedure was validated by computing the error between the empirical and simulated radiance curves. While results in the visible region of the spectrum where not very accurate, those for the infrared region of the spectrum were encouraging. This information can be used for correction of the atmospheric effects. For the simulation over ocean, the lowest error produced in this region was of the order of 105 and up to 14 times smaller than errors in the visible region. For the same spectral region on the forest case, the lowest error produced was of the order of 10-4, and up to 41 times smaller than errors in the visible region,

Gonzales, Fabian O.↗
DOE OSTI2024

Physics and chemistry from parsimonious representations: image analysis via invariant variational autoencoders

Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenomena from the data, such as manifestations of symmetry breaking phenomena in electron and scanning tunneling microscopy images, or variability of the nanoparticles. Variational autoencoders (VAEs) are emerging as a powerful paradigm for the unsupervised data analysis, allowing to disentangle the factors of variability and discover optimal parsimonious representation. Here, we summarize recent developments in VAEs, covering the basic principles and intuition behind the VAEs. The invariant VAEs are introduced as an approach to accommodate scale and translation invariances present in imaging data and separate known factors of variations from the ones to be discovered. We further describe the opportunities enabled by the control over VAE architecture, including conditional, semi-supervised, and joint VAEs. Several case studies of VAE applications for toy models and experimental datasets in Scanning Transmission Electron Microscopy are discussed, emphasizing the deep connection between VAE and basic physical principles. Python codes and datasets discussed in this article are available at https://github.com/saimani5/VAE-tutorials and can be used by researchers as an application guide when applying these to their own datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2023

UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-consistency constraint. To achieve this, we equip the generator with a Vision Transformer (ViT) and employ necessary training and regularization techniques. Compared to previous best-performing models, our model performs better and retains a strong correlation between the original and translated image. An accompanying ablation study shows that both the gradient penalty and self-supervised pre-training are crucial to the improvement. To promote reproducibility and open science, the source code, hyperparameter configurations, and pre-trained model are available at https: //github.com/LS4GAN/uvcgan.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

Rapid Prototyping Integrated With Nondestructive Evaluation and Finite Element Analysis

Most reverse engineering approaches involve imaging or digitizing an object then creating a computerized reconstruction that can be integrated, in three dimensions, into a particular design environment. Rapid prototyping (RP) refers to the practical ability to build high-quality physical prototypes directly from computer aided design (CAD) files. Using rapid prototyping, full-scale models or patterns can be built using a variety of materials in a fraction of the time required by more traditional prototyping techniques (refs. 1 and 2). Many software packages have been developed and are being designed to tackle the reverse engineering and rapid prototyping issues just mentioned. For example, image processing and three-dimensional reconstruction visualization software such as Velocity2 (ref. 3) are being used to carry out the construction process of three-dimensional volume models and the subsequent generation of a stereolithography file that is suitable for CAD applications. Producing three-dimensional models of objects from computed tomography (CT) scans is becoming a valuable nondestructive evaluation methodology (ref. 4). Real components can be rendered and subjected to temperature and stress tests using structural engineering software codes. For this to be achieved, accurate high-resolution images have to be obtained via CT scans and then processed, converted into a traditional file format, and translated into finite element models. Prototyping a three-dimensional volume of a composite structure by reading in a series of two-dimensional images generated via CT and by using and integrating commercial software (e.g. Velocity2, MSC/PATRAN (ref. 5), and Hypermesh (ref. 6)) is being applied successfully at the NASA Glenn Research Center. The building process from structural modeling to the analysis level is outlined in reference 7. Subsequently, a stress analysis of a composite cooling panel under combined thermomechanical loading conditions was performed to validate this process.

Abdul-Aziz, Ali↗
NASA NTRS2005

EUV Imaging of SWCX-Produced He(+) 30.4-nm Emission/Scattering at the Magnetosheath

Theoretically, charge exchange between solar wind alpha-particles and geocoronal hydrogen at the magnetosheath results in the production of helium ions in an excited state, i.e, He(2+) + H (right arrow) He(+*) + H(+) resulting in the emission of 30.4-nm radiation upon relaxation of the helium ions. It has been estimated that the magnetosphere was compressed to inside the orbit of IMAGE during the Halloween storm of 2003. This configuration should have placed the subsolar point of the magnetosheath well beyond the limb of the solar disk and allow EUV the potential of imaging this solar wind charge exchange interaction Analysis of EUV full-frame data acquired during 31 October 2003 (Day 304) indicates the detection of 30.4-nm photons in the likely vicinity of the magnetosheath either as a direct consequence of the emission proposed above or, provided the magnetosheath He(+) density was sufficient to exceed the EUV sensitivity threshold, via resonant scattering of solar UV. We present initial analysis of EUV imaging during the Halloween 2003 storm from the context of solar wind parameters, including composition, and from the perspective of the generation of simulated EUV imaging of the event both as an emitting and as a scattering process.

Adrian, M. L.↗
NASA NTRS2018

Coronal Imaging with the Solar Ultraviolet Imager

Coronal imaging capabilities of the Solar UltraViolet Imager (SUVI) on the Geostationary Operational Environmental Satellite-16 (GOES-16) are investigated. Launched in 2016, GOES-16 is stationed at 75.2 deg W longitude and accommodates both terrestrial and space weather instruments. SUVI is one of two instruments observing the Sun, providing solar images in six extreme ultraviolet (EUV) wavelengths: 94A, 131A, 171A, 195A, 284A and 304A. Mounted on a two axis gimballed Sun Pointed Platform (SPP), its 53 arc minute square field of view is nominally Sun-centered to provide high dynamic range images in all six wavelengths every four minutes. Analyses of on-orbit data indicated that SUVI had sufficient dynamic range and sensitivity in the 171A and 195A wavelengths to image the corona to the largest heights above the Sun to date while simultaneously imaging the Sun. The 1.6 megapixel Charge Coupled Device (CCD) detector enables the capture of the fine features of the corona. On-orbit calibration tests requiring movement of the SUVI line-of-sight off the Sun, demonstrated that the resulting dynamic disturbance didn't adversely impact the earth-pointing instrument performance. Combining these factors, we conducted a test to assess the performance of SUVI as an EUV extremely wide-field coronal imager by off-pointing the SPP around the Sun and synthesizing an image that's about 4 times the diameter of the Sun. The capability to perform coronal imaging at these two wavelengths is demonstrated by off-pointing the SUVI boresight to nine locations around the Sun and generating a composite coronal image that extends to approx. 4 solar radii. For this purpose, we exploited the satellite's ability to provide stable, fine pointing, even during the slews. Various exposure durations were considered during the first trial and a composite coronal image is obtained for each wavelength. The results are promising. The off-pointing locations and the exposure duration are being refined for the subsequent trials. The routine use of an ultraviolet solar imager as both an imager and a EUV coronagraph would be the first of its kind and is an exciting development. The on-orbit solar coronagraphs to date provide white light images with fields of view extending from 4-15 solar radii. Earlier, Seaton, et al investigated the evolution of the corona in EUV near the solar surface with the data from the Sun Watcher with Active Pixels and Image Processing (SWAP) EUV solar telescope on board the Project for On-Board Autonomy 2 (PROBA2). The presence of corona in EUV even to 4 solar radii is not known. The results of these experiments will begin to fill this void.

Tadikonda, Sivakumara K.↗