Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Image Classification”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Clustering methods for removing outliers from vision-based range estimates

The present approach to the automation of helicopter low-altitude flight uses one or more passive imaging sensors to extract environmental obstacle information; this is then processed via computer-vision techniques to yield a time-varying map of range to obstacles in the sensor's field of view along the vehicle's flight path. Attention is given to two related techniques which can eliminate outliers from a sparse range map, clustering sparse range-map information into different spatial classes that rely on a segmented and labeled image to aid in spatial classification within the image plane.

Hussien, B.↗
DOE OSTI2021

Deep learning classification of lipid droplets in quantitative phase images

We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1994

Electronic photography at NASA Langley Research Center

The field of photography began a metamorphosis several years ago which promises to fundamentally change how images are captured, transmitted, and output. At this time the metamorphosis is still in the early stages, but already new processes, hardware, and software are allowing many individuals and organizations to explore the entry of imaging into the information revolution. Exploration at this time is prerequisite to leading expertise in the future, and a number of branches at LaRC have ventured into electronic and digital imaging. Their progress until recently has been limited by two factors: the lack of an integrated approach and the lack of an electronic photographic capability. The purpose of the research conducted was to address these two items. In some respects, the lack of electronic photographs has prevented application of an integrated imaging approach. Since everything could not be electronic, the tendency was to work with hard copy. Over the summer, the Photographics Section has set up an Electronic Photography Laboratory. This laboratory now has the capability to scan film images, process the images, and output the images in a variety of forms. Future plans also include electronic capture capability. The current forms of image processing available include sharpening, noise reduction, dust removal, tone correction, color balancing, image editing, cropping, electronic separations, and halftoning. Output choices include customer specified electronic file formats which can be output on magnetic or optical disks or over the network, 4400 line photographic quality prints and transparencies to 8.5 by 11 inches, and 8000 line film negatives and transparencies to 4 by 5 inches. The problem of integrated imaging involves a number of branches at LaRC including Visual Imaging, Research Printing and Publishing, Data Visualization and Animation, Advanced Computing, and various research groups. These units must work together to develop common approaches to image processing and archiving. The ultimate goal is to be able to search for images using an on-line database and image catalog. These images could then be retrieved over the network as needed, along with information on the acquisition and processing prior to storage. For this goal to be realized, a number of standard processing protocols must be developed to allow the classification of images into categories. Standard series of processing algorithms can then be applied to each category (although many of these may be adaptive between images). Since the archived image files would be standardized, it should also be possible to develop standard output processing protocols for a number of output devices. If LaRC continues the research effort begun this summer, it may be one of the first organizations to develop an integrated approach to imaging. As such, it could serve as a model for other organizations in government and the private sector.

Holm, Jack M.↗
NASA NTRS2004

Fast Query-Optimized Kernel-Machine Classification

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Mazzoni, Dominic↗
DOE OSTI2024

RECON Label Quality Report

The final quality of any AI/ML system is directly related to the quality of the input data used to train the system. In this case, we are trying to build a reliable image classifier that can correctly identify electrical components in x-ray images. The classification confidence is directly related to the quality of the labels in the training data, which are used in developing the AI/ML classifier. Incorrect or incomplete labels can substantially hinder the performance of the system during the training process, as it tries to compensate for variations that should not exist. Image labels are entered by subject matter experts, and in general can be assumed to be correct. However, this is not a guarantee, so developing ways to measure label quality and help identify or reject bad labels is important, especially as the database continues to grow. Given the current size of the database, a full manual review of each component is not feasible. This report will highlight the current state of the “RECON” x-ray image database and summarize several recent developments to try to help ensure high quality labeling both now and in the future. Questions that we hope to answer with this development include: 1) Are there any components with incorrect labels? 2) Can we suggest labels for components that are marked “Unknown”? 3) What kind of overall confidence do we have in the quality of the existing labels? 4) What systems or procedures can we put in place to maximize label quality?

42 ENGINEERING↗
DOE OSTI2021

Large-Scale Classification of Urban Structural Units From Remote Sensing Imagery

Remote sensing in combination with deep learning has become instrumental for efficiently and accurately classifying land-use and land-cover across large geographic areas. These technologies have also been successful in characterizing urban environments in terms of their structural units, structure types, or morphological regions. In these approaches, an urban area is partitioned into regions that exhibit homogeneous physical characteristics. However, existing approaches are typically limited to a single city, use inconsistent typologies, and lack scalability and generalization capacity. In this article, we propose an urban structural units categorization scheme and demonstrate its utility by applying it to 13 cities. Inspired by the lack of scalability and generalization capacity in urban structural units mapping, we extend the reach of deep learning and conduct a set of classification experiments in all 13 cities. These experiments offer insights into the strengths and limitations of deep neural networks for classifying urban structural units over diverse geographic regions and on heterogeneous collections of satellite imagery. The efficacy of the proposed deep learning approach is compared to a baseline method of multiscale image features and support vector machines. Our validation on five cities shows that better performance is achieved with deep neural networks. Additionally, we evaluate the impact of input size, model depth, and spatial pyramid pooling to assess the generalization capacity of deep neural networks.

47 OTHER INSTRUMENTATION↗
NASA NTRS1993

Classification of high dimensional multispectral image data

A method for classifying high dimensional remote sensing data is described. The technique uses a radiometric adjustment to allow a human operator to identify and label training pixels by visually comparing the remotely sensed spectra to laboratory reflectance spectra. Training pixels for material without obvious spectral features are identified by traditional means. Features which are effective for discriminating between the classes are then derived from the original radiance data and used to classify the scene. This technique is applied to Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data taken over Cuprite, Nevada in 1992, and the results are compared to an existing geologic map. This technique performed well even with noisy data and the fact that some of the materials in the scene lack absorption features. No adjustment for the atmosphere or other scene variables was made to the data classified. While the experimental results compare favorably with an existing geologic map, the primary purpose of this research was to demonstrate the classification method, as compared to the geology of the Cuprite scene.

Hoffbeck, Joseph P.↗
NASA NTRS1989

An update of commercial infrared sensing and imaging instruments

A classification of infrared sensing instruments by type and application, listing commercially available instruments, from single point thermal probes to on-line control sensors, to high speed, high resolution imaging systems is given. A review of performance specifications follows, along with a discussion of typical thermographic display approaches utilized by various imager manufacturers. An update report on new instruments, new display techniques and newly introduced features of existing instruments is given.

Kaplan, Herbert↗
NASA NTRS2000

Near-infrared galaxy morphology atlas

We present a representative sample of near-infrared (1-2 mu m) images spanning the Hubble galaxy morphology classification sequence. The images come from the Two Micron All Sky Survey, with a range in brightness of 7 mag , K-s , 13.5 mag, and the morphological classifications from the NASA/IPAC Extragalactic Database.

Hubble sequence dwarf galaxy infrared↗
NASA NTRS2018

Exoplanet Classification and Yield Estimates for Direct Imaging Missions

Future NASA concept missions that are currently under study, like the Habitable Exoplanet Imaging Mission (HabEx) and the Large Ultra-violet Optical Infra Red Surveyor (UVOIR), could discover a large diversity of exoplanets. We propose here a classification scheme that distinguishes exoplanets into different categories based on their size and incident stellar flux, for the purpose of providing the expected number of exoplanets observed (yield) with direct imaging missions. The boundaries of this classification can be computed using the known chemical behavior of gases and condensates at different pressures and temperatures in a planetary atmosphere. In this study, we initially focus on condensation curves for sphalerite ZnS, H2O, CO2, and CH4. The order in which these species condense in a planetary atmosphere define the boundaries between different classes of planets. Broadly, the planets are divided into rocky planets (0.5-1.0 solar radius), super-Earths (1.0-1.75 solar radius), sub-Neptunes (1.75-3.5 solar radius), sub-Jovians (3.5-6.0 solar radius), and Jovians (6-14.3 solar radius) based on their planet sizes, and "hot," "warm," and "cold" based on the incident stellar flux. We then calculate planet occurrence rates within these boundaries for different kinds of exoplanets, eta (sub planet) [i.e. exoplanet], using the community coordinated results of NASA's Exoplanet Program Analysis Group's Science Analysis Group-13 (SAG-13). These occurrence rate estimates are in turn used to estimate the expected exoplanet yields for direct imaging missions of different telescope diameters.

Kopparapu, Ravi Kumar↗
DOE OSTI2023

Analysis of an optical imaging system prototype for autonomously monitoring zooplankton in an aquaculture facility

Traditional approaches to biomonitoring in aquatic systems, such as sample collection, sorting, and identification, require significant time and effort, thereby limiting the spatiotemporal resolution of sample collection. Additionally, collection and preservation of samples for subsequent taxonomic identification and enumeration leads to mortality of organisms. Recent advances in technologies that utilize optical imaging and machine learning have provided new opportunities to expedite biomonitoring and lead to significant cost savings. These technologies can be advantageous to scientists or managers that conduct routine biomonitoring to inform operations, as in the case of aquaculture facilities. The Small Aquatic Organism optical imaging system (SAO) is a high-throughput optical imaging and classification prototype system that relies on computer vision and machine learning (Support Vector Machines, or SVMs) to autonomously identify and enumerate aquatic organisms. The SAO provides a more sustainable method of collecting large volumes of data and has the benefit of being used in situ. In this study, we tested the performance of the SAO in providing comparable results to manual zooplankton community monitoring in ten ponds at an aquaculture facility. We performed a side-by-side study comparing the sampling methods of plankton tow nets, where major zooplankton taxonomic classes were manually identified and enumerated, to sampling with the SAO. Vouchered samples were used to develop a training library for the SAO, where classes consisted of water boatman and zooplankton groups: cladocerans, copepod adults, copepod nauplii, and rotifers. SAO imagery was manually classified and compared with predicted results for validation. Accuracy for the SVM classifier of the SAO was 37.4 %. Convolutional Neural Networks (CNN) and Random Forest classifiers were also applied to SAO imagery and image features for comparison. The best CNN model and our Random Forest model had accuracies of 80.4 % and 46.6 % respectively. Challenges faced included the small size of copepod nauplii and rotifers and the limited resolution of the imaging camera, although there are tradeoffs between imaging resolution and the sample processing rate. Furthermore, our comparison shows that advancement in both optical imaging and ML are needed in order for the SAO prototype to yield comparable results to manual community monitoring in an aquaculture facility.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1982

Analysis of a multisensor image data set of south San Rafael Swell, Utah

A Shuttle Imaging Radar (SIR-A) image of the southern portion of the San Rafael Swell in Utah has been digitized and registered to coregistered Landsat, Seasat, and HCMM thermal inertia images. The addition of the SIR-A image to the registered data set improves rock type discrimination in both qualitative and quantitative analyses. Sedimentary units can be separated in a combined SIR-A/Seasat image that cannot be seen in either image alone. Discriminant Analyses show that the classification accuracy is improved with addition of the SIR-A image to Landsat images. Classification accuracy is further improved when texture information from the Seasat and SIR-A images is included.

Evans, D. L.↗
DOE OSTI2025

Hydra: An AI-Based Framework for Interpretable and Portable Data Quality Monitoring

Hydra is an advanced framework designed for training and managing AI models for near real time data quality monitoring at Jefferson Lab. Deployed in all four experimental halls, Hydra has analyzed over 2 million images and has extended its capabilities to offline monitoring and validation. Hydra utilizes computer vision to continually analyze sets of images of monitoring plots generated 24/7 during experiments. Generally, these sets of images are produced at a rate and quantity that is exceedingly difficult for shift crews to effectively monitor. Significant effort has been devoted to enhancing Hydra’s user interface, to ensure that it provides clear, actionable insights for shift workers and other users. Gradient Weighted Class Activation Maps (GradCAM) provide added interpretability, allowing users to visualize important regions of the image for classification. Hydra has been containerized to enable the creation of portable demos and seamless integration with container-based technologies such as Kubernetes and Docker. With the user interface enhancements and containerization, Hydra can be rapidly deployed for new use cases and experiments. This talk will describe the Hydra framework, its user interface and experience, and the challenges inherent in its design and deployment.

Britton, Thomas [Thomas Jefferson National Acceler↗
DOE OSTI2022

Classification of computed thermal tomography images with deep learning convolutional neural network

Thermal tomography (TT) is a computational method for the reconstruction of depth profile of the internal material defects from Pulsed Infrared Thermography (PIT) nondestructive evaluation. Here, the PIT method consists of recording material surface temperature transients with a fast frame infrared camera, following thermal pulse deposition on the material surface with a flashlamp and heat diffusion into material bulk. TT algorithm obtains depth reconstructions of thermal effusivity, which has been shown to provide visualization of the subsurface internal defects in metals. In many applications, one needs to determine the defect shape and orientation from reconstructed effusivity images. Interpretation of TT images is non-trivial because of blurring, which increases with depth due to the heat diffusion-based nature of image formation. We have developed a deep learning convolutional neural network (CNN) to classify the size and orientation of subsurface material defects in TT images. CNN was trained with TT images produced with computer simulations of 2D metallic structures (thin plates) containing elliptical subsurface voids. The performance of CNN was investigated using test TT images developed with computer simulations of plates containing elliptical defects, and defects with shapes imported from scanning electron microscopy images. CNN demonstrated the ability to classify radii and angular orientation of elliptical defects in previously unseen test TT images. We have also demonstrated that CNN trained on the TT images of elliptical defects is capable of classifying the shape and orientation of irregular defects.

42 ENGINEERING↗
DOE OSTI2021

Galaxy zoo: stronger bars facilitate quenching in star-forming galaxies

ABSTRACT We have used Galaxy Zoo DECaLS (GZD) to study strong and weak bars in disc galaxies. Out of the 314 000 galaxies in GZD, we created a volume-limited sample (0.01 < z < 0.05, Mr < − 18.96) which contains 1867 galaxies with reliable volunteer bar classifications in the ALFALFA footprint. In keeping with previous Galaxy Zoo surveys (such as GZ2), the morphological classifications from GZD agree well with previous morphological surveys. GZD considers galaxies to either have a strong bar (15.5 per cent), a weak bar (28.1 per cent) or no bar (56.4 per cent), based on volunteer classifications on images obtained from the DECaLS survey. This places GZD in a unique position to assess differences between strong and weak bars. We find that the strong bar fraction is typically higher in quiescent galaxies than in star-forming galaxies, while the weak bar fraction is similar. Moreover, we have found that strong bars facilitate the quenching process in star-forming galaxies, finding higher fibre star formation rates (SFRs), lower gas masses, and shorter depletion time-scales in these galaxies compared to unbarred galaxies. However, we also found that any differences between strong and weak bars disappear when controlling for bar length. Based on this, we conclude that weak and strong bars are not fundamentally different phenomena. Instead, we propose that there is a continuum of bar types, which varies from ‘weakest’ to ‘strongest’.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Parallel Embeddings: a Visualization Technique for Contrasting Learned Representations

We introduce ``Parallel Embeddings'', a new technique that generalizes the classical Parallel Coordinates visualization technique from a sequence of features within a single matrix to a sequence of multiple feature matrices. This is accomplished by separately embedding each matrix in the sequence into a 2-D frame, juxtaposing these 2-D representations, then connecting points between frames. We outline how this visualization can be used for several ``model comparison'' tasks in machine learning. We compare user performance with Parallel Embeddings to a baseline using the TensorFlow Embedding Projector for estimating model accuracy and understanding conceptual model differences. We found that users were more accurate with Parallel Embeddings for model comparison and that users learned how to use Parallel Embeddings more quickly than TensorFlow Embedding Projector. Furthermore, users' analytical process using Embedding Projector was positively affected by using Parallel Embeddings beforehand.

Model comparison, machine learing, machine learnin↗
DOE OSTI2023

What Machine Learning Can and Cannot Do for Inertial Confinement Fusion

Machine learning methodologies have played remarkable roles in solving complex systems with large data, well-defined input–output pairs, and clearly definable goals and metrics. The methodologies are effective in image analysis, classification, and systems without long chains of logic. Recently, machine-learning methodologies have been widely applied to inertial confinement fusion (ICF) capsules and the design optimization of OMEGA (Omega Laser Facility) capsule implosion and NIF (National Ignition Facility) ignition capsules, leading to significant progress. As machine learning is being increasingly applied, concerns arise regarding its capabilities and limitations in the context of ICF. ICF is a complicated physical system that relies on physics knowledge and human judgment to guide machine learning. Additionally, the experimental database for ICF ignition is not large enough to provide credible training data. Most researchers in the field of ICF use simulations, or a mix of simulations and experimental results, instead of real data to train machine learning models and related tools. They then use the trained learning model to predict future events. This methodology can be successful, subject to a careful choice of data and simulations. However, because of the extreme sensitivity of the neutron yield to the input implosion parameters, physics-guided machine learning for ICF is extremely important and necessary, especially when the database is small, the uncertain-domain knowledge is large, and the physical capabilities of the learning models are still being developed. In this work, we identify problems in ICF that are suitable for machine learning and circumstances where machine learning is less likely to be successful. This study investigates the applications of machine learning and highlights fundamental research challenges and directions associated with machine learning in ICF.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1981

Wheat cultivation: Identifying and estimating area by means of LANDSAT data

Automatic classification of LANDSAT data supported by aerial photography for identification and estimation of wheat growing areas was evaluated. Data covering three regions in the State of Rio Grande do Sul, Brazil were analyzed. The average correct classification of IMAGE-100 data was 51.02% and 63.30%, respectively, for the periods of July and of September/October, 1979.

Dejesusparada, N.↗