Search NASA⌕ Search

SEARCH · Search NASA

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Comparison of edges detected at different polarisations in MAESTRO data

Edge detection would appear to be a crucial tool for analyzing multi-polarized, multi-frequency, and multi-temporal Synthetic Aperture Radar (SAR) images. Edge structure provides a simple means for comparing different polarizations and frequencies, and for detecting changes over time. Due to the fact that edges and segments (homogeneous regions) are dual concepts, edge detection has an important role to play in identifying segments within which mean backscatter measurements for use in image classification can be made. As part of a general investigation into edge detection in SAR imagery, an initial investigation was carried out into the detectability and nature of edges in multi-polarized and multi-frequency SAR images. The contrast ratio (CR) operator was used to detect edges. This operator was previously shown to perform well at detecting edges in single-polarized and single-frequency SAR images.

Caves, Ronald G.↗
DOE OSTI2025

Towards AI Based Data Classification for Decision Making During Testing

During the development of high-consequence items, test systems should be capable of differentiating between test failures resulting from narrowly missing requirements versus those indicating potentially catastrophic faults. In many instances, classifying the data corresponds to simply identifying whether measured waveforms have approximately the anticipated shape. Cast in this light, the problem reduces to converting raw data into a form optimal for use with neural network classifiers. This manuscript investigates different means of representing raw data for image classification. Raw data plots and Short Time Fourier Transform (STFT) spectrograms are classified by both custom built, small-scale, Convolution Neural Networks (CNN) and open-source, multi-million parameter, pre-trained deep CNNs. In the case of time varying frequency content, the STFTs provide images with greater detail and can be accurately classified with simpler networks. This requires less memory and runs faster than classifying the raw data using the more sophisticated options—making STFTs optimal for applications with memory constraints. STFTs are not a panacea. In some cases the time-domain signal contains useful information that should not be discarded. Rather than using raw data or STFTs, the images can be constructed from both by using red and green channels of an RGB image to visualize the real and imaginary components of the transform, with the raw data occupying the blue channel.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quantum Transfer Learning to Boost Dementia Detection

Dementia is a devastating condition with profound implications for individuals, families, and healthcare systems. Early and accurate detection of dementia is critical for timely intervention and improved patient outcomes. While classical machine learning and deep learning approaches have been explored extensively for dementia prediction, these solutions often struggle with high-dimensional biomedical data and large-scale datasets, quickly reaching computational and performance limitations. To address this challenge, quantum machine learning (QML) has emerged as a promising paradigm, offering faster training and advanced pattern recognition capabilities. This work aims to demonstrate the potential of quantum transfer learning (QTL) to enhance the performance of a weak classical deep learning model applied to a binary classification task for dementia detection. Besides, we show the effect of noise on the QTL-based approach, investigating the reliability and robustness of this method. Using the OASIS 2 dataset, we show how quantum techniques can transform a suboptimal classical model into a more effective solution for biomedical image classification, highlighting their potential impact on advancing healthcare technology.

Bhowmik, Sounak [University of Tennessee, Knoxvill↗
NASA NTRS1992

Supervised fully polarimetric classification of the Black Forest test site: From MAESTROI to MAC Europe

A study on the performance of a supervised fully polarimetric maximum likelihood classifier for synthetic aperture radar (SAR) data when applied to a specific classification context: forest classification based on age classes and in the presence of a sloping terrain is presented. For the experimental part, the polarimetric AIRSAR data at P, L, and C-band, acquired over the German Black Forest near Freiburg in the frame of the 1989 MAESTRO-1 campaign and the 1991 MAC Europe campaign was used, MAESTRO-1 with an ESA/JRC sponsored campaign, and MAC Europe (Multi-sensor Aircraft Campaign); in both cases the multi-frequency polarimetric JPL Airborne Synthetic Aperture Radar (AIRSAR) radar was flown over a number of European test sites. The study is structured as follows. At first, the general characteristics of the classifier and the dependencies from some parameters, like frequency bands, feature vector, calibration, using test areas lying on a flat terrain are investigated. Once it is determined the optimal conditions for the classifier performance, we then move on to the study of the slope effect. The bulk of this work is performed using the Maestrol data set. Next the classifier performance with the MAC Europe data is considered. The study is divided into two stages: first some of the tests done on the Maestro data are repeated, to highlight the improvements due to the new processing scheme that delivers 16 look data. Second we experiment with multi images classification with two goals: to assess the possibility of using a training set measured from one image to classify areas in different images; and to classify areas on critical slopes using different viewing angles. The main points of the study are listed and some of the results obtained so far are highlighted.

Degrandi, G.↗
NASA NTRS1989

Image-based terrain modeling with thematic mapper applied to resolving the limit of Holocene Lake expansion in the Great Salt Lake Desert, Utah, part 1

The LANDSAT Thematic Mapper (TM) scanner records reflected solar energy from the earth's surface in six wavelength regions, or bands, and one band that records emitted energy in the thermal region, giving a total of seven bands. Useful research was extracted about terrain morphometry from remote sensing measurements and this information is used in an image-based terrain model for selected coastal geomorphic features in the Great Salt Lake Desert (GSLD). Technical developments include the incorporation of Aerial Profiling of Terrain System (APTS) data in satellite image analysis, and the production and use of 3-D surface plots of TM reflectance data. Also included in the technical developments is the analysis of the ground control point spatial distribution and its affects on geometric correction, and the terrain mapping procedure; using satellite data in a way that eliminates the need to degrade the data by resampling. The most common approach for terrain mapping with multispectral scanner data includes the techniques of pattern recognition and image classification, as opposed to direct measurement of radiance for identification of terrain features. The research approach in this investigation was based on an understanding of the characteristics of reflected light resulting from the variations in moisture and geometry related to terrain as described by the physical laws of radiative transfer. The image-based terrain model provides quantitative information about the terrain morphometry based on the physical relationship between TM data, the physical character of the GSLD, and the APTS measurements.

Merola, John A.↗
DOE OSTI2024

Anchoring

This software provides methods and functions for training deep image classification models based on the principle of anchoring. It features a user-friendly PyTorch wrapper that facilitates the easy conversion of any model into an anchored model. The software supports various standard datasets and includes scripts for conducting evaluations. Developed with PyTorch, it is compatible with common neural network architectures used for image data. Additionally, it offers tools for computing evaluation metrics to assess model performance.

Narayanaswamy, Vivek Sivaraman↗
DOE OSTI2024

Quantifying leaf symptoms of sorghum charcoal rot in images of field‐grown plants using deep neural networks

Abstract Charcoal rot of sorghum (CRS) is a significant disease affecting sorghum crops, with limited genetic resistance available. The causative agent, Macrophomina phaseolina (Tassi) Goid, is a highly destructive fungal pathogen that targets over 500 plant species globally, including essential staple crops. Utilizing field image data for precise detection and quantification of CRS could greatly assist in the prompt identification and management of affected fields and thereby reduce yield losses. The objective of this work was to implement various machine learning algorithms to evaluate their ability to accurately detect and quantify CRS in red‐green‐blue images of sorghum plants exhibiting symptoms of infection. EfficientNet‐B3 and a fully convolutional network emerged as the top‐performing models for image classification and segmentation tasks, respectively. Among the classification models evaluated, EfficientNet‐B3 demonstrated superior performance, achieving an accuracy of 86.97%, a recall rate of 0.71, and an F1 score of 0.73. Of the segmentation models tested, FCN proved to be the most effective, exhibiting a validation accuracy of 97.76%, a recall rate of 0.68, and an F1 score of 0.66. As the size of the image patches increased, both models’ validation scores increased linearly, and their inference time decreased exponentially. This trend could be attributed to larger patches containing more information, improving model performance, and fewer patches reducing the computational load, thus decreasing inference time. The models, in addition to being immediately useful for breeders and growers of sorghum, advance the domain of automated plant phenotyping and may serve as a foundation for drone‐based or other automated field phenotyping efforts. Additionally, the models presented herein can be accessed through a web‐based application where users can easily analyze their own images.

Gonzalez, Emmanuel M.↗
NASA NTRS1988

Preliminary assessment of airborne imaging spectrometer and airborne thematic mapper data acquired for forest decline areas in the Federal Republic of Germany

This study evaluated the utility of data collected by the high-spectral resolution airborne imaging spectrometer (AIS-2, tree mode, spectral range 0.8-2.2 microns) and the broad-band Daedalus airborne thematic mapper (ATM, spectral range 0.42-13.0 micron) in assessing forest decline damage at a predominantly Scotch pine forest in the FRG. Analysis of spectral radiance values from the ATM and raw digital number values from AIS-2 showed that higher reflectance in the near infrared was characteristic of high damage (heavy chlorosis, limited needle loss) in Scotch pine canopies. A classification image of a portion of the AIS-2 flight line agreed very well with a damage assessment map produced by standard aerial photointerpretation techniques.

Herrmann, Karin↗
NASA NTRS1995

Searching for patterns in remote sensing image databases using neural networks

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Paola, Justin D.↗
NASA NTRS2018

Follow-up Imaging of Disk Candidates from the Disk Detective Citizen Science Project: New Discoveries and False Positives in WISE Circumstellar Disk Surveys

The Disk Detective citizen science project aims to find new stars with excess 22 m emission from circumstellar dust in the All WISE data release from the Wide-field Infrared Survey Explorer. We evaluated 261 Disk Detective objects of interest with imaging with the Robo-AO adaptive optics instrument on the 1.5 m telescope at Palomar Observatory and with RetroCam on the 2.5 m du Pont Telescope at Las Campanas Observatory to search for background objects at 0 15–12 separations from each target. Our analysis of these data leads us to reject 7% of targets. Combining this result with statistics from our online image classification efforts implies that at most7.9%±0.2% of All WISE-selected infrared excesses are good disk candidates. Applying our false-positive rates to other surveys, we find that the infrared excess searches of McDonald et al. and Marton et al. all have false-positiverates >70%. Moreover, we find that all 13 disk candidates in Theissen & West with W4 signal-to-noise ratio >3are false positives. We present 244 disk candidates that have survived vetting by follow-up imaging. Of these,213 are newly identified disk systems. Twelve of these are candidate members of comoving pairs based on Gaia astrometry, supporting the hypothesis that warm dust is associated with binary systems. We also note the discovery of 22 m excess around two known members of the Scorpius–Centaurus association, and we identifyknown disk host WISEA J164540.79-310226.6 as a likely Sco-Cen member. Thirty of these disk candidates arecloser than 125 pc (including 26 debris disks), making them good targets for both direct-imaging exoplanetsearches.

Wide-field Infrared Survey Explorer↗
NASA NTRS1993

Classification of multispectral image data by the Binary Diamond neural network and by nonparametric, pixel-by-pixel methods

The classification of multispectral image data obtained from satellites has become an important tool for generating ground cover maps. This study deals with the application of nonparametric pixel-by-pixel classification methods in the classification of pixels, based on their multispectral data. A new neural network, the Binary Diamond, is introduced, and its performance is compared with a nearest neighbor algorithm and a back-propagation network. The Binary Diamond is a multilayer, feed-forward neural network, which learns from examples in unsupervised, 'one-shot' mode. It recruits its neurons according to the actual training set, as it learns. The comparisons of the algorithms were done by using a realistic data base, consisting of approximately 90,000 Landsat 4 Thematic Mapper pixels. The Binary Diamond and the nearest neighbor performances were close, with some advantages to the Binary Diamond. The performance of the back-propagation network lagged behind. An efficient nearest neighbor algorithm, the binned nearest neighbor, is described. Ways for improving the performances, such as merging categories, and analyzing nonboundary pixels, are addressed and evaluated.

Salu, Yehuda↗
NASA NTRS2011

CropEx Web-Based Agricultural Monitoring and Decision Support

CropEx is a Web-based agricultural Decision Support System (DSS) that monitors changes in crop health over time. It is designed to be used by a wide range of both public and private organizations, including individual producers and regional government offices with a vested interest in tracking vegetation health. The database and data management system automatically retrieve and ingest data for the area of interest. Another stores results of the processing and supports the DSS. The processing engine will allow server-side analysis of imagery with support for image sub-setting and a set of core raster operations for image classification, creation of vegetation indices, and change detection. The system includes the Web-based (CropEx) interface, data ingestion system, server-side processing engine, and a database processing engine. It contains a Web-based interface that has multi-tiered security profiles for multiple users. The interface provides the ability to identify areas of interest to specific users, user profiles, and methods of processing and data types for selected or created areas of interest. A compilation of programs is used to ingest available data into the system, classify that data, profile that data for quality, and make data available for the processing engine immediately upon the data s availability to the system (near real time). The processing engine consists of methods and algorithms used to process the data in a real-time fashion without copying, storing, or moving the raw data. The engine makes results available to the database processing engine for storage and further manipulation. The database processing engine ingests data from the image processing engine, distills those results into numerical indices, and stores each index for an area of interest. This process happens each time new data is ingested and processed for the area of interest, and upon subsequent database entries, the database processing engine qualifies each value for each area of interest and conducts a logical processing of results indicating when and where thresholds are exceeded. Reports are provided at regular, operator-determined intervals that include variances from thresholds and links to view raw data for verification, if necessary. The technology and method of development allow the code base to easily be modified for varied use in the real-time and near-real-time processing environments. In addition, the final product will be demonstrated as a means for rapid draft assessment of imagery.

Harvey. Craig↗
DOE OSTI2026

VoroClust: Scalable Clustering for Remote Sensing

Although supervised machine learning provides a powerful framework for image classification and segmentation, it requires comprehensive consistent datasets, which are not available for many remote-sensing applications. Remote-sensing datasets are expensive to collect, and each is acquired under different environmental conditions or with significant variations in system operating parameters. Unsupervised clustering algorithms analyze the structure of each dataset independently, rather than drawing on similarities with existing “training” examples, and are thus well suited for practical remote-sensing applications. We introduce VoroClust, a fast density-based unsupervised clustering algorithm applicable to high-resolution and high-dimensional data. VoroClust runs as fast as distance-based clustering methods, while capturing complex regional geometries at least as well as current-density-based methods. It uses a data-centered sphere cover to reduce computational demands, while still capturing data topology. It then propagates clusters outward from local peaks in density. We show that VoroClust provides fast state-of-the-art clustering for both high-resolution polarimetric synthetic aperture radar and high-dimensional hyperspectral imaging datasets.

42 ENGINEERING↗
NASA NTRS1993

Automated cloud classification with a fuzzy logic expert system

An unresolved problem in current cloud retrieval algorithms concerns the analysis of scenes containing overlapping cloud layers. Cloud parameterizations are very important both in global climate models and in studies of the Earth's radiation budget. Most cloud retrieval schemes, such as the bispectral method used by the International Satellite Cloud Climatology Project (ISCCP), have no way of determining whether overlapping cloud layers exist in any group of satellite pixels. One promising method uses fuzzy logic to determine whether mixed cloud and/or surface types exist within a group of pixels, such as cirrus, land, and water, or cirrus and stratus. When two or more class types are present, fuzzy logic uses membership values to assign the group of pixels partially to the different class types. The strength of fuzzy logic lies in its ability to work with patterns that may include more than one class, facilitating greater information extraction from satellite radiometric data. The development of the fuzzy logic rule-based expert system involves training the fuzzy classifier with spectral and textural features calculated from accurately labeled 32x32 regions of Advanced Very High Resolution Radiometer (AVHRR) 1.1-km data. The spectral data consists of AVHRR channels 1 (0.55-0.68 mu m), 2 (0.725-1.1 mu m), 3 (3.55-3.93 mu m), 4 (10.5-11.5 mu m), and 5 (11.5-12.5 mu m), which include visible, near-infrared, and infrared window regions. The textural features are based on the gray level difference vector (GLDV) method. A sophisticated new interactive visual image Classification System (IVICS) is used to label samples chosen from scenes collected during the FIRE IFO II. The training samples are chosen from predefined classes, chosen to be ocean, land, unbroken stratiform, broken stratiform, and cirrus. The November 28, 1991 NOAA overpasses contain complex multilevel cloud situations ideal for training and validating the fuzzy logic expert system.

Tovinkere, Vasanth↗
NASA NTRS2019

Feature Learning for Multispectral Satellite Imagery Classification Using Neural Architecture Search

Automated classification of remote sensing data is an integral tool for earth scientists, and deep learning has proven very successful at solving such problems. However, building deep learning models to process the data requires expert knowledge of machine learning. We introduce DELTA, a software toolkit to bridge this technical gap and make deep learning easily accessible to earth scientists. Visual feature engineering is a critical part of the machine learning lifecycle, and hence is a key area that will be automated by DELTA. Hand-engineered features can perform well, but require a cross functional team with expertise in both machine learning and the specific problem domain, which is costly in both researcher time and labor. The problem is more acute with multispectral satellite imagery, which requires considerable computational resources to process. In order to automate the feature learning process, a neural architecture search samples the space of asymmetric and symmetric autoencoders using evolutionary algorithms. Since denoising autoencoders have been shown to perform well for feature learning, the autoencoders are trained on various levels of noise and the features generated by the best performing autoencoders evaluated according to their performance on image classification tasks. The resulting features are demonstrated to be effective for Landsat-8 flood mapping, as well as benchmark datasets CIFAR10 and SVHN.

Robert Campbell↗
DOE OSTI2025

Confidence-weighted integration of human and machine judgments for superior decision-making

Large language models (LLMs) can surpass humans in certain forecasting tasks. What role does this leave for humans in the overall decision process? One possibility is that humans, despite performing worse than LLMs, can still add value when teamed with them. A human and machine team can surpass each individual teammate when team members’ confidence is well calibrated and team members diverge in which tasks they find difficult (i.e., calibration and diversity are needed). We simplified and extended a Bayesian approach to combining judgments using a logistic regression framework that integrates confidence-weighted judgments for any number of team members. Using this straightforward method, we demonstrated its effectiveness in both image classification and neuroscience forecasting tasks. Combining human judgments with one or more machines consistently improved overall team performance. Our hope is that this simple and effective strategy for integrating the judgments of humans and machines will lead to productive collaborations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Understanding and Estimating Error Propagation in Neural Networks for Scientific Data Analysis

Neural networks are increasingly integrated into scientific discovery, where input data reduction and model quantization play a key role in accelerating inference. However, understanding and mitigating the impact of these techniques on output error is critical for ensuring reliable results, particularly in tasks demanding high numerical precision. This paper introduces a comprehensive framework for optimizing neural network inference in scientific computing by combining data reduction and weight quantization while maintaining error-controlled outcomes. We develop theoretical analyses to bound error propagation under these reductions and propose a framework that balances computational performance with error constraints. Evaluation on real-world learning-based combustion simulations and satellite image classification demonstrates that our derived error bounds accurately predict observed errors while enabling significant computational speedup under our framework. This work highlights the potential for further leveraging advancements in modern lossy compression algorithms and hardware accelerators that support lower-precision formats.

He, Weiming [New Jersey Institute of Technology]↗