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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRS1998

Neutral Networks for Subpixel Classification of Multispectral Images

In this work, the implementation and use of AVHRR (Advanced Very High Resolution Radiometer) images for subpixel analysis is studied. The work consists of two parts, the first is making training data, the second is using the training data to design a neural net subpixel analyzer. Most work on subpixel analysis has been done with images with more spectral bands. AVHRR images were chosen because of their easy acquisition, and because the five spectral bands allow investigation into the development of training data. The first step in subpixel analysis is the development of training data. This consists of image to be classified, and the classification of each pixel. In order to do the classification, a high spatial resolution image is typically needed in order to manually create a classified image. It is difficult to have both the image of interest, and a high spatial resolution image of the same area taken at the same time. Thus it was studied whether a subsampled image taken from the image of interest could serve as the training data. Statistical work has been done showing the unusefulness of this approach. In the second part of the analysis, a feedforward neural net was trained and used to classify the AVHRR images. Results of these tests, comparing the neural net with typical statistical based schemes are shown.

Figueroa, Ricardo R.↗
DOE OSTI2021

Convolutional Neural Networks Based Remote Sensing Scene Classification under Clear and Cloudy Environments

Remote sensing (RS) scene classification has wide applications in the environmental monitoring and geological survey. In the real-world applications, the RS scene images taken by the satellite might have two scenarios: clear and cloudy environments. However, most of existing methods did not consider these two environments simultaneously. In this paper, we assume that the global and local features are iscriminative in either clear or cloudy environments. Many existing Convolution Neural Networks (CNN) based models have made excellent achievements in the image classification, however they somewhat ignored the global and local features in their network structure. In this paper, we propose a new CNN based network (named GLNet) with the Global Encoder and Local Encoder to extract the discriminative global and local features for the RS scene classification, where the constraints for inter-class dispersion and intra-class compactness are embedded in the GLNet training. The experimental results on two publicized RS scene classification datasets show that the proposed GLNet could achieve better performance based on many existing CNN backbones under both clear and cloudy environments.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1990

Remote Detection and Mapping of Supergene Iron Oxides in the Cripple Creek Mining District, Colorado

The Geophysical and Environmental Research Imaging Spectrometer (GERIS) was flown over the Cripple Creek mining district in south-central Colorado to improve the geological understanding of the district. As part of the study, an airborne mapping technique was developed for the discrimination of the ferric iron minerals hematite, goethite, and jarosite, minerals often important indicators of the distribution of economic mineralization. A software technique was developed which uses the binary encoding of spectral slopes to identify the mineral hematite from the group goethite/jarosite. Mixtures of hematite and goethite can also be detected with GERIS data. The study included district-wide field mapping and spectral measurements to evaluate the accuracy of the image classifications. The ARC/INFO geographic information system (GIS) was a useful tool which allowed quantitative comparison of the field mapping and GERIS image data sets. The study results demonstrate the ability to discriminate individual iron minerals using imaging spectroscopy, and the development of a rapid mapping technique useful in the reconnaissance stage of minerals exploration.

Taranik, D. L.↗
DOE OSTI2023

Experimental Observations of the Topology of Convolutional Neural Network Activations

Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture resulting in high-dimensional, difficult to interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper we apply cutting edge techniques from TDA with the goal of gaining insight towards interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers and discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight as to how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.

topological data analysis, deep learning↗
NASA NTRS1981

Land cover classification accuracy as a function of sensor spatial resolution

The benefits obtained from sensor systems for monitoring earth resources will depend on the application and interpretation methods used. A frequently used analysis method is supervised per-pixel multispectral classification with a typical application being land cover classification. An investigation is conducted to evaluate the effect of spatial resolution on the ability to classify land cover types with per-pixel digital image classification techniques. Attention is also given to the documentation of changes in scene noise and the percentage of boundary pixels as a function of spatial resolution, in order to improve the understanding of the interrelationship between classification accuracy and spatial resolution. It is found that scene noise varies considerably between land cover categories. Changes in scene noise with coarsening resolution occur at different rates for different categories.

Markham, B. L.↗
NASA NTRS1982

Mapping of deciduous forest cover using simulated Landsat-D TM data

An evaluation is presented of the supervised vegetation classification images of heavily forested terrain in the eastern US produced from simulated Landsat-D Thematic Mapper data as part of the Joint NASA/Geosat Test Case study of the Lost River, West Virginia, gas field. This investigation utilized data supplied by the NS-001 aircraft multispectral scanner (15 m IFOV) of NASA. The instruments recognized a total of 9 vegetation classes and one soil class. A hybrid parallelepiped-Bayesian maximum likelihood classifier was employed to produce the supervised vegetation classifications. The data were obtained at the height of the fall foliage display for this portion of West Virginia. Results show that both classifications are highly accurate, based on a comparison of assignment of vegetation classes on each of the images with actual ground conditions. It is noted that the anomalous distribution of certain woody species found in the resulting supervised classifications may be related to the microseepage of methane from the gas reservoir.

Rock, B. N.↗
NASA NTRS1984

Information extraction and transmission techniques for spaceborne synthetic aperture radar images

Information extraction and transmission techniques for synthetic aperture radar (SAR) imagery were investigated. Four interrelated problems were addressed. An optimal tonal SAR image classification algorithm was developed and evaluated. A data compression technique was developed for SAR imagery which is simple and provides a 5:1 compression with acceptable image quality. An optimal textural edge detector was developed. Several SAR image enhancement algorithms have been proposed. The effectiveness of each algorithm was compared quantitatively.

Frost, V. S.↗
DOE OSTI2021

Rotational Equivariance for Object Classification Using xView

With the recent addition of large, curated and labeled data sets to the remote sensing discipline, deep learning models have largely surpassed the performance of classical techniques. These deep models, typically Convolutional Neural Networks, are invariant to translation through the use of successive convolution layers which are themselves equivariant to translation. Further, the combination of multiple convolution and pooling layers means that in practice, the model is also approximately invariant to translation. However, until recently these models could only approach rotational invariance through data augmentation. Here we propose using a new model formulation which achieves rotational equaivariance without data augmentation for overhead imagery classification. We utilize the popular xView data set to compare the rotational equivariance formalization against a regular CNN and CNN with rotational data augmentation for the task of image classification.

Bynum, Lucius EJ↗
NASA NTRS1981

APPLEPIPS /Apple Personal Image Processing System/ - An interactive digital image processing system for the Apple II microcomputer

Recent developments related to microprocessor-based personal computers have made low-cost digital image processing systems a reality. Image analysis systems built around these microcomputers provide color image displays for images as large as 256 by 240 pixels in sixteen colors. Descriptive statistics can be computed for portions of an image, and supervised image classification can be obtained. The systems support Basic, Fortran, Pascal, and assembler language. A description is provided of a system which is representative of the new microprocessor-based image processing systems currently on the market. While small systems may never be truly independent of larger mainframes, because they lack 9-track tape drives, the independent processing power of the microcomputers will help alleviate some of the turn-around time problems associated with image analysis and display on the larger multiuser systems.

Masuoka, E.↗
DOE OSTI2020

Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x-ray image classification with multiple structural attributes. In this paper, we present an interactive system for domain scientists to visually study the multiple attributes learning models applied to x-ray scattering images. It allows domain scientists to interactively explore this important type of scientific images in embedded spaces that are defined on the model prediction output, the actual labels, and the discovered feature space of neural networks. Users are allowed to flexibly select instance images, their clusters, and compare them regarding the specified visual representation of attributes. The exploration is guided by the manifestation of model performance related to mutual relationships among attributes, which often affect the learning accuracy and effectiveness. The system thus supports domain scientists to improve the training dataset and model, find questionable attributes labels, and identify outlier images or spurious data clusters. Case studies and scientists feedback demonstrate its functionalities and usefulness.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors

This software offers methods and functions for training calibrated out-of-distribution detectors for medical image classification tasks. It includes functionalities for training, synthesizing data augmentations, calibration, and out-of-distribution detection. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.

Narayanaswamy, VivekSivaraman↗
DOE OSTI2024

On the nature of apparent transient sources on the National Geographic Society–Palomar Observatory Sky Survey glass copy plates

Abstract We examine critically recent claims for the presence of above-atmosphere optical transients in publicly available digitized scans of Schmidt telescope photographic plate material derived from the National Geographic Society–Palomar Observatory Sky Survey. We employ the publicly available SuperCOSMOS Sky Survey catalogues to examine statistically the morphology of the sources. We develop a simple, objective, and automated image classification scheme based on a random forest decision tree classifier. We find that the putative transients are likely to be spurious artefacts of the photographic emulsion. We suggest a possible cause of the appearance of these images as resulting from the copying procedure employed to disseminate glass copy survey atlas sets in the era before large-scale digitization programmes.

Hambly, N. C. (ORCID:0000000299019064)↗
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 OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2022

Image feature extraction and galaxy classification: a novel and efficient approach with automated machine learning

ABSTRACT In this work, we explore the possibility of applying machine learning methods designed for 1D problems to the task of galaxy image classification. The algorithms used for image classification typically rely on multiple costly steps, such as the point spread function deconvolution and the training and application of complex Convolutional Neural Networks of thousands or even millions of parameters. In our approach, we extract features from the galaxy images by analysing the elliptical isophotes in their light distribution and collect the information in a sequence. The sequences obtained with this method present definite features allowing a direct distinction between galaxy types. Then, we train and classify the sequences with machine learning algorithms, designed through the platform Modulos AutoML. As a demonstration of this method, we use the second public release of the Dark Energy Survey (DES DR2). We show that we are able to successfully distinguish between early-type and late-type galaxies, for images with signal-to-noise ratio greater than 300. This yields an accuracy of $86{{\ \rm per\ cent}}$ for the early-type galaxies and $93{{\ \rm per\ cent}}$ for the late-type galaxies, which is on par with most contemporary automated image classification approaches. The data dimensionality reduction of our novel method implies a significant lowering in computational cost of classification. In the perspective of future data sets obtained with e.g. Euclid and the Vera Rubin Observatory, this work represents a path towards using a well-tested and widely used platform from industry in efficiently tackling galaxy classification problems at the peta-byte scale.

79 ASTRONOMY AND ASTROPHYSICS↗
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.↗