Global ETD Search

441	A Multilinear (Tensor) Algebraic Framework for Computer Graphics, Computer Vision and Machine Learning Vasilescu, M. Alex O. 09 June 2014 (has links) This thesis introduces a multilinear algebraic framework for computer graphics, computer vision, and machine learning, particularly for the fundamental purposes of image synthesis, analysis, and recognition. Natural images result from the multifactor interaction between the imaging process, the scene illumination, and the scene geometry. We assert that a principled mathematical approach to disentangling and explicitly representing these causal factors, which are essential to image formation, is through numerical multilinear algebra, the algebra of higher-order tensors. Our new image modeling framework is based on(i) a multilinear generalization of principal components analysis (PCA), (ii) a novel multilinear generalization of independent components analysis (ICA), and (iii) a multilinear projection for use in recognition that maps images to the multiple causal factor spaces associated with their formation. Multilinear PCA employs a tensor extension of the conventional matrix singular value decomposition (SVD), known as the M-mode SVD, while our multilinear ICA method involves an analogous M-mode ICA algorithm. As applications of our tensor framework, we tackle important problems in computer graphics, computer vision, and pattern recognition; in particular, (i) image-based rendering, specifically introducing the multilinear synthesis of images of textured surfaces under varying view and illumination conditions, a new technique that we call ``TensorTextures'', as well as (ii) the multilinear analysis and recognition of facial images under variable face shape, view, and illumination conditions, a new technique that we call ``TensorFaces''. In developing these applications, we introduce a multilinear image-based rendering algorithm and a multilinear appearance-based recognition algorithm. As a final, non-image-based application of our framework, we consider the analysis, synthesis and recognition of human motion data using multilinear methods, introducing a new technique that we call ``Human Motion Signatures''. multilinear algebra tensor algebra computer vision computer graphics machine learning principal component analysis (PCA) independent component analysis (ICA/BSS) kernel component analysis (KPCA/KICA) local linear embedding multifactor LLE M-mode SVD M-mode PCA M-mode ICA multilinear projection m-mode pseudo-inverse tensor m-mode identity tensor m-mode product genearlization texture synthesis face recognition human motion signatures 0984 0800 0805 0463
442	A Multilinear (Tensor) Algebraic Framework for Computer Graphics, Computer Vision and Machine Learning Vasilescu, M. Alex O. 09 June 2014 (has links) This thesis introduces a multilinear algebraic framework for computer graphics, computer vision, and machine learning, particularly for the fundamental purposes of image synthesis, analysis, and recognition. Natural images result from the multifactor interaction between the imaging process, the scene illumination, and the scene geometry. We assert that a principled mathematical approach to disentangling and explicitly representing these causal factors, which are essential to image formation, is through numerical multilinear algebra, the algebra of higher-order tensors. Our new image modeling framework is based on(i) a multilinear generalization of principal components analysis (PCA), (ii) a novel multilinear generalization of independent components analysis (ICA), and (iii) a multilinear projection for use in recognition that maps images to the multiple causal factor spaces associated with their formation. Multilinear PCA employs a tensor extension of the conventional matrix singular value decomposition (SVD), known as the M-mode SVD, while our multilinear ICA method involves an analogous M-mode ICA algorithm. As applications of our tensor framework, we tackle important problems in computer graphics, computer vision, and pattern recognition; in particular, (i) image-based rendering, specifically introducing the multilinear synthesis of images of textured surfaces under varying view and illumination conditions, a new technique that we call ``TensorTextures'', as well as (ii) the multilinear analysis and recognition of facial images under variable face shape, view, and illumination conditions, a new technique that we call ``TensorFaces''. In developing these applications, we introduce a multilinear image-based rendering algorithm and a multilinear appearance-based recognition algorithm. As a final, non-image-based application of our framework, we consider the analysis, synthesis and recognition of human motion data using multilinear methods, introducing a new technique that we call ``Human Motion Signatures''. multilinear algebra tensor algebra computer vision computer graphics machine learning principal component analysis (PCA) independent component analysis (ICA/BSS) kernel component analysis (KPCA/KICA) local linear embedding multifactor LLE M-mode SVD M-mode PCA M-mode ICA multilinear projection m-mode pseudo-inverse tensor m-mode identity tensor m-mode product genearlization texture synthesis face recognition human motion signatures 0984 0800 0805 0463
443	Getting it right operationalizing civilian capacity for conflict and post-conflict environments. McNaught, James A. January 1900 (has links) "A paper submitted to the faculty of the NWC in partial satisfaction of the requirements of the JMO Department." / Title from title screen (viewed June 10, 2008). "February 14, 2005." Faculty advisor: Douglas Hime. "ADA464898"--URL. Includes bibliographical references (p. 24-27).
444	Elektrische Charakterisierung PLD-gewachsener Zinkoxid-Nanodrähte Zimmermann, Gregor 17 August 2010 (has links) Die vorliegende Arbeit beschäftigt sich mit der elektrischen Charakterisierung von Zinkoxid-Nanodrähten, die mittels gepulster Laserablation (PLD) hergestellt wurden. Ausgehend von den so generierten ZnO-Nanodraht-Ensembles werden Methoden zu deren elektrischer Untersuchung diskutiert und auf praktische Anwendbarkeit hin verglichen. Die entwickelten Methoden werden auf Ensembles von auf n-leitenden ZnO- und ZnO:Ga-Dünnschichten aufgewachsenen Phosphor-dotierten ZnO-Nanodrähten angewendet. Deren reproduzierbares, in Strom–Spannungs- (I–U-) Kennlinien beobachtetes diodenartiges Verhalten wird genauer beleuchtet. Im Zusammenhang mit der elektrischen Charakterisierung einzelner ZnO-Nano-drähte werden experimentelle Methoden zur Vereinzelung und zur Kontaktierung der vereinzelten ZnO-Nanodrähte diskutiert. Dabei werden sowohl etablierte Methoden wie Elektronenstrahllithographie (EBL) als auch neue Techniken wie elektronen- und ionenstrahlinduzierte Deposition (EBID/IBID) und Strom–Spannungs-Rastersondenmikroskopie (I-AFM) behandelt und ihre Eignung für eingehende elektrische Untersuchungen und reproduzierbare Messungen analysiert. Die geeignetsten Methoden werden schließlich eingesetzt, um spezifischen Widerstand sowie Ladungsträgermobilität und -dichte sowohl in nominell undotierten als auch in Aluminium-dotierten ZnO-Nanodrähten zu untersuchen und zu vergleichen. In der Ableitung der physikalischen Materialparameter aus den Messdaten wird dabei besonderes Augenmerk auf die Einbeziehung der geometrischen Besonderheiten der Nanodrähte gegenüber Volumenmaterial- und Dünnschichtproben gelegt. Im Zuge dessen wird unter anderem ein Modell für den elektrischen Widerstand in Nanodrähten mit ihrer Länge nach veränderlichem Querschnitt abgeleitet. info:eu-repo/classification/ddc/537 ddc:537 info:eu-repo/classification/ddc/539 ddc:539
445	Machine Learning for Speech Forensics and Hypersonic Vehicle Applications Emily R Bartusiak (6630773) 06 December 2022 (has links) <p>Synthesized speech may be used for nefarious purposes, such as fraud, spoofing, and misinformation campaigns. We present several speech forensics methods based on deep learning to protect against such attacks. First, we use a convolutional neural network (CNN) and transformers to detect synthesized speech. Then, we investigate closed set and open set speech synthesizer attribution. We use a transformer to attribute a speech signal to its source (i.e., to identify the speech synthesizer that created it). Additionally, we show that our approach separates different known and unknown speech synthesizers in its latent space, even though it has not seen any of the unknown speech synthesizers during training. Next, we explore machine learning for an objective in the aerospace domain.</p> <p><br></p> <p>Compared to conventional ballistic vehicles and cruise vehicles, hypersonic glide vehicles (HGVs) exhibit unprecedented abilities. They travel faster than Mach 5 and maneuver to evade defense systems and hinder prediction of their final destinations. We investigate machine learning for identifying different HGVs and a conic reentry vehicle (CRV) based on their aerodynamic state estimates. We also propose a HGV flight phase prediction method. Inspired by natural language processing (NLP), we model flight phases as “words” and HGV trajectories as “sentences.” Next, we learn a “grammar” from the HGV trajectories that describes their flight phase transition patterns. Given “words” from the initial part of a HGV trajectory and the “grammar”, we predict future “words” in the “sentence” (i.e., future HGV flight phases in the trajectory). We demonstrate that this approach successfully predicts future flight phases for HGV trajectories, especially in scenarios with limited training data. We also show that it can be used in a transfer learning scenario to predict flight phases of HGV trajectories that exhibit new maneuvers and behaviors never seen before during training.</p> Audio processing Computer vision Digital forensics Deep learning machine learning deep learning speech forensics media forensics convolutional neural network transformer convolutional transformer ensemble spectrogram analysis mel spectrogram analysis synthesized speech detection synthesized speech attribution closed set open set t-stochastic neighbor embedding latent space analysis hypersonics hypersonic glide vehicles vehicle classification flight phase prediction stochastic grammar k-nearest neighbors support vector machine probabilistic context-free grammar automatic distillation of structure generalized earley parser transfer learning

Page generated in 0.0453 seconds