View All Items

Title: A STRUCTURAL AND FUNCTIONAL ANALYSIS OF HUMAN BRAIN MRI WITH ATTENTION DEFICIT HYPERACTIVITY DISORDER.
Creator: Watane, Arjun A, Bagci, Ulas, University of Central Florida
Abstract / Description: Attention Deficit Hyperactivity Disorder (ADHD) affects 5-10% of children worldwide. Its effects are mainly behavioral, manifesting in symptoms such as inattention, hyperactivity, and impulsivity. If not monitored and treated, ADHD may adversely affect a child's health, education, and social life. Furthermore, the neurological disorder is currently diagnosed through interviews and opinions of teachers, parents, and physicians. Because this is a subjective method of identifying ADHD, it is...
Show moreAttention Deficit Hyperactivity Disorder (ADHD) affects 5-10% of children worldwide. Its effects are mainly behavioral, manifesting in symptoms such as inattention, hyperactivity, and impulsivity. If not monitored and treated, ADHD may adversely affect a child's health, education, and social life. Furthermore, the neurological disorder is currently diagnosed through interviews and opinions of teachers, parents, and physicians. Because this is a subjective method of identifying ADHD, it is easily prone to error and misdiagnosis. Therefore, there is a clear need to develop an objective diagnostic method for ADHD. The focus of this study is to explore the use of machine language classifiers on information from the brain MRI and fMRI of both ADHD and non-ADHD subjects. The imaging data are preprocessed to remove any intra-subject and inter-subject variation. For both MRI and fMRI, similar preprocessing stages are performed, including normalization, skull stripping, realignment, smoothing, and co-registration. The next step is to extract features from the data. For MRI, anatomical features such as cortical thickness, surface area, volume, and intensity are obtained. For fMRI, region of interest (ROI) correlation coefficients between 116 cortical structures are determined. A large number of image features are collected, yet many of them may include redundant and useless information. Therefore, the features used for training and testing the classifiers are selected in two separate ways, feature ranking and stability selection, and their results are compared. Once the best features from MRI and fMRI are determined, the following classifiers are trained and tested through leave-one-out cross validation, experimenting with varying feature numbers, for each imaging modality and feature selection method: support vector machine, support vector regression, random forest, and elastic net. Thus, there are four experiments (MRI-rank, MRI-stability, fMRI-rank, fMRI-stability) with four classifiers in each for a total of 16 classifiers trained per each feature count attempted. The results of each classifier are the decisions of each subject, ADHD or non-ADHD. Finally, a classifier decision ensemble is created through the combination of the outputs of the best classifiers in a majority voting method that includes results of both the MRI and fMRI classifiers and keeps both feature selection results independent. The results suggest that ADHD is more easily identified through fMRI because the classification accuracies are a lot higher using fMRI data rather than MRI data. Furthermore, significant activity correlation differences exist between the brain's frontal lobe and cerebellum and also the left and right hemispheres among ADHD and non-ADHD subjects. When including MRI decisions with fMRI in the classifier ensemble, performance is boosted to a high ADHD detection accuracy of 96.2%, suggesting that MRI information assists in validating fMRI classification decisions. This study is an important step towards the development of an automatic and objective method for ADHD diagnosis. While more work is needed to externally validate and improve the classification accuracy, new applications of current methods with promising results are introduced here.
Show less
Date Issued: 2017
Identifier: CFH2000203, ucf:45978
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFH2000203

Title: Human Action Detection, Tracking and Segmentation in Videos.
Creator: Tian, Yicong, Shah, Mubarak, Bagci, Ulas, Liu, Fei, Walker, John, University of Central Florida
Abstract / Description: This dissertation addresses the problem of human action detection, human tracking and segmentation in videos. They are fundamental tasks in computer vision and are extremely challenging to solve in realistic videos. We first propose a novel approach for action detection by exploring the generalization of deformable part models from 2D images to 3D spatiotemporal volumes. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to...
Show moreThis dissertation addresses the problem of human action detection, human tracking and segmentation in videos. They are fundamental tasks in computer vision and are extremely challenging to solve in realistic videos. We first propose a novel approach for action detection by exploring the generalization of deformable part models from 2D images to 3D spatiotemporal volumes. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to clutter. This approach deals with detecting action performed by a single person. When there are multiple humans in the scene, humans need to be segmented and tracked from frame to frame before action recognition can be performed. Next, we propose a novel approach for multiple object tracking (MOT) by formulating detection and data association in one framework. Our method allows us to overcome the confinements of data association based MOT approaches, where the performance is dependent on the object detection results provided at input level. We show that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. In this tracker, targets are represented by bounding boxes, which is a coarse representation. However, pixel-wise object segmentation provides fine level information, which is desirable for later tasks. Finally, we propose a tracker that simultaneously solves three main problems: detection, data association and segmentation. This is especially important because the output of each of those three problems are highly correlated and the solution of one can greatly help improve the others. The proposed approach achieves more accurate segmentation results and also helps better resolve typical difficulties in multiple target tracking, such as occlusion, ID-switch and track drifting.
Show less
Date Issued: 2018
Identifier: CFE0007378, ucf:52069
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007378

Title: Design and Motion Control of a Four Degree of Freedom Robotic Needle Guide for MRI-Guided Intervention.
Creator: Zhang, Shihao, Song, Sang-Eun, Xu, Yunjun, Bagci, Ulas, University of Central Florida
Abstract / Description: In the past several MRI compatible robotic needle guide devices for targeted prostate biopsy have been developed. The large and complex structure have been identified as the major limitations of those devices. Such limitations, in addition to complex steps for device to image registration have prevented widespread implementation of MRI-guided prostate biopsy despite the advantages of MRI compared to TRUS. We have designed a compact MRI-guided robotic intervention with the capability to have...
Show moreIn the past several MRI compatible robotic needle guide devices for targeted prostate biopsy have been developed. The large and complex structure have been identified as the major limitations of those devices. Such limitations, in addition to complex steps for device to image registration have prevented widespread implementation of MRI-guided prostate biopsy despite the advantages of MRI compared to TRUS. We have designed a compact MRI-guided robotic intervention with the capability to have angulated insertion to avoid damage to any anatomical feature along the needle path. The system consists of a novel mechanism driven Robotic Needle Guide (RNG). The RNG is a 4-DOF robotic needle manipulator mounted on a Gross Positioning Module (GPM), which is locked on the MRI table. The RNG consists of four parallel stacked disks with an engraved profile path. The rotary motion and positioning of the discs at an angle aids in guiding the biopsy needle. Once a clinician selects a target for needle insertion, the intervention provides possible insertion angles. Then, the most suitable angle is selected by the clinician based on the safest trajectory. The selected target and insertion angle are then computed as control parameters of RNG i.e. the discs are then rotated to the required angle. Insertion is followed by quick confirmation scans to ascertain needle position at all times.
Show less
Date Issued: 2018
Identifier: CFE0007116, ucf:51942
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007116

Title: Visionary Ophthalmics: Confluence of Computer Vision and Deep Learning for Ophthalmology.
Creator: Morley, Dustin, Foroosh, Hassan, Bagci, Ulas, Gong, Boqing, Mohapatra, Ram, University of Central Florida
Abstract / Description: Ophthalmology is a medical field ripe with opportunities for meaningful application of computer vision algorithms. The field utilizes data from multiple disparate imaging techniques, ranging from conventional cameras to tomography, comprising a diverse set of computer vision challenges. Computer vision has a rich history of techniques that can adequately meet many of these challenges. However, the field has undergone something of a revolution in recent times as deep learning techniques have...
Show moreOphthalmology is a medical field ripe with opportunities for meaningful application of computer vision algorithms. The field utilizes data from multiple disparate imaging techniques, ranging from conventional cameras to tomography, comprising a diverse set of computer vision challenges. Computer vision has a rich history of techniques that can adequately meet many of these challenges. However, the field has undergone something of a revolution in recent times as deep learning techniques have sprung into the forefront following advances in GPU hardware. This development raises important questions regarding how to best leverage insights from both modern deep learning approaches and more classical computer vision approaches for a given problem. In this dissertation, we tackle challenging computer vision problems in ophthalmology using methods all across this spectrum. Perhaps our most significant work is a highly successful iris registration algorithm for use in laser eye surgery. This algorithm relies on matching features extracted from the structure tensor and a Gabor wavelet (-) a classically driven approach that does not utilize modern machine learning. However, drawing on insight from the deep learning revolution, we demonstrate successful application of backpropagation to optimize the registration significantly faster than the alternative of relying on finite differences. Towards the other end of the spectrum, we also present a novel framework for improving RANSAC segmentation algorithms by utilizing a convolutional neural network (CNN) trained on a RANSAC-based loss function. Finally, we apply state-of-the-art deep learning methods to solve the problem of pathological fluid detection in optical coherence tomography images of the human retina, using a novel retina-specific data augmentation technique to greatly expand the data set. Altogether, our work demonstrates benefits of applying a holistic view of computer vision, which leverages deep learning and associated insights without neglecting techniques and insights from the previous era.
Show less
Date Issued: 2018
Identifier: CFE0007058, ucf:52001
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007058

Title: End to End Brain Fiber Orientation Estimation Using Deep Learning.
Creator: Puttashamachar, Nandakishore, Bagci, Ulas, Shah, Mubarak, Rahnavard, Nazanin, Sundaram, Kalpathy, University of Central Florida
Abstract / Description: In this work, we explore the various Brain Neuron tracking techniques, one of the most significant applications of Diffusion Tensor Imaging. Tractography is a non-invasive method to analyze underlying tissue micro-structure. Understanding the structure and organization of the tissues facilitates a diagnosis method to identify any aberrations which can occurwithin tissues due to loss of cell functionalities, provides acute information on the occurrences of brain ischemia or stroke, the...
Show moreIn this work, we explore the various Brain Neuron tracking techniques, one of the most significant applications of Diffusion Tensor Imaging. Tractography is a non-invasive method to analyze underlying tissue micro-structure. Understanding the structure and organization of the tissues facilitates a diagnosis method to identify any aberrations which can occurwithin tissues due to loss of cell functionalities, provides acute information on the occurrences of brain ischemia or stroke, the mutation of certain neurological diseases such as Alzheimer, multiple sclerosis and so on. Under all these circumstances, accurate localization of the aberrations in efficient manner can help save a life. Following up with the limitations introduced by the current Tractography techniques such as computational complexity, reconstruction errors during tensor estimation and standardization, we aim to elucidate these limitations through our research findings. We introduce an End to End Deep Learning framework which can accurately estimate the most probable likelihood orientation at each voxel along a neuronal pathway. We use Probabilistic Tractography as our baseline model to obtain the training data and which also serve as a Tractography Gold Standard for our evaluations. Through experiments we show that our Deep Network can do a significant improvement over current Tractography implementations by reducing the run-time complexity to a significant new level. Our architecture also allows for variable sized input DWI signals eliminating the need to worry about memory issues as seen with the traditional techniques. The advantageof this architecture is that it is perfectly desirable to be processed on a cloud setup and utilize the existing multi GPU frameworks to perform whole brain Tractography in minutes rather than hours. The proposed method is a good alternative to the current state of the art orientation estimation technique which we demonstrate across multiple benchmarks.
Show less
Date Issued: 2017
Identifier: CFE0007292, ucf:52156
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007292

Title: A Decision Support Tool for Video Retinal Angiography.
Creator: Laha, Sumit, Bagci, Ulas, Foroosh, Hassan, Song, Sam, University of Central Florida
Abstract / Description: Fluorescein angiogram (FA) is a medical procedure that helps the ophthalmologists to monitor the status of the retinal blood vessels and to diagnose proper treatment. This research is motivated by the necessity of blood vessel segmentation of the retina. Retinal vessel segmentation has been a major challenge and has long drawn the attention of researchers for decades due to the presence of complex blood vessels with varying size, shape, angles and branching pattern of vessels, and non-uniform...
Show moreFluorescein angiogram (FA) is a medical procedure that helps the ophthalmologists to monitor the status of the retinal blood vessels and to diagnose proper treatment. This research is motivated by the necessity of blood vessel segmentation of the retina. Retinal vessel segmentation has been a major challenge and has long drawn the attention of researchers for decades due to the presence of complex blood vessels with varying size, shape, angles and branching pattern of vessels, and non-uniform illumination and huge anatomical variability between subjects. In this thesis, we introduce a new computational tool that combines deep learning based machine learning algorithm and a signal processing based video magnification method to support physicians in analyzing and diagnosing retinal angiogram videos for the first time in the literature.The proposed approach has a pipeline-based architecture containing three phases - image registration for large motion removal from video angiogram, retinal vessel segmentation and video magnification based on the segmented vessels. In image registration phase, we align distorted frames in the FA video using rigid registration approaches. In the next phase, we use baseline capsule based neural networks for retinal vessel segmentation in comparison with the state-of-the-art methods. We move away from traditional convolutional network approaches to capsule networks in this work. This is because, despite being widely used in different computer vision applications, convolutional neural networks suffer from learning ability to understand the object-part relationships, have high computational times due to additive nature of neurons and, loose information in the pooling layer. Although having these drawbacks, we use deep learning methods like U-Net and Tiramisu to measure the performance and accuracy of SegCaps. Lastly, we apply Eulerian video magnification to magnify the subtle changes in the retinal video. In this phase, magnification is applied to segmented videos to visualize the flow of blood in the retinal vessels.
Show less
Date Issued: 2018
Identifier: CFE0007342, ucf:52125
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007342

Title: Optimization Algorithms for Deep Learning Based Medical Image Segmentations.
Creator: Mortazi, Aliasghar, Bagci, Ulas, Shah, Mubarak, Mahalanobis, Abhijit, Pensky, Marianna, University of Central Florida
Abstract / Description: Medical image segmentation is one of the fundamental processes to understand and assess the functionality of different organs and tissues as well as quantifying diseases and helping treatmentplanning. With ever increasing number of medical scans, the automated, accurate, and efficient medical image segmentation is as unmet need for improving healthcare. Recently, deep learn-ing has emerged as one the most powerful methods for almost all image analysis tasks such as segmentation, detection,...
Show moreMedical image segmentation is one of the fundamental processes to understand and assess the functionality of different organs and tissues as well as quantifying diseases and helping treatmentplanning. With ever increasing number of medical scans, the automated, accurate, and efficient medical image segmentation is as unmet need for improving healthcare. Recently, deep learn-ing has emerged as one the most powerful methods for almost all image analysis tasks such as segmentation, detection, and classification and so in medical imaging. In this regard, this dissertation introduces new algorithms to perform medical image segmentation for different (a) imaging modalities, (b) number of objects, (c) dimensionality of images, and (d) under varying labelingconditions. First, we study dimensionality problem by introducing a new 2.5D segmentation engine that can be used in single and multi-object settings. We propose new fusion strategies and loss functions for deep neural networks to generate improved delineations. Later, we expand the proposed idea into 3D and 4D medical images and develop a "budget (computational) friendly"architecture search algorithm to make this process self-contained and fully automated without scarifying accuracy. Instead of manual architecture design, which is often based on plug-in and out and expert experience, the new algorithm provides an automated search of successful segmentation architecture within a short period of time. Finally, we study further optimization algorithms on label noise issue and improve overall segmentation problem by incorporating prior information about label noise and object shape information. We conclude the thesis work by studying different network and hyperparameter optimization settings that are fine-tuned for varying conditions for medical images. Applications are chosen from cardiac scans (images) and efficacy of the proposed algorithms are demonstrated on several data sets publicly available, and independently validated by blind evaluations.
Show less
Date Issued: 2019
Identifier: CFE0007841, ucf:52825
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007841

Title: Learning Algorithms for Fat Quantification and Tumor Characterization.
Creator: Hussein, Sarfaraz, Bagci, Ulas, Shah, Mubarak, Heinrich, Mark, Pensky, Marianna, University of Central Florida
Abstract / Description: Obesity is one of the most prevalent health conditions. About 30% of the world's and over 70% of the United States' adult populations are either overweight or obese, causing an increased risk for cardiovascular diseases, diabetes, and certain types of cancer. Among all cancers, lung cancer is the leading cause of death, whereas pancreatic cancer has the poorest prognosis among all major cancers. Early diagnosis of these cancers can save lives. This dissertation contributes towards the...
Show moreObesity is one of the most prevalent health conditions. About 30% of the world's and over 70% of the United States' adult populations are either overweight or obese, causing an increased risk for cardiovascular diseases, diabetes, and certain types of cancer. Among all cancers, lung cancer is the leading cause of death, whereas pancreatic cancer has the poorest prognosis among all major cancers. Early diagnosis of these cancers can save lives. This dissertation contributes towards the development of computer-aided diagnosis tools in order to aid clinicians in establishing the quantitative relationship between obesity and cancers. With respect to obesity and metabolism, in the first part of the dissertation, we specifically focus on the segmentation and quantification of white and brown adipose tissue. For cancer diagnosis, we perform analysis on two important cases: lung cancer and Intraductal Papillary Mucinous Neoplasm (IPMN), a precursor to pancreatic cancer. This dissertation proposes an automatic body region detection method trained with only a single example. Then a new fat quantification approach is proposed which is based on geometric and appearance characteristics. For the segmentation of brown fat, a PET-guided CT co-segmentation method is presented. With different variants of Convolutional Neural Networks (CNN), supervised learning strategies are proposed for the automatic diagnosis of lung nodules and IPMN. In order to address the unavailability of a large number of labeled examples required for training, unsupervised learning approaches for cancer diagnosis without explicit labeling are proposed. We evaluate our proposed approaches (both supervised and unsupervised) on two different tumor diagnosis challenges: lung and pancreas with 1018 CT and 171 MRI scans respectively. The proposed segmentation, quantification and diagnosis approaches explore the important adiposity-cancer association and help pave the way towards improved diagnostic decision making in routine clinical practice.
Show less
Date Issued: 2018
Identifier: CFE0007196, ucf:52288
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007196

Title: Super Resolution of Wavelet-Encoded Images and Videos.
Creator: Atalay, Vildan, Foroosh, Hassan, Bagci, Ulas, Hughes, Charles, Pensky, Marianna, University of Central Florida
Abstract / Description: In this dissertation, we address the multiframe super resolution reconstruction problem for wavelet-encoded images and videos. The goal of multiframe super resolution is to obtain one or more high resolution images by fusing a sequence of degraded or aliased low resolution images of the same scene. Since the low resolution images may be unaligned, a registration step is required before super resolution reconstruction. Therefore, we first explore in-band (i.e. in the wavelet-domain) image...
Show moreIn this dissertation, we address the multiframe super resolution reconstruction problem for wavelet-encoded images and videos. The goal of multiframe super resolution is to obtain one or more high resolution images by fusing a sequence of degraded or aliased low resolution images of the same scene. Since the low resolution images may be unaligned, a registration step is required before super resolution reconstruction. Therefore, we first explore in-band (i.e. in the wavelet-domain) image registration; then, investigate super resolution.Our motivation for analyzing the image registration and super resolution problems in the wavelet domain is the growing trend in wavelet-encoded imaging, and wavelet-encoding for image/video compression. Due to drawbacks of widely used discrete cosine transform in image and video compression, a considerable amount of literature is devoted to wavelet-based methods. However, since wavelets are shift-variant, existing methods cannot utilize wavelet subbands efficiently. In order to overcome this drawback, we establish and explore the direct relationship between the subbands under a translational shift, for image registration and super resolution. We then employ our devised in-band methodology, in a motion compensated video compression framework, to demonstrate the effective usage of wavelet subbands.Super resolution can also be used as a post-processing step in video compression in order to decrease the size of the video files to be compressed, with downsampling added as a pre-processing step. Therefore, we present a video compression scheme that utilizes super resolution to reconstruct the high frequency information lost during downsampling. In addition, super resolution is a crucial post-processing step for satellite imagery, due to the fact that it is hard to update imaging devices after a satellite is launched. Thus, we also demonstrate the usage of our devised methods in enhancing resolution of pansharpened multispectral images.
Show less
Date Issued: 2017
Identifier: CFE0006854, ucf:51744
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006854

Title: The Identification and Segmentation of Astrocytoma Prior to Critical Mass, by means of a Volumetric/Subregion Regression Analysis of Normal and Neoplastic Brain Tissue.
Creator: Higgins, Lyn, Hughes, Charles, Morrow, Patricia Bockelman, Bagci, Ulas, Lisle, Curtis, University of Central Florida
Abstract / Description: As the underlying cause of Glioblastoma Multiforme (GBM) is presently unclear, this research implements a new approach to identifying and segmenting plausible instances of GBM prior to critical mass. Grade-IV Astrocytoma, or GBM, is an aggressive and malignant cancer arising from star-shaped glial cells, or astrocytes, where the astrocytes, functionally, assist in the support and protection of neurons within the central nervous system and spinal cord. Subsequently, our motivation for...
Show moreAs the underlying cause of Glioblastoma Multiforme (GBM) is presently unclear, this research implements a new approach to identifying and segmenting plausible instances of GBM prior to critical mass. Grade-IV Astrocytoma, or GBM, is an aggressive and malignant cancer arising from star-shaped glial cells, or astrocytes, where the astrocytes, functionally, assist in the support and protection of neurons within the central nervous system and spinal cord. Subsequently, our motivation for researching the ability to recognize GBM is that the underlying cause of the mutation is presently unclear, leading to the operative that GBM is only detectable through a combination of MRI and CT brain scans, cooperatively, along with a resection biopsy. Since astrocytoma only becomes evident at critical mass, when the cellular structure of the neoplasm becomes visible within the image, this research seeks to achieve earlier identification and segmentation of the neoplasm by evaluating the malignant area via a volumetric voxel approach to removing noise artifacts and analyzing voxel differentials. In order to investigate neoplasm continuity, a differential approach has been implemented utilizing a multi-polynomial/multi-domain regression algorithm, thus, ultimately, providing a graphical and mathematical analysis of the differentials within critical mass and non-critical mass images. Given these augmentations to MRI and CT image rectifications, we theorize that our approach will improve on astrocytoma recognition and segmentation, along with achieving greater accuracy in diagnostic evaluations of the malignant area.
Show less
Date Issued: 2018
Identifier: CFE0007336, ucf:52111
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007336

Title: Approximate In-memory computing on RERAMs.
Creator: Khokhar, Salman Anwar, Heinrich, Mark, Leavens, Gary, Yuksel, Murat, Bagci, Ulas, Rahman, Talat, University of Central Florida
Abstract / Description: Computing systems have seen tremendous growth over the past few decades in their capabilities, efficiency, and deployment use cases. This growth has been driven by progress in lithography techniques, improvement in synthesis tools, architectures and power management. However, there is a growing disparity between computing power and the demands on modern computing systems. The standard Von-Neuman architecture has separate data storage and data processing locations. Therefore, it suffers from a...
Show moreComputing systems have seen tremendous growth over the past few decades in their capabilities, efficiency, and deployment use cases. This growth has been driven by progress in lithography techniques, improvement in synthesis tools, architectures and power management. However, there is a growing disparity between computing power and the demands on modern computing systems. The standard Von-Neuman architecture has separate data storage and data processing locations. Therefore, it suffers from a memory-processor communication bottleneck, which is commonly referredto as the 'memory wall'. The relatively slower progress in memory technology compared with processing units has continued to exacerbate the memory wall problem. As feature sizes in the CMOSlogic family reduce further, quantum tunneling effects are becoming more prominent. Simultaneously, chip transistor density is already so high that all transistors cannot be powered up at the same time without violating temperature constraints, a phenomenon characterized as dark-silicon. Coupled with this, there is also an increase in leakage currents with smaller feature sizes, resultingin a breakdown of 'Dennard's' scaling. All these challenges cannot be met without fundamental changes in current computing paradigms. One viable solution is in-memory computing, wherecomputing and storage are performed alongside each other. A number of emerging memory fabrics such as ReRAMS, STT-RAMs, and PCM RAMs are capable of performing logic in-memory.ReRAMs possess high storage density, have extremely low power consumption and a low cost of fabrication. These advantages are due to the simple nature of its basic constituting elements whichallow nano-scale fabrication. We use flow-based computing on ReRAM crossbars for computing that exploits natural sneak paths in those crossbars.Another concurrent development in computing is the maturation of domains that are error resilient while being highly data and power intensive. These include machine learning, pattern recognition,computer vision, image processing, and networking, etc. This shift in the nature of computing workloads has given weight to the idea of (")approximate computing("), in which device efficiency is improved by sacrificing tolerable amounts of accuracy in computation. We present a mathematically rigorous foundation for the synthesis of approximate logic and its mapping to ReRAM crossbars using search based and graphical methods.
Show less
Date Issued: 2019
Identifier: CFE0007827, ucf:52817
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007827

Title: Estimation and clustering in statistical ill-posed linear inverse problems.
Creator: Rajapakshage, Rasika, Pensky, Marianna, Swanson, Jason, Zhang, Teng, Bagci, Ulas, Foroosh, Hassan, University of Central Florida
Abstract / Description: The main focus of the dissertation is estimation and clustering in statistical ill-posed linear inverse problems. The dissertation deals with a problem of simultaneously estimating a collection of solutions of ill-posed linear inverse problems from their noisy images under an operator that does not have a bounded inverse, when the solutions are related in a certain way. The dissertation defense consists of three parts. In the first part, the collection consists of measurements of temporal...
Show moreThe main focus of the dissertation is estimation and clustering in statistical ill-posed linear inverse problems. The dissertation deals with a problem of simultaneously estimating a collection of solutions of ill-posed linear inverse problems from their noisy images under an operator that does not have a bounded inverse, when the solutions are related in a certain way. The dissertation defense consists of three parts. In the first part, the collection consists of measurements of temporal functions at various spatial locations. In particular, we studythe problem of estimating a three-dimensional function based on observations of its noisy Laplace convolution. In the second part, we recover classes of similar curves when the class memberships are unknown. Problems of this kind appear in many areas of application where clustering is carried out at the pre-processing step and then the inverse problem is solved for each of the cluster averages separately. As a result, the errors of the procedures are usually examined for the estimation step only. In both parts, we construct the estimators, study their minimax optimality and evaluate their performance via a limited simulation study. In the third part, we propose a new computational platform to better understand the patterns of R-fMRI by taking into account the challenge of inevitable signal fluctuations and interpretthe success of dynamic functional connectivity approaches. Towards this, we revisit an auto-regressive and vector auto-regressive signal modeling approach for estimating temporal changes of the signal in brain regions. We then generate inverse covariance matrices fromthe generated windows and use a non-parametric statistical approach to select significant features. Finally, we use Lasso to perform classification of the data. The effectiveness of theproposed method is evidenced in the classification of R-fMRI scans
Show less
Date Issued: 2019
Identifier: CFE0007710, ucf:52450
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007710

Title: Synergistic Visualization And Quantitative Analysis Of Volumetric Medical Images.
Creator: Torosdagli, Neslisah, Bagci, Ulas, Hughes, Charles, Jha, Sumit Kumar, Lisle, Curtis, University of Central Florida
Abstract / Description: The medical diagnosis process starts with an interview with the patient, and continues with the physical exam. In practice, the medical professional may require additional screenings to precisely diagnose. Medical imaging is one of the most frequently used non-invasive screening methods to acquire insight of human body. Medical imaging is not only essential for accurate diagnosis, but also it can enable early prevention. Medical data visualization refers to projecting the medical data into a...
Show moreThe medical diagnosis process starts with an interview with the patient, and continues with the physical exam. In practice, the medical professional may require additional screenings to precisely diagnose. Medical imaging is one of the most frequently used non-invasive screening methods to acquire insight of human body. Medical imaging is not only essential for accurate diagnosis, but also it can enable early prevention. Medical data visualization refers to projecting the medical data into a human understandable format at mediums such as 2D or head-mounted displays without causing any interpretation which may lead to clinical intervention. In contrast to the medical visualization, quantification refers to extracting the information in the medical scan to enable the clinicians to make fast and accurate decisions.Despite the extraordinary process both in medical visualization and quantitative radiology, efforts to improve these two complementary fields are often performed independently and synergistic combination is under-studied. Existing image-based software platforms mostly fail to be used in routine clinics due to lack of a unified strategy that guides clinicians both visually and quan- titatively. Hence, there is an urgent need for a bridge connecting the medical visualization and automatic quantification algorithms in the same software platform. In this thesis, we aim to fill this research gap by visualizing medical images interactively from anywhere, and performing a fast, accurate and fully-automatic quantification of the medical imaging data. To end this, we propose several innovative and novel methods. Specifically, we solve the following sub-problems of the ul- timate goal: (1) direct web-based out-of-core volume rendering, (2) robust, accurate, and efficient learning based algorithms to segment highly pathological medical data, (3) automatic landmark- ing for aiding diagnosis and surgical planning and (4) novel artificial intelligence algorithms to determine the sufficient and necessary data to derive large-scale problems.
Show less
Date Issued: 2019
Identifier: CFE0007541, ucf:52593
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007541

Title: Spatiotemporal Graphs for Object Segmentation and Human Pose Estimation in Videos.
Creator: Zhang, Dong, Shah, Mubarak, Qi, GuoJun, Bagci, Ulas, Yun, Hae-Bum, University of Central Florida
Abstract / Description: Images and videos can be naturally represented by graphs, with spatial graphs for images and spatiotemporal graphs for videos. However, for different applications, there are usually different formulations of the graphs, and algorithms for each formulation have different complexities. Therefore, wisely formulating the problem to ensure an accurate and efficient solution is one of the core issues in Computer Vision research. We explore three problems in this domain to demonstrate how to...
Show moreImages and videos can be naturally represented by graphs, with spatial graphs for images and spatiotemporal graphs for videos. However, for different applications, there are usually different formulations of the graphs, and algorithms for each formulation have different complexities. Therefore, wisely formulating the problem to ensure an accurate and efficient solution is one of the core issues in Computer Vision research. We explore three problems in this domain to demonstrate how to formulate all of these problems in terms of spatiotemporal graphs and obtain good and efficient solutions.The first problem we explore is video object segmentation. The goal is to segment the primary moving objects in the videos. This problem is important for many applications, such as content based video retrieval, video summarization, activity understanding and targeted content replacement. In our framework, we use object proposals, which are object-like regions obtained by low-level visual cues. Each object proposal has an object-ness score associated with it, which indicates how likely this object proposal corresponds to an object. The problem is formulated as a directed acyclic graph, for which nodes represent the object proposals and edges represent the spatiotemporal relationship between nodes. A dynamic programming solution is employed to select one object proposal from each video frame, while ensuring their consistency throughout the video frames. Gaussian mixture models (GMMs) are used for modeling the background and foreground, and Markov Random Fields (MRFs) are employed to smooth the pixel-level segmentation.In the above spatiotemporal graph formulation, we consider the object segmentation in only single video. Next, we consider multiple videos and model the video co-segmentation problem as a spatiotemporal graph. The goal here is to simultaneously segment the moving objects from multiple videos and assign common objects the same labels. The problem is formulated as a regulated maximum clique problem using object proposals. The object proposals are tracked in adjacent frames to generate a pool of candidate tracklets. Then an undirected graph is built with the nodes corresponding to the tracklets from all the videos and edges representing the similarities between the tracklets. A modified Bron-Kerbosch Algorithm is applied to the graph in order to select the prominent objects contained in these videos, hence relate the segmentation of each object in different videos.In online and surveillance videos, the most important object class is the human. In contrast to generic video object segmentation and co-segmentation, specific knowledge about humans, which is defined by a pose (i.e. human skeleton), can be employed to help the segmentation and tracking of people in the videos. We formulate the problem of human pose estimation in videos using the spatiotemporal graph. In this formulation, the nodes represent different body parts in the video frames and edges represent the spatiotemporal relationship between body parts in adjacent frames. The graph is carefully designed to ensure an exact and efficient solution. The overall objective for the new formulation is to remove the simple cycles from the traditional graph-based formulations. Dynamic programming is employed in different stages in the method to select the best tracklets and human pose configurations
Show less
Date Issued: 2016
Identifier: CFE0006429, ucf:51488
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006429

Title: Weakly Labeled Action Recognition and Detection.
Creator: Sultani, Waqas, Shah, Mubarak, Bagci, Ulas, Qi, GuoJun, Yun, Hae-Bum, University of Central Florida
Abstract / Description: Research in human action recognition strives to develop increasingly generalized methods thatare robust to intra-class variability and inter-class ambiguity. Recent years have seen tremendousstrides in improving recognition accuracy on ever larger and complex benchmark datasets, comprisingrealistic actions (")in the wild(") videos. Unfortunately, the all-encompassing, dense, globalrepresentations that bring about such improvements often benefit from the inherent characteristics,specific to...
Show moreResearch in human action recognition strives to develop increasingly generalized methods thatare robust to intra-class variability and inter-class ambiguity. Recent years have seen tremendousstrides in improving recognition accuracy on ever larger and complex benchmark datasets, comprisingrealistic actions (")in the wild(") videos. Unfortunately, the all-encompassing, dense, globalrepresentations that bring about such improvements often benefit from the inherent characteristics,specific to datasets and classes, that do not necessarily reflect knowledge about the entity to berecognized. This results in specific models that perform well within datasets but generalize poorly.Furthermore, training of supervised action recognition and detection methods need several precisespatio-temporal manual annotations to achieve good recognition and detection accuracy. For instance,current deep learning architectures require millions of accurately annotated videos to learnrobust action classifiers. However, these annotations are quite difficult to achieve.In the first part of this dissertation, we explore the reasons for poor classifier performance whentested on novel datasets, and quantify the effect of scene backgrounds on action representationsand recognition. We attempt to address the problem of recognizing human actions while trainingand testing on distinct datasets when test videos are neither labeled nor available during training. Inthis scenario, learning of a joint vocabulary, or domain transfer techniques are not applicable. Weperform different types of partitioning of the GIST feature space for several datasets and computemeasures of background scene complexity, as well as, for the extent to which scenes are helpfulin action classification. We then propose a new process to obtain a measure of confidence in eachpixel of the video being a foreground region using motion, appearance, and saliency together in a3D-Markov Random Field (MRF) based framework. We also propose multiple ways to exploit theforeground confidence: to improve bag-of-words vocabulary, histogram representation of a video,and a novel histogram decomposition based representation and kernel.iiiThe above-mentioned work provides probability of each pixel being belonging to the actor, however,it does not give the precise spatio-temporal location of the actor. Furthermore, above frameworkwould require precise spatio-temporal manual annotations to train an action detector. However,manual annotations in videos are laborious, require several annotators and contain humanbiases. Therefore, in the second part of this dissertation, we propose a weakly labeled approachto automatically obtain spatio-temporal annotations of actors in action videos. We first obtain alarge number of action proposals in each video. To capture a few most representative action proposalsin each video and evade processing thousands of them, we rank them using optical flow andsaliency in a 3D-MRF based framework and select a few proposals using MAP based proposal subsetselection method. We demonstrate that this ranking preserves the high-quality action proposals.Several such proposals are generated for each video of the same action. Our next challenge is toiteratively select one proposal from each video so that all proposals are globally consistent. Weformulate this as Generalized Maximum Clique Graph problem (GMCP) using shape, global andfine-grained similarity of proposals across the videos. The output of our method is the most actionrepresentative proposals from each video. Using our method can also annotate multiple instancesof the same action in a video can also be annotated. Moreover, action detection experiments usingannotations obtained by our method and several baselines demonstrate the superiority of ourapproach.The above-mentioned annotation method uses multiple videos of the same action. Therefore, inthe third part of this dissertation, we tackle the problem of spatio-temporal action localization in avideo, without assuming the availability of multiple videos or any prior annotations. The action islocalized by employing images downloaded from the Internet using action label. Given web images,we first dampen image noise using random walk and evade distracting backgrounds withinimages using image action proposals. Then, given a video, we generate multiple spatio-temporalaction proposals. We suppress camera and background generated proposals by exploiting opticalivflow gradients within proposals. To obtain the most action representative proposals, we propose toreconstruct action proposals in the video by leveraging the action proposals in images. Moreover,we preserve the temporal smoothness of the video and reconstruct all proposal bounding boxesjointly using the constraints that push the coefficients for each bounding box toward a commonconsensus, thus enforcing the coefficient similarity across multiple frames. We solve this optimizationproblem using the variant of two-metric projection algorithm. Finally, the video proposalthat has the lowest reconstruction cost and is motion salient is used to localize the action. Ourmethod is not only applicable to the trimmed videos, but it can also be used for action localizationin untrimmed videos, which is a very challenging problem.Finally, in the third part of this dissertation, we propose a novel approach to generate a few properlyranked action proposals from a large number of noisy proposals. The proposed approach beginswith dividing each proposal into sub-proposals. We assume that the quality of proposal remainsthe same within each sub-proposal. We, then employ a graph optimization method to recombinethe sub-proposals in all action proposals in a single video in order to optimally build new actionproposals and rank them by the combined node and edge scores. For an untrimmed video, we firstdivide the video into shots and then make the above-mentioned graph within each shot. Our methodgenerates a few ranked proposals that can be better than all the existing underlying proposals. Ourexperimental results validated that the properly ranked action proposals can significantly boostaction detection results.Our extensive experimental results on different challenging and realistic action datasets, comparisonswith several competitive baselines and detailed analysis of each step of proposed methodsvalidate the proposed ideas and frameworks.
Show less
Date Issued: 2017
Identifier: CFE0006801, ucf:51809
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006801

Title: Visual Saliency Detection and Semantic Segmentation.
Creator: Souly, Nasim, Shah, Mubarak, Bagci, Ulas, Qi, GuoJun, Pensky, Marianna, University of Central Florida
Abstract / Description: Visual saliency is the ability to select the most relevant data in the scene and reduce the amount of data that needs to be processed. We propose a novel unsupervised approach to detect visual saliency in videos. For this, we employ a hierarchical segmentation technique to obtain supervoxels of a video, and simultaneously, we build a dictionary from cuboids of the video. Then we create a feature matrix from coefficients of dictionary elements. Next, we decompose this matrix into sparse and...
Show moreVisual saliency is the ability to select the most relevant data in the scene and reduce the amount of data that needs to be processed. We propose a novel unsupervised approach to detect visual saliency in videos. For this, we employ a hierarchical segmentation technique to obtain supervoxels of a video, and simultaneously, we build a dictionary from cuboids of the video. Then we create a feature matrix from coefficients of dictionary elements. Next, we decompose this matrix into sparse and redundant parts and obtain salient regions using group lasso. Our experiments provide promising results in terms of predicting eye movement. Moreover, we apply our method on action recognition task and achieve better results. Saliency detection only highlights important regions, in Semantic Segmentation, the aim is to assign a semantic label to each pixel in the image. Even though semantic segmentation can be achieved by simply applying classifiers to each pixel or a region, the results may not be desirable since general context information is not considered. To address this issue, we propose two supervised methods. First, an approach to discover interactions between labels and regions using a sparse estimation of precision matrix obtained by graphical lasso. Second, a knowledge-based method to incorporate dependencies among regions in the image during inference. High-level knowledge rules - such as co-occurrence- are extracted from training data and transformed into constraints in Integer Programming formulation. A difficulty in the most supervised semantic segmentation approaches is the lack of enough training data. To address this, a semi-supervised learning approach to exploit the plentiful amount of available unlabeled,as well as synthetic images generated via Generative Adversarial Networks (GAN), is presented. Furthermore, an extension of the proposed model to use additional weakly labeled data is proposed. We demonstrate our approaches on three challenging bench-marking datasets
Show less
Date Issued: 2017
Identifier: CFE0006918, ucf:51694
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006918

Title: Online, Supervised and Unsupervised Action Localization in Videos.
Creator: Soomro, Khurram, Shah, Mubarak, Heinrich, Mark, Hu, Haiyan, Bagci, Ulas, Yun, Hae-Bum, University of Central Florida
Abstract / Description: Action recognition classifies a given video among a set of action labels, whereas action localization determines the location of an action in addition to its class. The overall aim of this dissertation is action localization. Many of the existing action localization approaches exhaustively search (spatially and temporally) for an action in a video. However, as the search space increases with high resolution and longer duration videos, it becomes impractical to use such sliding window...
Show moreAction recognition classifies a given video among a set of action labels, whereas action localization determines the location of an action in addition to its class. The overall aim of this dissertation is action localization. Many of the existing action localization approaches exhaustively search (spatially and temporally) for an action in a video. However, as the search space increases with high resolution and longer duration videos, it becomes impractical to use such sliding window techniques. The first part of this dissertation presents an efficient approach for localizing actions by learning contextual relations between different video regions in training. In testing, we use the context information to estimate the probability of each supervoxel belonging to the foreground action and use Conditional Random Field (CRF) to localize actions. In the above method and typical approaches to this problem, localization is performed in an offline manner where all the video frames are processed together. This prevents timely localization and prediction of actions/interactions - an important consideration for many tasks including surveillance and human-machine interaction. Therefore, in the second part of this dissertation we propose an online approach to the challenging problem of localization and prediction of actions/interactions in videos. In this approach, we use human poses and superpixels in each frame to train discriminative appearance models and perform online prediction of actions/interactions with Structural SVM. Above two approaches rely on human supervision in the form of assigning action class labels to videos and annotating actor bounding boxes in each frame of training videos. Therefore, in the third part of this dissertation we address the problem of unsupervised action localization. Given unlabeled videos without annotations, this approach aims at: 1) Discovering action classes using a discriminative clustering approach, and 2) Localizing actions using a variant of Knapsack problem.
Show less
Date Issued: 2017
Identifier: CFE0006917, ucf:51685
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006917

Title: Global Data Association for Multiple Pedestrian Tracking.
Creator: Dehghan, Afshin, Shah, Mubarak, Qi, GuoJun, Bagci, Ulas, Zhang, Shaojie, Zheng, Qipeng, University of Central Florida
Abstract / Description: Multi-object tracking is one of the fundamental problems in computer vision. Almost all multi-object tracking systems consist of two main components; detection and data association. In the detection step, object hypotheses are generated in each frame of a sequence. Later, detections that belong to the same target are linked together to form final trajectories. The latter step is called data association. There are several challenges that render this problem difficult, such as occlusion,...
Show moreMulti-object tracking is one of the fundamental problems in computer vision. Almost all multi-object tracking systems consist of two main components; detection and data association. In the detection step, object hypotheses are generated in each frame of a sequence. Later, detections that belong to the same target are linked together to form final trajectories. The latter step is called data association. There are several challenges that render this problem difficult, such as occlusion, background clutter and pose changes. This dissertation aims to address these challenges by tackling the data association component of tracking and contributes three novel methods for solving data association. Firstly, this dissertation will present a new framework for multi-target tracking that uses a novel data association technique using the Generalized Maximum Clique Problem (GMCP) formulation. The majority of current methods, such as bipartite matching, incorporate a limited temporal locality of the sequence into the data association problem. This makes these methods inherently prone to ID-switches and difficulties caused by long-term occlusions, a cluttered background and crowded scenes. On the other hand, our approach incorporates both motion and appearance in a global manner. Unlike limited temporal locality methods which incorporate a few frames into the data association problem, this method incorporates the whole temporal span and solves the data association problem for one object at a time. Generalized Minimum Clique Graph (GMCP) is used to solve the optimization problem of our data association method. The proposed method is supported by superior results on several benchmark sequences. GMCP leads us to a more accurate approach to multi-object tracking by considering all the pairwise relationships in a batch of frames; however, it has some limitations. Firstly, it finds target trajectories one-by-one, missing joint optimization. Secondly, for optimization we use a greedy solver, based on local neighborhood search, making our optimization prone to local minimas. Finally GMCP tracker is slow, which is a burden when dealing with time-sensitive applications. In order to address these problems, we propose a new graph theoretic problem, called Generalized Maximum Multi Clique Problem (GMMCP). GMMCP tracker has all the advantages of the GMCP tracker while addressing its limitations. A solution is presented to GMMCP where no simplification is assumed in problem formulation or problem optimization. GMMCP is NP hard but it can be formulated through a Binary-Integer Program where the solution to small- and medium-sized tracking problems can be found efficiently. To improve speed, Aggregated Dummy Nodes are used for modeling occlusions and miss detections. This also reduces the size of the input graph without using any heuristics. We show that using the speed-up method, our tracker lends itself to a real-time implementation, increasing its potential usefulness in many applications. In test against several tracking datasets, we show that the proposed method outperforms competitive methods. Thus far we have assumed that the number of people do not exceed a few dozens. However, this is not always the case. In many scenarios such as, marathon, political rallies or religious rites, the number of people in a frame may reach few hundreds or even few thousands. Tracking in high-density crowd sequences is a challenging problem due to several reasons. Human detection methods often fail to localize objects correctly in extremely crowded scenes. This limits the use of data association based tracking methods. Additionally, it is hard to extend existing multi-target tracking to track targets in highly-crowded scenes, because the large number of targets increases the computational complexity. Furthermore, the small apparent target size makes it challenging to extract features to discriminate targets from their surroundings. Finally, we present a tracker that addresses the above-mentioned problems. We formulate online crowd tracking as a Binary Quadratic Programing, where both detection and data association problems are solved together. Our formulation employs target's individual information in the form of appearance and motion as well as contextual cues in the form of neighborhood motion, spatial proximity and grouping constraints. Due to large number of targets, state-of-the-art commercial quadratic programing solvers fail to efficiently find the solution to the proposed optimization. In order to overcome the computational complexity of available solvers, we propose to use the most recent version of Modified Frank-Wolfe algorithms with SWAP steps. The proposed tracker can track hundreds of targets efficiently and improves state-of-the-art results by significant margin on high density crowd sequences.
Show less
Date Issued: 2016
Identifier: CFE0006095, ucf:51201
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006095

Title: Signal processing with Fourier analysis, novel algorithms and applications.
Creator: Syed, Alam, Foroosh, Hassan, Sun, Qiyu, Bagci, Ulas, Rahnavard, Nazanin, Atia, George, Katsevich, Alexander, University of Central Florida
Abstract / Description: Fourier analysis is the study of the way general functions may be represented or approximatedby sums of simpler trigonometric functions, also analogously known as sinusoidal modeling. Theoriginal idea of Fourier had a profound impact on mathematical analysis, physics, and engineeringbecause it diagonalizes time-invariant convolution operators. In the past signal processing was atopic that stayed almost exclusively in electrical engineering, where only the experts could cancelnoise, compress...
Show moreFourier analysis is the study of the way general functions may be represented or approximatedby sums of simpler trigonometric functions, also analogously known as sinusoidal modeling. Theoriginal idea of Fourier had a profound impact on mathematical analysis, physics, and engineeringbecause it diagonalizes time-invariant convolution operators. In the past signal processing was atopic that stayed almost exclusively in electrical engineering, where only the experts could cancelnoise, compress and reconstruct signals. Nowadays it is almost ubiquitous, as everyone now dealswith modern digital signals.Medical imaging, wireless communications and power systems of the future will experience moredata processing conditions and wider range of applications requirements than the systems of today.Such systems will require more powerful, efficient and flexible signal processing algorithms thatare well designed to handle such needs. No matter how advanced our hardware technology becomeswe will still need intelligent and efficient algorithms to address the growing demands in signalprocessing. In this thesis, we investigate novel techniques to solve a suite of four fundamentalproblems in signal processing that have a wide range of applications. The relevant equations, literatureof signal processing applications, analysis and final numerical algorithms/methods to solvethem using Fourier analysis are discussed for different applications in the electrical engineering /computer science. The first four chapters cover the following topics of central importance in thefield of signal processing: Fast Phasor Estimation using Adaptive Signal Processing (Chapter 2) Frequency Estimation from Nonuniform Samples (Chapter 3) 2D Polar and 3D Spherical Polar Nonuniform Discrete Fourier Transform (Chapter 4)iv Robust 3D registration using Spherical Polar Discrete Fourier Transform and Spherical Harmonics(Chapter 5)Even though each of these four methods discussed may seem completely disparate, the underlyingmotivation for more efficient processing by exploiting the Fourier domain signal structureremains the same. The main contribution of this thesis is the innovation in the analysis, synthesis, discretization of certain well-known problems like phasor estimation, frequency estimation, computations of a particular non-uniform Fourier transform and signal registration on the transformed domain. We conduct propositions and evaluations of certain applications relevant algorithms suchas, frequency estimation algorithm using non-uniform sampling, polar and spherical polar Fourier transform. The techniques proposed are also useful in the field of computer vision and medical imaging. From a practical perspective, the proposed algorithms are shown to improve the existing solutions in the respective fields where they are applied/evaluated. The formulation and final proposition is shown to have a variety of benefits. Future work with potentials in medical imaging, directional wavelets, volume rendering, video/3D object classifications, high dimensional registration are also discussed in the final chapter. Finally, in the spirit of reproducible research, we release the implementation of these algorithms to the public using Github.
Show less
Date Issued: 2017
Identifier: CFE0006803, ucf:51775
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006803

Deep Learning (3)	+ -
Machine Learning (3)	+ -
Computer Vision (2)	+ -
Radiology (2)	+ -
deep learning (2)	+ -

segmentation (2)	+ -
video object segmentation (2)	+ -
3D noise reduction (1)	+ -
ADHD (1)	+ -
Action Detection (1)	+ -
Action Localization (1)	+ -
Action Recognition (1)	+ -
Biopsy Needle Guide (1)	+ -
Brain Neuron Connection (1)	+ -
Cancer (1)	+ -
Cancer Diagnosis (1)	+ -
Capsule networks (1)	+ -
Constrained Integer Programming (1)	+ -
Deep learning (1)	+ -
Diffusion Tensor Imaging (1)	+ -
Discrete Wavelet Transform (1)	+ -
Dynamic Contrast Enhanced imaging (1)	+ -
Eulerian video magnification (1)	+ -
Fluorescein angiogram (1)	+ -
Frequency Estimation (1)	+ -
Functional Laplace deconvolution (1)	+ -
GAN (1)	+ -
GBM (1)	+ -
GBM simulation (1)	+ -
Generative Adversarial Networks (1)	+ -

ETD Collection (18)	+ -
Honors Collection (1)	+ -

Bagci, Ulas (19)	+ -
University of Central Florida (19)	+ -
Shah, Mubarak (9)	+ -
Foroosh, Hassan (5)	+ -
Pensky, Marianna (5)	+ -

Qi, GuoJun (4)	+ -
Heinrich, Mark (3)	+ -
Hughes, Charles (3)	+ -
Yun, Hae-Bum (3)	+ -
Lisle, Curtis (2)	+ -
Rahnavard, Nazanin (2)	+ -
Atalay, Vildan (1)	+ -
Atia, George (1)	+ -
Dehghan, Afshin (1)	+ -
Gong, Boqing (1)	+ -
Higgins, Lyn (1)	+ -
Hu, Haiyan (1)	+ -
Hussein, Sarfaraz (1)	+ -
Jha, Sumit Kumar (1)	+ -
Katsevich, Alexander (1)	+ -
Khokhar, Salman Anwar (1)	+ -
Laha, Sumit (1)	+ -
Leavens, Gary (1)	+ -
Liu, Fei (1)	+ -
Mahalanobis, Abhijit (1)	+ -
Mohapatra, Ram (1)	+ -
Morley, Dustin (1)	+ -
Morrow, Patricia Bockelman (1)	+ -
Mortazi, Aliasghar (1)	+ -
Puttashamachar, Nandakishore (1)	+ -

Search In

Sort Results By:

Narrow results by:

Topical Subject

Collection

Type of Resource

Language

Creator

Format

Owner