Current Search: vision (x)
Pages
-
-
Title
-
"BUT THIS IS WHAT I SEE; THIS IS WHAT I SEE": RE-IMAGINING GENDERED SUBJECTIVITY THROUGH THE WOMAN ARTIST IN PHELPS, JOHNSTONE, AND WOOLF.
-
Creator
-
Wayne, Heather, Jones, Anna, University of Central Florida
-
Abstract / Description
-
Since the publication of Laura MulveyÃÂ's influential article ÃÂ"Visual Pleasure and Narrative Cinema,ÃÂ" in which she identifies the pervasive presence of the male gaze in Hollywood cinema, scholars have sought to account for the female spectator in her paradigm of gendered vision. This thesis suggests that women writers have long debated the problem of the female spectator through literary depictions of the female artist. Women...
Show moreSince the publication of Laura MulveyÃÂ's influential article ÃÂ"Visual Pleasure and Narrative Cinema,ÃÂ" in which she identifies the pervasive presence of the male gaze in Hollywood cinema, scholars have sought to account for the female spectator in her paradigm of gendered vision. This thesis suggests that women writers have long debated the problem of the female spectator through literary depictions of the female artist. Women writers of the nineteenth and twentieth centuriesÃÂ--including Elizabeth Stuart Phelps, Edith Johnstone, and Virginia WoolfÃÂ--recognized the power of the woman artist to undermine the trope of the male gazing subject and a passive female object. Examining PhelpsÃÂ's The Story of Avis (1877), JohnstoneÃÂ's A Sunless Heart (1894), and WoolfÃÂ's To the Lighthouse (1927) illustrates how the woman artistÃÂ's active vision disrupts MulveyÃÂ's ÃÂ"active/male and passive/femaleÃÂ" binary of vision. PhelpsÃÂ's painter-heroine Avis destabilizes the power of the male gaze not only by exerting her own vision, but also by acting as an active object to manipulate the way she is seen. Johnstone uses artist Gasparine to demonstrate the dangers of vision shaped by either aesthetic or political conventions, suggesting that even feminist idealism can promote the objectification of its heroines. Finally, Woolf redefines the terms of objectification through painter Lily Briscoe, whose vision imbues material objects with subjectivity, thereby going beyond the boundaries between male and female to blur the distinction between subject and object. Through their novels, Phelps, Johnstone, and Woolf suggest that depictions of human experience need to be radically re-thought in order to adequately represent the complexity of subjectivity.
Show less
-
Date Issued
-
2010
-
Identifier
-
CFE0003291, ucf:48491
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0003291
-
-
Title
-
A Historical Analysis of the Evolution of the Administrative and Organizational Structure of the University of Central Florida as it Relates to Growth.
-
Creator
-
Lindsley, Boyd, Murray, Barbara, Doherty, Walter, Murray, Kenneth, Dziuban, Charles, University of Central Florida
-
Abstract / Description
-
This was a qualitative historical study, which was recounted chronologically and organized around the terms of the four full-time presidents of the university. The review addressed the processes associated with the establishment and development of Florida Technological University beginning in 1963 through its name change to the University of Central Florida in 1979, concluding in 2013. The organization's mission, vision, and goals, how they evolved and the impact they had on the university...
Show moreThis was a qualitative historical study, which was recounted chronologically and organized around the terms of the four full-time presidents of the university. The review addressed the processes associated with the establishment and development of Florida Technological University beginning in 1963 through its name change to the University of Central Florida in 1979, concluding in 2013. The organization's mission, vision, and goals, how they evolved and the impact they had on the university were of particular interest. The study was focused on the administrative actions and organizational changes that took place within the university to assist faculty in teaching, research, and service as well as external conditions and events which impacted the university and shaped its development. The growth of the university, as well as the productivity of the faculty, were of interest in the study.
Show less
-
Date Issued
-
2015
-
Identifier
-
CFE0005650, ucf:50187
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0005650
-
-
Title
-
A Study of Localization and Latency Reduction for Action Recognition.
-
Creator
-
Masood, Syed, Tappen, Marshall, Foroosh, Hassan, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
-
Abstract / Description
-
The success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this...
Show moreThe success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning system parameters or by selecting better feature points. Instead, we show that the problem lies in the spatio-temporal cuboid volume extracted from the interest point locations. Having identified the problem, we show how improved results can be achieved by simple modifications to the cuboids.For the above method however, one requires near-perfect localization of the action within a video sequence. To achieve this objective, we present a two stage weakly supervised probabilistic model for simultaneous localization and recognition of actions in videos. Different from previous approaches, our method is novel in that it (1) eliminates the need for manual annotations for the training procedure and (2) does not require any human detection or tracking in the classification stage. The first stage of our framework is a probabilistic action localization model which extracts the most promising sub-windows in a video sequence where an action can take place. We use a non-linear classifier in the second stage of our framework for the final classification task. We show the effectiveness of our proposed model on two well known real-world datasets: UCF Sports and UCF11 datasets.Another application of the weakly supervised probablistic model proposed above is in the gaming environment. An important aspect in designing interactive, action-based interfaces is reliably recognizing actions with minimal latency. High latency causes the system's feedback to lag behind and thus significantly degrade the interactivity of the user experience. With slight modification to the weakly supervised probablistic model we proposed for action localization, we show how it can be used for reducing latency when recognizing actions in Human Computer Interaction (HCI) environments. This latency-aware learning formulation trains a logistic regression-based classifier that automatically determines distinctive canonical poses from the data and uses these to robustly recognize actions in the presence of ambiguous poses. We introduce a novel (publicly released) dataset for the purpose of our experiments. Comparisons of our method against both a Bag of Words and a Conditional Random Field (CRF) classifier show improved recognition performance for both pre-segmented and online classification tasks.
Show less
-
Date Issued
-
2012
-
Identifier
-
CFE0004575, ucf:49210
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0004575
-
-
Title
-
A Study of the Relationship between Continuous Professional Learning Community Implementation and Student Achievement in a Large Urban School District.
-
Creator
-
Sutula, Erica, Taylor, Rosemarye, Baldwin, Lee, Doherty, Walter, Ellis, Amanda, University of Central Florida
-
Abstract / Description
-
The purpose of this causal comparative study was to understand the differences in comparative data across a large urban school district and to examine the continued effects of the PLC model on teacher and leader perception of the model and student achievement as measured by the 2012 and 2014 FCAT 2.0 Reading and Mathematics. The population for this study included all instructional and leadership personnel in schools within the target school district, with a final convenience sample across the...
Show moreThe purpose of this causal comparative study was to understand the differences in comparative data across a large urban school district and to examine the continued effects of the PLC model on teacher and leader perception of the model and student achievement as measured by the 2012 and 2014 FCAT 2.0 Reading and Mathematics. The population for this study included all instructional and leadership personnel in schools within the target school district, with a final convenience sample across the two school years of N=5,954.The research questions for this study focused on (a) the change in teacher's perception of teachers from the 2012 to the 2014 school year, (b) the impact, if any, of teacher and leader perception on student performance for the FCAT, (c) the differences between the perceptions of teachers and leaders. This study added to the findings of Ellis (2010), expanding the understanding of the complexities of collaboration among teachers, administrators, collaboration, and students. Conclusions from the quantitative analysis found a statistically significant difference between how teachers perceived the implementation of collaborative time during both the 2012 and 2014 school years. Further analysis concluded that there was a statistically significant positive relationship between continual PLC implementation and student achievement for Grade 3 Reading and Mathematics. Other grade levels did show educationally significant findings for the impact of continual implementation on student achievement, but the results did not meet the criteria for statistical significance. There was not a statistically significant relationship between any other measure and any of the considered standardized test scores. Statistically significant differences were found between the 2012 and 2014 perceptions of teachers and leaders.Recommendations from the quantitative analysis include the importance of having collaborative time for teachers. Furthermore, leaders should focus on maximizing the effectiveness of collaborative time by curtailing the amount of required administrative tasks, thereby allowing teachers to focus on designing instructional interventions and analyzing student data through collaboration. This study is an addition to the current literature demonstrating the general perceptions, and impacts of long term implementation of the PLC model, when paired with Ellis' (2010) study it is clear that teachers need continual work within one collaborative model, modeling of collaborative practices by leadership, and support from school leaders for collaborative time to begin positively impacting student achievement.
Show less
-
Date Issued
-
2017
-
Identifier
-
CFE0006802, ucf:51812
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0006802
-
-
Title
-
Action Recognition, Temporal Localization and Detection in Trimmed and Untrimmed Video.
-
Creator
-
Hou, Rui, Shah, Mubarak, Mahalanobis, Abhijit, Hua, Kien, Sukthankar, Rahul, University of Central Florida
-
Abstract / Description
-
Automatic understanding of videos is one of the most active areas of computer vision research. It has applications in video surveillance, human computer interaction, video sports analysis, virtual and augmented reality, video retrieval etc. In this dissertation, we address four important tasks in video understanding, namely action recognition, temporal action localization, spatial-temporal action detection and video object/action segmentation. This dissertation makes contributions to above...
Show moreAutomatic understanding of videos is one of the most active areas of computer vision research. It has applications in video surveillance, human computer interaction, video sports analysis, virtual and augmented reality, video retrieval etc. In this dissertation, we address four important tasks in video understanding, namely action recognition, temporal action localization, spatial-temporal action detection and video object/action segmentation. This dissertation makes contributions to above tasks by proposing. First, for video action recognition, we propose a category level feature learning method. Our proposed method automatically identifies such pairs of categories using a criterion of mutual pairwise proximity in the (kernelized) feature space, and a category-level similarity matrix where each entry corresponds to the one-vs-one SVM margin for pairs of categories. Second, for temporal action localization, we propose to exploit the temporal structure of actions by modeling an action as a sequence of sub-actions and present a computationally efficient approach. Third, we propose 3D Tube Convolutional Neural Network (TCNN) based pipeline for action detection. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. It generalizes the popular faster R-CNN framework from images to videos. Last, an end-to-end encoder-decoder based 3D convolutional neural network pipeline is proposed, which is able to segment out the foreground objects from the background. Moreover, the action label can be obtained as well by passing the foreground object into an action classifier. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for video understanding compared to the state-of-the-art.
Show less
-
Date Issued
-
2019
-
Identifier
-
CFE0007655, ucf:52502
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0007655
-
-
Title
-
Adversarial Attacks On Vision Algorithms Using Deep Learning Features.
-
Creator
-
Michel, Andy, Jha, Sumit Kumar, Leavens, Gary, Valliyil Thankachan, Sharma, University of Central Florida
-
Abstract / Description
-
Computer vision algorithms, such as those implementing object detection, are known to be sus-ceptible to adversarial attacks. Small barely perceptible perturbations to the input can cause visionalgorithms to incorrectly classify inputs that they would have otherwise classified correctly. Anumber of approaches have been recently investigated to generate such adversarial examples fordeep neural networks. Many of these approaches either require grey-box access to the deep neuralnet being...
Show moreComputer vision algorithms, such as those implementing object detection, are known to be sus-ceptible to adversarial attacks. Small barely perceptible perturbations to the input can cause visionalgorithms to incorrectly classify inputs that they would have otherwise classified correctly. Anumber of approaches have been recently investigated to generate such adversarial examples fordeep neural networks. Many of these approaches either require grey-box access to the deep neuralnet being attacked or rely on adversarial transfer and grey-box access to a surrogate neural network.In this thesis, we present an approach to the synthesis of adversarial examples for computer vi-sion algorithms that only requires black-box access to the algorithm being attacked. Our attackapproach employs fuzzing with features derived from the layers of a convolutional neural networktrained on adversarial examples from an unrelated dataset. Based on our experimental results,we believe that our validation approach will enable designers of cyber-physical systems and otherhigh-assurance use-cases of vision algorithms to stress test their implementations.
Show less
-
Date Issued
-
2017
-
Identifier
-
CFE0006898, ucf:51714
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0006898
-
-
Title
-
AUTONOMOUS ROBOTIC GRASPING IN UNSTRUCTURED ENVIRONMENTS.
-
Creator
-
Jabalameli, Amirhossein, Behal, Aman, Haralambous, Michael, Pourmohammadi Fallah, Yaser, Boloni, Ladislau, Xu, Yunjun, University of Central Florida
-
Abstract / Description
-
A crucial problem in robotics is interacting with known or novel objects in unstructured environments. While the convergence of a multitude of research advances is required to address this problem, our goal is to describe a framework that employs the robot's visual perception to identify and execute an appropriate grasp to pick and place novel objects. Analytical approaches explore for solutions through kinematic and dynamic formulations. On the other hand, data-driven methods retrieve grasps...
Show moreA crucial problem in robotics is interacting with known or novel objects in unstructured environments. While the convergence of a multitude of research advances is required to address this problem, our goal is to describe a framework that employs the robot's visual perception to identify and execute an appropriate grasp to pick and place novel objects. Analytical approaches explore for solutions through kinematic and dynamic formulations. On the other hand, data-driven methods retrieve grasps according to their prior knowledge of either the target object, human experience, or through information obtained from acquired data. In this dissertation, we propose a framework based on the supporting principle that potential contacting regions for a stable grasp can be foundby searching for (i) sharp discontinuities and (ii) regions of locally maximal principal curvature in the depth map. In addition to suggestions from empirical evidence, we discuss this principle by applying the concept of force-closure and wrench convexes. The key point is that no prior knowledge of objects is utilized in the grasp planning process; however, the obtained results show thatthe approach is capable to deal successfully with objects of different shapes and sizes. We believe that the proposed work is novel because the description of the visible portion of objects by theaforementioned edges appearing in the depth map facilitates the process of grasp set-point extraction in the same way as image processing methods with the focus on small-size 2D image areas rather than clustering and analyzing huge sets of 3D point-cloud coordinates. In fact, this approach dismisses reconstruction of objects. These features result in low computational costs and make it possible to run the proposed algorithm in real-time. Finally, the performance of the approach is successfully validated by applying it to the scenes with both single and multiple objects, in both simulation and real-world experiment setups.
Show less
-
Date Issued
-
2019
-
Identifier
-
CFE0007892, ucf:52757
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0007892
-
-
Title
-
Computer Vision Based Structural Identification Framework for Bridge Health Mornitoring.
-
Creator
-
Khuc, Tung, Catbas, Necati, Oloufa, Amr, Mackie, Kevin, Zaurin, Ricardo, Shah, Mubarak, University of Central Florida
-
Abstract / Description
-
The objective of this dissertation is to develop a comprehensive Structural Identification (St-Id) framework with damage for bridge type structures by using cameras and computer vision technologies. The traditional St-Id frameworks rely on using conventional sensors. In this study, the collected input and output data employed in the St-Id system are acquired by series of vision-based measurements. The following novelties are proposed, developed and demonstrated in this project: a) vehicle...
Show moreThe objective of this dissertation is to develop a comprehensive Structural Identification (St-Id) framework with damage for bridge type structures by using cameras and computer vision technologies. The traditional St-Id frameworks rely on using conventional sensors. In this study, the collected input and output data employed in the St-Id system are acquired by series of vision-based measurements. The following novelties are proposed, developed and demonstrated in this project: a) vehicle load (input) modeling using computer vision, b) bridge response (output) using full non-contact approach using video/image processing, c) image-based structural identification using input-output measurements and new damage indicators. The input (loading) data due vehicles such as vehicle weights and vehicle locations on the bridges, are estimated by employing computer vision algorithms (detection, classification, and localization of objects) based on the video images of vehicles. Meanwhile, the output data as structural displacements are also obtained by defining and tracking image key-points of measurement locations. Subsequently, the input and output data sets are analyzed to construct novel types of damage indicators, named Unit Influence Surface (UIS). Finally, the new damage detection and localization framework is introduced that does not require a network of sensors, but much less number of sensors.The main research significance is the first time development of algorithms that transform the measured video images into a form that is highly damage-sensitive/change-sensitive for bridge assessment within the context of Structural Identification with input and output characterization. The study exploits the unique attributes of computer vision systems, where the signal is continuous in space. This requires new adaptations and transformations that can handle computer vision data/signals for structural engineering applications. This research will significantly advance current sensor-based structural health monitoring with computer-vision techniques, leading to practical applications for damage detection of complex structures with a novel approach. By using computer vision algorithms and cameras as special sensors for structural health monitoring, this study proposes an advance approach in bridge monitoring through which certain type of data that could not be collected by conventional sensors such as vehicle loads and location, can be obtained practically and accurately.
Show less
-
Date Issued
-
2016
-
Identifier
-
CFE0006127, ucf:51174
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0006127
-
-
Title
-
Computerized Evaluatution of Microsurgery Skills Training.
-
Creator
-
Jotwani, Payal, Foroosh, Hassan, Hughes, Charles, Hua, Kien, University of Central Florida
-
Abstract / Description
-
The style of imparting medical training has evolved, over the years. The traditional methods of teaching and practicing basic surgical skills under apprenticeship model, no longer occupy the first place in modern technically demanding advanced surgical disciplines like neurosurgery. Furthermore, the legal and ethical concerns for patient safety as well as cost-effectiveness have forced neurosurgeons to master the necessary microsurgical techniques to accomplish desired results. This has lead...
Show moreThe style of imparting medical training has evolved, over the years. The traditional methods of teaching and practicing basic surgical skills under apprenticeship model, no longer occupy the first place in modern technically demanding advanced surgical disciplines like neurosurgery. Furthermore, the legal and ethical concerns for patient safety as well as cost-effectiveness have forced neurosurgeons to master the necessary microsurgical techniques to accomplish desired results. This has lead to increased emphasis on assessment of clinical and surgical techniques of the neurosurgeons. However, the subjective assessment of microsurgical techniques like micro-suturing under the apprenticeship model cannot be completely unbiased. A few initiatives using computer-based techniques, have been made to introduce objective evaluation of surgical skills.This thesis presents a novel approach involving computerized evaluation of different components of micro-suturing techniques, to eliminate the bias of subjective assessment. The work involved acquisition of cine clips of micro-suturing activity on synthetic material. Image processing and computer vision based techniques were then applied to these videos to assess different characteristics of micro-suturing viz. speed, dexterity and effectualness. In parallel subjective grading on these was done by a senior neurosurgeon. Further correlation and comparative study of both the assessments was done to analyze the efficacy of objective and subjective evaluation.
Show less
-
Date Issued
-
2015
-
Identifier
-
CFE0006221, ucf:51056
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0006221
-
-
Title
-
Concerning the Perceptive Gaze: The Impact of Vision Theories on Late Nineteenth-Century Victorian Literature.
-
Creator
-
Rushworth, Lindsay, Jones, Anna, Philpotts, Trey, Campbell, James, University of Central Florida
-
Abstract / Description
-
This thesis examines two specific interventions in vision theory(-)namely, Herbert Spencer's theory of organic memory, which he developed by way of Lamarckian genetics and Darwinian evolution in A System of Synthetic Philosophy (1864), and the Aesthetic Movement (1870s(-)1890s), famously articulated by Walter Pater in The Renaissance: Studies in Art and Poetry (1873 and 1893). I explore the impact of these theories on late nineteenth-century fiction, focusing on two novels: Thomas Hardy's Two...
Show moreThis thesis examines two specific interventions in vision theory(-)namely, Herbert Spencer's theory of organic memory, which he developed by way of Lamarckian genetics and Darwinian evolution in A System of Synthetic Philosophy (1864), and the Aesthetic Movement (1870s(-)1890s), famously articulated by Walter Pater in The Renaissance: Studies in Art and Poetry (1873 and 1893). I explore the impact of these theories on late nineteenth-century fiction, focusing on two novels: Thomas Hardy's Two on a Tower (1882) and Edith Johnstone's A Sunless Heart (1894). These two authors' texts engage with scientific and aesthetic visual theories to demonstrate their anxieties concerning the perceptive gaze and to reveal the difficulties and limitations of visual perception and misperception for both the observer and the observed within the context of social class.It is widely accepted by scholars of the so-called visual turn in the Victorian era(-) following landmark works by Kate Flint and Nancy Armstrong(-)that myriad anxieties were associated with new ways of seeing during this time. Building on this work, my thesis focuses specifically on how these two approaches to visual perception(-)organic memory and Aestheticism(-)were intertwined with anxieties about social status and mobility. The novels analyzed in this thesis demonstrate how subjective visual perception affects one's place within the social hierarchy, as we see reflected in the fluctuating social statuses of Hardy's star-crossed lovers, Swithin St Cleeve and Lady Constantine, and Johnstone's two female protagonists, Gasparine O'Neill and Lotus Grace.
Show less
-
Date Issued
-
2019
-
Identifier
-
CFE0007527, ucf:52624
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0007527
-
-
Title
-
DEPTH FROM DEFOCUSED MOTION.
-
Creator
-
Myles, Zarina, da Vitoria Lobo, Niels, University of Central Florida
-
Abstract / Description
-
Motion in depth and/or zooming causes defocus blur. This work presents a solution to the problem of using defocus blur and optical flow information to compute depth at points that defocus when they move.We first formulate a novel algorithm which recovers defocus blur and affine parameters simultaneously. Next we formulate a novel relationship (the blur-depth relationship) between defocus blur, relative object depth and three parameters based on camera motion and intrinsic camera parameters.We...
Show moreMotion in depth and/or zooming causes defocus blur. This work presents a solution to the problem of using defocus blur and optical flow information to compute depth at points that defocus when they move.We first formulate a novel algorithm which recovers defocus blur and affine parameters simultaneously. Next we formulate a novel relationship (the blur-depth relationship) between defocus blur, relative object depth and three parameters based on camera motion and intrinsic camera parameters.We can handle the situation where a single image has points which have defocused, got sharper or are focally unperturbed. Moreover, our formulation is valid regardless of whether the defocus is due to the image plane being in front of or behind the point of sharp focus.The blur-depth relationship requires a sequence of at least three images taken with the camera moving either towards or away from the object. It can be used to obtain an initial estimate of relative depth using one of several non-linear methods. We demonstrate a solution based on the Extended Kalman Filter in which the measurement equation is the blur-depth relationship.The estimate of relative depth is then used to compute an initial estimate of camera motion parameters. In order to refine depth values, the values of relative depth and camera motion are then input into a second Extended Kalman Filter in which the measurement equations are the discrete motion equations. This set of cascaded Kalman filters can be employed iteratively over a longer sequence of images in order to further refine depth.We conduct several experiments on real scenery in order to demonstrate the range of object shapes that the algorithm can handle. We show that fairly good estimates of depth can be obtained with just three images.
Show less
-
Date Issued
-
2004
-
Identifier
-
CFE0000135, ucf:46179
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0000135
-
-
Title
-
DESIGNING LIGHT FILTERS TO DETECT SKIN USING A LOW-POWERED SENSOR.
-
Creator
-
Tariq, Muhammad, Wisniewski, Pamela, Gong, Boqing, Leavens, Gary, University of Central Florida
-
Abstract / Description
-
Detection of nudity in photos and videos, especially prior to uploading to the internet, is vital to solving many problems related to adolescent sexting, the distribution of child pornography, and cyber-bullying. The problem with using nudity detection algorithms as a means to combat these problems is that: 1) it implies that a digitized nude photo of a minor already exists (i.e., child pornography), and 2) there are real ethical and legal concerns around the distribution and processing of...
Show moreDetection of nudity in photos and videos, especially prior to uploading to the internet, is vital to solving many problems related to adolescent sexting, the distribution of child pornography, and cyber-bullying. The problem with using nudity detection algorithms as a means to combat these problems is that: 1) it implies that a digitized nude photo of a minor already exists (i.e., child pornography), and 2) there are real ethical and legal concerns around the distribution and processing of child pornography. Once a camera captures an image, that image is no longer secure. Therefore, we need to develop new privacy-preserving solutions that prevent the digital capture of nude imagery of minors. My research takes a first step in trying to accomplish this long-term goal: In this thesis, I examine the feasibility of using a low-powered sensor to detect skin dominance (defined as an image comprised of 50% or more of human skin tone) in a visual scene. By designing four custom light filters to enhance the digital information extracted from 300 scenes captured with the sensor (without digitizing high-fidelity visual features), I was able to accurately detect a skin dominant scene with 83.7% accuracy, 83% precision, and 85% recall. The long-term goal to be achieved in the future is to design a low-powered vision sensor that can be mounted on a digital camera lens on a teen's mobile device to detect and/or prevent the capture of nude imagery. Thus, I discuss the limitations of this work toward this larger goal, as well as future research directions.
Show less
-
Date Issued
-
2017
-
Identifier
-
CFE0006806, ucf:51792
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0006806
-
-
Title
-
DETECTING CURVED OBJECTS AGAINST CLUTTERED BACKGROUNDS.
-
Creator
-
Prokaj, Jan, Lobo, Niels, University of Central Florida
-
Abstract / Description
-
Detecting curved objects against cluttered backgrounds is a hard problem in computer vision. We present new low-level and mid-level features to function in these environments. The low-level features are fast to compute, because they employ an integral image approach, which makes them especially useful in real-time applications. The mid-level features are built from low-level features, and are optimized for curved object detection. The usefulness of these features is tested by designing an...
Show moreDetecting curved objects against cluttered backgrounds is a hard problem in computer vision. We present new low-level and mid-level features to function in these environments. The low-level features are fast to compute, because they employ an integral image approach, which makes them especially useful in real-time applications. The mid-level features are built from low-level features, and are optimized for curved object detection. The usefulness of these features is tested by designing an object detection algorithm using these features. Object detection is accomplished by transforming the mid-level features into weak classifiers, which then produce a strong classifier using AdaBoost. The resulting strong classifier is then tested on the problem of detecting heads with shoulders. On a database of over 500 images of people, cropped to contain head and shoulders, and with a diverse set of backgrounds, the detection rate is 90% while the false positive rate on a database of 500 negative images is less than 2%.
Show less
-
Date Issued
-
2008
-
Identifier
-
CFE0002102, ucf:47535
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0002102
-
-
Title
-
Development of 3D Vision Testbed for Shape Memory Polymer Structure Applications.
-
Creator
-
Thompson, Kenneth, Xu, Yunjun, Gou, Jihua, Lin, Kuo-Chi, University of Central Florida
-
Abstract / Description
-
As applications for shape memory polymers (SMPs) become more advanced, it is necessary to have the ability to monitor both the actuation and thermal properties of structures made of such materials. In this paper, a method of using three stereo pairs of webcams and a single thermal camera is studied for the purposes of both tracking three dimensional motion of shape memory polymers, as well as the temperature of points of interest within the SMP structure. The method used includes a stereo...
Show moreAs applications for shape memory polymers (SMPs) become more advanced, it is necessary to have the ability to monitor both the actuation and thermal properties of structures made of such materials. In this paper, a method of using three stereo pairs of webcams and a single thermal camera is studied for the purposes of both tracking three dimensional motion of shape memory polymers, as well as the temperature of points of interest within the SMP structure. The method used includes a stereo camera calibration with integrated local minimum tracking algorithms to locate points of interest on the material and measure their temperature through interpolation techniques. The importance of the proposed method is that it allows a means to cost effectively monitor the surface temperature of a shape memory polymer structure without having to place intrusive sensors on the samples, which would limit the performance of the shape memory effect. The ability to monitor the surface temperatures of a SMP structure allows for more complex configurations to be created while increasing the performance and durability of the material. Additionally, as compared to the previous version, both the functionalities of the testbed and the user interface have been significantly improved.
Show less
-
Date Issued
-
2015
-
Identifier
-
CFE0005893, ucf:50860
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0005893
-
-
Title
-
EDUCATIONAL VISION IN FLORIDA SCHOOL DISTRICTS: VISION ALIGNMENT AND LEADERSHIP STYLE.
-
Creator
-
Sikkenga, Cindy, House, Jess, University of Central Florida
-
Abstract / Description
-
The purpose of this study was to address a gap in the organizational leadership research related to the sharing, or alignment, of leadership vision across organizational levels, with a focus on educational vision alignment in Florida K-12 public school districts. The study also sought to determine to what extent, if any, there were differences among Florida school districts exhibiting different levels of educational vision alignment. The broad question addressed by the current research was...
Show moreThe purpose of this study was to address a gap in the organizational leadership research related to the sharing, or alignment, of leadership vision across organizational levels, with a focus on educational vision alignment in Florida K-12 public school districts. The study also sought to determine to what extent, if any, there were differences among Florida school districts exhibiting different levels of educational vision alignment. The broad question addressed by the current research was this: To what degree are the educational visions of superintendents and principals aligned within Florida K-12 public school districts? The following research questions further guided the study: 1. What common themes can be found in the published vision statements of the 67 Florida K-12 public school districts? 2. To what extent, if any, do Florida K-12 public school district superintendents and their respective principals agree with one another on the importance of the common themes found in Florida school districts' published vision statements? 3. What is the relationship, if any, between educational vision alignment levels in Florida K-12 public school districts and principals' perceptions of their superintendents' leadership styles? 4. To what extent, if any, are there differences among Florida K-12 public school districts exhibiting different levels of educational vision alignment? The Florida Educational Vision Questionnaire Superintendent Form (FEVQ-S), a researcher developed questionnaire, was administered to all 67 Florida K-12 public school district superintendents. With superintendent approval, two additional questionnaires were administered to a sample of 242 principals in 23 school districts. The Florida Educational Vision Questionnaire Principal Form (FEVQ-P) and the Multifactor Leadership Questionnaire Form 5X Rater (MLQ-5X) (Avolio, Bass, & Jung, 1999) were returned fully completed by 105 principals in 21 districts. A total of 81 principal responses in 20 districts were usable, yielding overall usable response rates of 29.9% (superintendents) and 33.5% (principals). Comparisons of FEVQ responses of superintendents and principals in each school district were made using a researcher developed measure, the Educational Vision Alignment Index (EVAI). Within each district, the EVAI was compared with the superintendent's leadership style as measured by the principals' responses to the MLQ-5X. School districts were then compared using data obtained from the FEVQ demographic items, the Florida School Indicators Report (FSIR) (FLDOE, 2003a), the 2004 School Grades by District Report (FLDOE, n.d.), and the online Florida Public School Superintendents report (FLDOE, 2005c). The FSIR contains data on district characteristics such as operating costs, per pupil expenditures, school staff composition, student membership, student mobility rates, student stability rates, and teacher descriptors. The 2004 School Grades by District report contains both the school grades for each district and the total number of schools per district. The Florida Public School Superintendents report contains general school district information and superintendent status (i.e., elected or appointed) information. Detailed data analyses related to each of the four research questions indicated that: 1. Several common themes can be found in the published vision statements of the 67 Florida K-12 public school districts, 2. Florida K-12 public school district superintendents and their respective principals agree with one another on the importance of some of these common themes, 3. Several relationships exist between the educational vision alignment levels in Florida K-12 public school districts and principals' perceptions of their superintendents' leadership styles, and 4. There are differences among Florida K-12 public school districts exhibiting different levels of educational vision alignment. The current study illustrated that in Florida K-12 public school districts whose superintendents were perceived to be transformational leaders, a strong alignment of educational vision between the superintendents and their principals was also apparent, particularly in those districts having elected superintendents. Using the two researcher developed tools, the Florida Educational Vision Questionnaire (FEVQ) and the Educational Vision Alignment Index (EVAI), it was shown that this alignment pertained to specific content items, or themes, derived from an analysis of the educational vision statements of the 67 Florida school districts. These results indicate that the current emphasis in Florida on the development of transformational leaders who are knowledgeable in techniques for developing and communicating shared visions is therefore warranted.
Show less
-
Date Issued
-
2006
-
Identifier
-
CFE0001349, ucf:46995
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0001349
-
-
Title
-
Gradient based MRF learning for image restoration and segmentation.
-
Creator
-
Samuel, Kegan, Tappen, Marshall, Da Vitoria Lobo, Niels, Foroosh, Hassan, Li, Xin, University of Central Florida
-
Abstract / Description
-
The undirected graphical model or Markov Random Field (MRF) is one of the more popular models used in computer vision and is the type of model with which this work is concerned. Models based on these methods have proven to be particularly useful in low-level vision systems and have led to state-of-the-art results for MRF-based systems. The research presented will describe a new discriminative training algorithm and its implementation.The MRF model will be trained by optimizing its parameters...
Show moreThe undirected graphical model or Markov Random Field (MRF) is one of the more popular models used in computer vision and is the type of model with which this work is concerned. Models based on these methods have proven to be particularly useful in low-level vision systems and have led to state-of-the-art results for MRF-based systems. The research presented will describe a new discriminative training algorithm and its implementation.The MRF model will be trained by optimizing its parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. While previous work has relied on time-consuming iterative approximations or stochastic approximations, this work will demonstrate how implicit differentiation can be used to analytically differentiate the overall training loss with respect to the MRF parameters. This framework leads to an efficient, flexible learning algorithm that can be applied to a number of different models.The effectiveness of the proposed learning method will then be demonstrated by learning the parameters of two related models applied to the task of denoising images. The experimental results will demonstrate that the proposed learning algorithm is comparable and, at times, better than previous training methods applied to the same tasks.A new segmentation model will also be introduced and trained using the proposed learning method. The proposed segmentation model is based on an energy minimization framework that is novel in how it incorporates priors on the size of the segments in a way that is straightforward to implement. While other methods, such as normalized cuts, tend to produce segmentations of similar sizes, this method is able to overcome that problem and produce more realistic segmentations.
Show less
-
Date Issued
-
2012
-
Identifier
-
CFE0004595, ucf:49207
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0004595
-
-
Title
-
Holistic Representations for Activities and Crowd Behaviors.
-
Creator
-
Solmaz, Berkan, Shah, Mubarak, Da Vitoria Lobo, Niels, Jha, Sumit, Ilie, Marcel, Moore, Brian, University of Central Florida
-
Abstract / Description
-
In this dissertation, we address the problem of analyzing the activities of people in a variety of scenarios, this is commonly encountered in vision applications. The overarching goal is to devise new representations for the activities, in settings where individuals or a number of people may take a part in specific activities. Different types of activities can be performed by either an individual at the fine level or by several people constituting a crowd at the coarse level. We take into...
Show moreIn this dissertation, we address the problem of analyzing the activities of people in a variety of scenarios, this is commonly encountered in vision applications. The overarching goal is to devise new representations for the activities, in settings where individuals or a number of people may take a part in specific activities. Different types of activities can be performed by either an individual at the fine level or by several people constituting a crowd at the coarse level. We take into account the domain specific information for modeling these activities. The summary of the proposed solutions is presented in the following.The holistic description of videos is appealing for visual detection and classification tasks for several reasons including capturing the spatial relations between the scene components, simplicity, and performance [1, 2, 3]. First, we present a holistic (global) frequency spectrum based descriptor for representing the atomic actions performed by individuals such as: bench pressing, diving, hand waving, boxing, playing guitar, mixing, jumping, horse riding, hula hooping etc. We model and learn these individual actions for classifying complex user uploaded videos. Our method bypasses the detection of interest points, the extraction of local video descriptors and the quantization of local descriptors into a code book; it represents each video sequence as a single feature vector. This holistic feature vector is computed by applying a bank of 3-D spatio-temporal filters on the frequency spectrum of a video sequence; hence it integrates the information about the motion and scene structure. We tested our approach on two of the most challenging datasets, UCF50 [4] and HMDB51 [5], and obtained promising results which demonstrates the robustness and the discriminative power of our holistic video descriptor for classifying videos of various realistic actions.In the above approach, a holistic feature vector of a video clip is acquired by dividing the video into spatio-temporal blocks then concatenating the features of the individual blocks together. However, such a holistic representation blindly incorporates all the video regions regardless of their contribution in classification. Next, we present an approach which improves the performance of the holistic descriptors for activity recognition. In our novel method, we improve the holistic descriptors by discovering the discriminative video blocks. We measure the discriminativity of a block by examining its response to a pre-learned support vector machine model. In particular, a block is considered discriminative if it responds positively for positive training samples, and negatively for negative training samples. We pose the problem of finding the optimal blocks as a problem of selecting a sparse set of blocks, which maximizes the total classifier discriminativity. Through a detailed set of experiments on benchmark datasets [6, 7, 8, 9, 5, 10], we show that our method discovers the useful regions in the videos and eliminates the ones which are confusing for classification, which results in significant performance improvement over the state-of-the-art.In contrast to the scenes where an individual performs a primitive action, there may be scenes with several people, where crowd behaviors may take place. For these types of scenes the traditional approaches for recognition will not work due to severe occlusion and computational requirements. The number of videos is limited and the scenes are complicated, hence learning these behaviors is not feasible. For this problem, we present a novel approach, based on the optical flow in a video sequence, for identifying five specific and common crowd behaviors in visual scenes. In the algorithm, the scene is overlaid by a grid of particles, initializing a dynamical system which is derived from the optical flow. Numerical integration of the optical flow provides particle trajectories that represent the motion in the scene. Linearization of the dynamical system allows a simple and practical analysis and classification of the behavior through the Jacobian matrix. Essentially, the eigenvalues of this matrix are used to determine the dynamic stability of points in the flow and each type of stability corresponds to one of the five crowd behaviors. The identified crowd behaviors are (1) bottlenecks: where many pedestrians/vehicles from various points in the scene are entering through one narrow passage, (2) fountainheads: where many pedestrians/vehicles are emerging from a narrow passage only to separate in many directions, (3) lanes: where many pedestrians/vehicles are moving at the same speeds in the same direction, (4) arches or rings: where the collective motion is curved or circular, and (5) blocking: where there is a opposing motion and desired movement of groups of pedestrians is somehow prohibited. The implementation requires identifying a region of interest in the scene, and checking the eigenvalues of the Jacobian matrix in that region to determine the type of flow, that corresponds to various well-defined crowd behaviors. The eigenvalues are only considered in these regions of interest, consistent with the linear approximation and the implied behaviors. Since changes in eigenvalues can mean changes in stability, corresponding to changes in behavior, we can repeat the algorithm over clips of long video sequences to locate changes in behavior. This method was tested on over real videos representing crowd and traffic scenes.
Show less
-
Date Issued
-
2013
-
Identifier
-
CFE0004941, ucf:49638
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0004941
-
-
Title
-
Human Action Localization and Recognition in Unconstrained Videos.
-
Creator
-
Boyraz, Hakan, Tappen, Marshall, Foroosh, Hassan, Lin, Mingjie, Zhang, Shaojie, Sukthankar, Rahul, University of Central Florida
-
Abstract / Description
-
As imaging systems become ubiquitous, the ability to recognize human actions is becoming increasingly important. Just as in the object detection and recognition literature, action recognition can be roughly divided into classification tasks, where the goal is to classify a video according to the action depicted in the video, and detection tasks, where the goal is to detect and localize a human performing a particular action. A growing literature is demonstrating the benefits of localizing...
Show moreAs imaging systems become ubiquitous, the ability to recognize human actions is becoming increasingly important. Just as in the object detection and recognition literature, action recognition can be roughly divided into classification tasks, where the goal is to classify a video according to the action depicted in the video, and detection tasks, where the goal is to detect and localize a human performing a particular action. A growing literature is demonstrating the benefits of localizing discriminative sub-regions of images and videos when performing recognition tasks. In this thesis, we address the action detection and recognition problems. Action detection in video is a particularly difficult problem because actions must not only be recognized correctly, but must also be localized in the 3D spatio-temporal volume. We introduce a technique that transforms the 3D localization problem into a series of 2D detection tasks. This is accomplished by dividing the video into overlapping segments, then representing each segment with a 2D video projection. The advantage of the 2D projection is that it makes it convenient to apply the best techniques from object detection to the action detection problem. We also introduce a novel, straightforward method for searching the 2D projections to localize actions, termed Two-Point Subwindow Search (TPSS). Finally, we show how to connect the local detections in time using a chaining algorithm to identify the entire extent of the action. Our experiments show that video projection outperforms the latest results on action detection in a direct comparison.Second, we present a probabilistic model learning to identify discriminative regions in videos from weakly-supervised data where each video clip is only assigned a label describing what action is present in the frame or clip. While our first system requires every action to be manually outlined in every frame of the video, this second system only requires that the video be given a single high-level tag. From this data, the system is able to identify discriminative regions that correspond well to the regions containing the actual actions. Our experiments on both the MSR Action Dataset II and UCF Sports Dataset show that the localizations produced by this weakly supervised system are comparable in quality to localizations produced by systems that require each frame to be manually annotated. This system is able to detect actions in both 1) non-temporally segmented action videos and 2) recognition tasks where a single label is assigned to the clip. We also demonstrate the action recognition performance of our method on two complex datasets, i.e. HMDB and UCF101. Third, we extend our weakly-supervised framework by replacing the recognition stage with a two-stage neural network and apply dropout for preventing overfitting of the parameters on the training data. Dropout technique has been recently introduced to prevent overfitting of the parameters in deep neural networks and it has been applied successfully to object recognition problem. To our knowledge, this is the first system using dropout for action recognition problem. We demonstrate that using dropout improves the action recognition accuracies on HMDB and UCF101 datasets.
Show less
-
Date Issued
-
2013
-
Identifier
-
CFE0004977, ucf:49562
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0004977
-
-
Title
-
Human Detection, Tracking and Segmentation in Surveillance Video.
-
Creator
-
Shu, Guang, Shah, Mubarak, Boloni, Ladislau, Wang, Jun, Lin, Mingjie, Sugaya, Kiminobu, University of Central Florida
-
Abstract / Description
-
This dissertation addresses the problem of human detection and tracking in surveillance videos. Even though this is a well-explored topic, many challenges remain when confronted with data from real world situations. These challenges include appearance variation, illumination changes, camera motion, cluttered scenes and occlusion. In this dissertation several novel methods for improving on the current state of human detection and tracking based on learning scene-specific information in video...
Show moreThis dissertation addresses the problem of human detection and tracking in surveillance videos. Even though this is a well-explored topic, many challenges remain when confronted with data from real world situations. These challenges include appearance variation, illumination changes, camera motion, cluttered scenes and occlusion. In this dissertation several novel methods for improving on the current state of human detection and tracking based on learning scene-specific information in video feeds are proposed.Firstly, we propose a novel method for human detection which employs unsupervised learning and superpixel segmentation. The performance of generic human detectors is usually degraded in unconstrained video environments due to varying lighting conditions, backgrounds and camera viewpoints. To handle this problem, we employ an unsupervised learning framework that improves the detection performance of a generic detector when it is applied to a particular video. In our approach, a generic DPM human detector is employed to collect initial detection examples. These examples are segmented into superpixels and then represented using Bag-of-Words (BoW) framework. The superpixel-based BoW feature encodes useful color features of the scene, which provides additional information. Finally a new scene-specific classifier is trained using the BoW features extracted from the new examples. Compared to previous work, our method learns scene-specific information through superpixel-based features, hence it can avoid many false detections typically obtained by a generic detector. We are able to demonstrate a significant improvement in the performance of the state-of-the-art detector.Given robust human detection, we propose a robust multiple-human tracking framework using a part-based model. Human detection using part models has become quite popular, yet its extension in tracking has not been fully explored. Single camera-based multiple-person tracking is often hindered by difficulties such as occlusion and changes in appearance. We address such problems by developing an online-learning tracking-by-detection method. Our approach learns part-based person-specific Support Vector Machine (SVM) classifiers which capture articulations of moving human bodies with dynamically changing backgrounds. With the part-based model, our approach is able to handle partial occlusions in both the detection and the tracking stages. In the detection stage, we select the subset of parts which maximizes the probability of detection. This leads to a significant improvement in detection performance in cluttered scenes. In the tracking stage, we dynamically handle occlusions by distributing the score of the learned person classifier among its corresponding parts, which allows us to detect and predict partial occlusions and prevent the performance of the classifiers from being degraded. Extensive experiments using the proposed method on several challenging sequences demonstrate state-of-the-art performance in multiple-people tracking.Next, in order to obtain precise boundaries of humans, we propose a novel method for multiple human segmentation in videos by incorporating human detection and part-based detection potential into a multi-frame optimization framework. In the first stage, after obtaining the superpixel segmentation for each detection window, we separate superpixels corresponding to a human and background by minimizing an energy function using Conditional Random Field (CRF). We use the part detection potentials from the DPM detector, which provides useful information for human shape. In the second stage, the spatio-temporal constraints of the video is leveraged to build a tracklet-based Gaussian Mixture Model for each person, and the boundaries are smoothed by multi-frame graph optimization. Compared to previous work, our method could automatically segment multiple people in videos with accurate boundaries, and it is robust to camera motion. Experimental results show that our method achieves better segmentation performance than previous methods in terms of segmentation accuracy on several challenging video sequences.Most of the work in Computer Vision deals with point solution; a specific algorithm for a specific problem. However, putting different algorithms into one real world integrated system is a big challenge. Finally, we introduce an efficient tracking system, NONA, for high-definition surveillance video. We implement the system using a multi-threaded architecture (Intel Threading Building Blocks (TBB)), which executes video ingestion, tracking, and video output in parallel. To improve tracking accuracy without sacrificing efficiency, we employ several useful techniques. Adaptive Template Scaling is used to handle the scale change due to objects moving towards a camera. Incremental Searching and Local Frame Differencing are used to resolve challenging issues such as scale change, occlusion and cluttered backgrounds. We tested our tracking system on a high-definition video dataset and achieved acceptable tracking accuracy while maintaining real-time performance.
Show less
-
Date Issued
-
2014
-
Identifier
-
CFE0005551, ucf:50278
-
Format
-
Document (PDF)
-
PURL
-
http://purl.flvc.org/ucf/fd/CFE0005551
-
-
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
Pages