View All Items
(1 - 20 of 140)
Pages
- Title
- Digital Image Processing Using NTEC Facilities.
- Creator
-
Roesch, James F., Simons, Jr., Fred O., Engineering
- Abstract / Description
-
University of Central Florida College of Engineering Thesis; Digital image enhancement refers to the improvement of a given image for human interpretation. Digital image processing facilities are those in which hardware and software computing elements are combined in such a way as to enable the processing of digital images. This report describes the use of the Naval Training Equipment Center (NTEC) Computer Systems Laboratory computing facilities to enhance digital images. Described are two...
Show moreUniversity of Central Florida College of Engineering Thesis; Digital image enhancement refers to the improvement of a given image for human interpretation. Digital image processing facilities are those in which hardware and software computing elements are combined in such a way as to enable the processing of digital images. This report describes the use of the Naval Training Equipment Center (NTEC) Computer Systems Laboratory computing facilities to enhance digital images. Described are two major hardware systems, the IKONAS RDS-3000 raster display graphics system and the VAX-11/780, and the digital image processing program (DIMPRP) written by the author. Digital image enhancement theory and practice are addressed through a discussion of the DIMPRP software. Finally, enhancements to the NTEC digital image processing facility such as improvements in hardware reliability, documentation, and increased speed of program esecution are discussed.
Show less - Date Issued
- 1984
- Identifier
- CFR0008160, ucf:53072
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFR0008160
- Title
- A METHOD OF CONTENT-BASED IMAGE RETRIEVAL FOR THE GENERATION OF IMAGE MOSAICS.
- Creator
-
Snead, Michael, Richie, Samuel, University of Central Florida
- Abstract / Description
-
An image mosaic is an artistic work that uses a number of smaller images creatively combined together to form another larger image. Each building block image, or tessera, has its own distinctive and meaningful content, but when viewed from a distance the tesserae come together to form an aesthetically pleasing montage. This work presents the design and implementation of MosaiX, a computer software system that generates these image mosaics automatically. To control the image mosaic creation...
Show moreAn image mosaic is an artistic work that uses a number of smaller images creatively combined together to form another larger image. Each building block image, or tessera, has its own distinctive and meaningful content, but when viewed from a distance the tesserae come together to form an aesthetically pleasing montage. This work presents the design and implementation of MosaiX, a computer software system that generates these image mosaics automatically. To control the image mosaic creation process, several parameters are used within the system. Each parameter affects the overall mosaic quality, as well as required processing time, in its own unique way. A detailed analysis is performed to evaluate each parameter individually. Additionally, this work proposes two novel ways by which to evaluate the quality of an image mosaic in a quantitative way. One method focuses on the perceptual color accuracy of the mosaic reproduction, while the other concentrates on edge replication. Both measures include preprocessing to take into account the unique visual features present in an image mosaic. Doing so minimizes quality penalization due the inherent properties of an image mosaic that make them visually appealing.
Show less - Date Issued
- 2007
- Identifier
- CFE0001585, ucf:47115
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001585
- Title
- HOW AM I NOT MYSELF? A SEMIOTIC ANALYSIS OF IMAGES.
- Creator
-
Main, Michael, Congdon, Kristin, University of Central Florida
- Abstract / Description
-
There has been much debate in the history of philosophy aimed at determining what it is, exactly, that makes a person who and what she is. Varying theories have offered a wide range of concepts in pursuit of the answer to this question. Some thinkers, such as B.F. Skinner, have claimed that it is observable behavior patterns that determine who and what a person is. Yet other thinkers, such as Carl Jung, have attributed unconscious motivators as being determinative in deciphering who and what...
Show moreThere has been much debate in the history of philosophy aimed at determining what it is, exactly, that makes a person who and what she is. Varying theories have offered a wide range of concepts in pursuit of the answer to this question. Some thinkers, such as B.F. Skinner, have claimed that it is observable behavior patterns that determine who and what a person is. Yet other thinkers, such as Carl Jung, have attributed unconscious motivators as being determinative in deciphering who and what a person is. Jung claims that it is the conscious and unconscious working together that determines who and what a person is. The purpose of this thesis is to discover evidence that supports or disproves the theory of self in which the unconscious and conscious work together to determine who and/or what a person is. This is done by semiotically analyzing the Visual Products (VP) of Visual Product Producers (VPP) who were or are afflicted with Bipolar Disorder. This thesis consists of the semiotic analysis of selected works by Jackson Pollock, Virginia Woolf, Vincent Van Gogh, and myself (Michael Main). Semiotic analysis studies how meanings are generated as opposed to what meanings are generated. It should be noted that semiotics was used strictly as a method of analysis and not as a guiding philosophy. In examining how the works of the selected VPPs generate meaning, it is hoped that evidence is produced that proves or disproves the theory of who or what a person is as determined by the interaction of the conscious and unconscious.
Show less - Date Issued
- 2011
- Identifier
- CFH0003792, ucf:44776
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0003792
- Title
- AM I TOO FAT TO BE A PRINCESS? EXAMINING THE EFFECTS OF POPULAR CHILDREN'S MEDIA ON PRESCHOOLERS' BODY IMAGE.
- Creator
-
Hayes, Sharon, Dunn, Stacey, University of Central Florida
- Abstract / Description
-
The current study investigated the effects of brief exposure to appearance-related media on female preschoolers' body image. Results indicated that exposure did not affect body dissatisfaction or engagement in appearance-related play behaviors. Surprisingly, participants' self-reported frequency of weight concerns decreased at posttest. In contrast to older populations, it is possible that young children may adopt the persona of attractive characters with whom they identify rather...
Show moreThe current study investigated the effects of brief exposure to appearance-related media on female preschoolers' body image. Results indicated that exposure did not affect body dissatisfaction or engagement in appearance-related play behaviors. Surprisingly, participants' self-reported frequency of weight concerns decreased at posttest. In contrast to older populations, it is possible that young children may adopt the persona of attractive characters with whom they identify rather than comparing themselves to the characters. This level of identification temporarily may alleviate weight concerns. This is the first empirical study to provide support for previous findings that suggest media exposure does not affect body image in young children. Also presented are data regarding familial influences and other media consumption (e.g., television viewing) on girls' body dissatisfaction.
Show less - Date Issued
- 2008
- Identifier
- CFE0002039, ucf:47588
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002039
- Title
- CYBER SEXY:ELECTRONIC GAME PLAY AND PERCEPTIONS OF ATTRACTIVENESS AMONG COLLEGE-AGED MEN.
- Creator
-
Wack, Elizabeth, Tantleff Dunn, Stacey, University of Central Florida
- Abstract / Description
-
The current study was conducted to determine whether or not electronic gaming is related to the formation of certain body ideals and appraisals of attractiveness. A sample of 219 college-aged males (age 18 to 32) completed a variety of measures designed to gather information about their game play habits, their perceptions of their own attractiveness (MBSRQ, SMAQ), and their perceptions of women's attractiveness (BCRS, FRS, photographs of women of different BMIs). Results indicate that men...
Show moreThe current study was conducted to determine whether or not electronic gaming is related to the formation of certain body ideals and appraisals of attractiveness. A sample of 219 college-aged males (age 18 to 32) completed a variety of measures designed to gather information about their game play habits, their perceptions of their own attractiveness (MBSRQ, SMAQ), and their perceptions of women's attractiveness (BCRS, FRS, photographs of women of different BMIs). Results indicate that men's ratings of women's attractiveness vary across the genres of games most frequently played but that frequency of play and age of commencement of game play are not related to self-perceptions of physical attractiveness, the association of positive attributes with muscularity, or the drive to become more muscular. However, results suggest that men's appearance satisfaction and the degree to which they value muscularity are influenced by the extent to which they compare their own appearance to that of the characters they play in the games. Results indicate that unlike other forms of media, electronic gaming is not related to decreased appearance satisfaction in players or the formation of unrealistic standards of attractiveness for women.
Show less - Date Issued
- 2007
- Identifier
- CFE0001661, ucf:47243
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001661
- Title
- DEBRIS TRACKING IN A SEMISTABLE BACKGROUND.
- Creator
-
Vanumamalai, KarthikKalathi, Kasparis, Takis, University of Central Florida
- Abstract / Description
-
Object Tracking plays a very pivotal role in many computer vision applications such as video surveillance, human gesture recognition and object based video compressions such as MPEG-4. Automatic detection of any moving object and tracking its motion is always an important topic of computer vision and robotic fields. This thesis deals with the problem of detecting the presence of debris or any other unexpected objects in footage obtained during spacecraft launches, and this poses a challenge...
Show moreObject Tracking plays a very pivotal role in many computer vision applications such as video surveillance, human gesture recognition and object based video compressions such as MPEG-4. Automatic detection of any moving object and tracking its motion is always an important topic of computer vision and robotic fields. This thesis deals with the problem of detecting the presence of debris or any other unexpected objects in footage obtained during spacecraft launches, and this poses a challenge because of the non-stationary background. When the background is stationary, moving objects can be detected by frame differencing. Therefore there is a need for background stabilization before tracking any moving object in the scene. Here two problems are considered and in both footage from Space shuttle launch is considered with the objective to track any debris falling from the Shuttle. The proposed method registers two consecutive frames using FFT based image registration where the amount of transformation parameters (translation, rotation) is calculated automatically. This information is the next passed to a Kalman filtering stage which produces a mask image that is used to find high intensity areas which are of potential interest.
Show less - Date Issued
- 2005
- Identifier
- CFE0000886, ucf:46628
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000886
- Title
- TESTING AN INTERVENTION TO ADDRESS THE SOCIOCULTURAL INFLUENCE OF MASS MEDIA ON BODY IMAGE: CAN WE REVERSE THE CURSE?.
- Creator
-
Murray, Janet, Tantleff Dunn, Stacey, University of Central Florida
- Abstract / Description
-
The adverse effects of exposure to unrealistic ideals in the media are well documented, however, this is the first study to explore the possibility that women may experience improvement in body image and affect via social comparison to women with realistic, non-ideal body shape and size. Using material from The Century Project©, the impact of exposure to nude, non-pornographic photographs of women of varied shape, size, age, and physical condition, and the photographed women's personal...
Show moreThe adverse effects of exposure to unrealistic ideals in the media are well documented, however, this is the first study to explore the possibility that women may experience improvement in body image and affect via social comparison to women with realistic, non-ideal body shape and size. Using material from The Century Project©, the impact of exposure to nude, non-pornographic photographs of women of varied shape, size, age, and physical condition, and the photographed women's personal commentaries about how they successfully cope with body image concerns was tested using an experimental design. It was hypothesized that exposure to the photographs and their associated commentaries would lead to an improvement in body image, mood, and self-esteem, and that this effect would be moderated by preexisting levels of internalization of the thin ideal and strong core beliefs about the importance of appearance (schematicity). Women exposed to the photos and comments condition experienced significantly less appearance-related anxiety than those exposed to photo-only and comments-only conditions, and internalization, but not schematicity, moderated this effect. Findings suggest women who have a greater tendency to internalize sociocultural body image standards may be more receptive to positive changes in these standards when presented with a persuasive visual and cognitive stimulus. However, without both aspects (visual and commentary) high internalizers appear to experience greater negative reactions to these stimuli.
Show less - Date Issued
- 2005
- Identifier
- CFE0000707, ucf:46599
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000707
- Title
- VISIONING THE NATION: CLASSICAL IMAGES AS ALLEGORY DURING THE FRENCH REVOLUTION.
- Creator
-
Reed, Kristopher, Lyons, Amelia, University of Central Florida
- Abstract / Description
-
In the latter half of the Eighteenth Century, France experienced a seismic shift in the nature of political culture. The king gave way to the nation at the center of political life as the location of sovereignty transferred to the people. While the French Revolution changed the structure of France's government, it also changed the allegorical representations of the nation. At the Revolution's onset, the monarchy embodied both the state and nation as equated ideas. During the...
Show moreIn the latter half of the Eighteenth Century, France experienced a seismic shift in the nature of political culture. The king gave way to the nation at the center of political life as the location of sovereignty transferred to the people. While the French Revolution changed the structure of France's government, it also changed the allegorical representations of the nation. At the Revolution's onset, the monarchy embodied both the state and nation as equated ideas. During the Revolutionary Decade and through the reign of Napoleon different governments experienced the need to reorient these symbols away from the person of the king to the national community. Following the king's execution, the Committee government invented connections to the ancient past in order to build legitimacy for their rule in addition to extricating the monarchy's symbols from political life. During the rule of Napoleon, he used classical symbols to associate himself with Roman Emperors to embody the nation in his person. Through an examination of the different types of classical symbols that each government illustrates the different ways that attempted to symbolically document this important shift in the location of sovereignty away from the body of the king to the nation.
Show less - Date Issued
- 2007
- Identifier
- CFE0001901, ucf:47496
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001901
- Title
- High resolution time-resolved imaging system in the vacuum ultraviolet region.
- Creator
-
Jang, Yuseong, Richardson, Martin, Moharam, Jim, Likamwa, Patrick, University of Central Florida
- Abstract / Description
-
High-power debris-free vacuum ultraviolet (VUV) light sources have applications in several scientific and engineering areas, such as high volume manufacturing lithography and inspection tools in the semiconductor industry, as well as other applications in material processing and photochemistry.For the past decades, the semiconductor industry has been driven by what is called "Moore's Law". The entire semiconductor industry relies on this rule, which requires chip makers to pack transistors...
Show moreHigh-power debris-free vacuum ultraviolet (VUV) light sources have applications in several scientific and engineering areas, such as high volume manufacturing lithography and inspection tools in the semiconductor industry, as well as other applications in material processing and photochemistry.For the past decades, the semiconductor industry has been driven by what is called "Moore's Law". The entire semiconductor industry relies on this rule, which requires chip makers to pack transistors more tightly with every new generation of chips, shrinking the size of transistors. The ability to solve roadmap challenges is, at least partly, proportional to our ability to measure them. The focus of this thesis is on imaging transient VUV laser plasma sources with specialized reflective imaging optics for metrology applications. The plasma dynamics in novel laser-based Zinc and Tin plasma sources will be discussed. The Schwarzschild optical system was installed to investigate the time evolution of the plasma size in the VUV region at wavelengths of 172 nm and 194 nm. The outcomes are valuable for interpreting the dynamics of low-temperature plasma and to optimize laser-based VUV light sources.
Show less - Date Issued
- 2014
- Identifier
- CFE0005352, ucf:50492
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005352
- Title
- OPTIMIZING THE HIGH DYNAMIC RANGE IMAGING PIPELINE.
- Creator
-
Akyuz, Ahmet, Reinhard, Erik, University of Central Florida
- Abstract / Description
-
High dynamic range (HDR) imaging is a rapidly growing field in computer graphics and image processing. It allows capture, storage, processing, and display of photographic information within a scene-referred framework. The HDR imaging pipeline consists of the major steps an HDR image is expected to go through from capture to display. It involves various techniques to create HDR images, pixel encodings and file formats for storage, tone mapping for display on conventional display devices and...
Show moreHigh dynamic range (HDR) imaging is a rapidly growing field in computer graphics and image processing. It allows capture, storage, processing, and display of photographic information within a scene-referred framework. The HDR imaging pipeline consists of the major steps an HDR image is expected to go through from capture to display. It involves various techniques to create HDR images, pixel encodings and file formats for storage, tone mapping for display on conventional display devices and direct display on HDR capable screens. Each of these stages have important open problems, which need to be addressed for a smoother transition to an HDR imaging pipeline. We addressed some of these important problems such as noise reduction in HDR imagery, preservation of color appearance, validation of tone mapping operators, and image display on HDR monitors. The aim of this thesis is thus, to present our findings and describe the research we have conducted within the framework of optimizing the HDR imaging pipeline.
Show less - Date Issued
- 2007
- Identifier
- CFE0001875, ucf:47404
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001875
- Title
- Computational imaging systems for high-speed, adaptive sensing applications.
- Creator
-
Sun, Yangyang, Pang, Sean, Li, Guifang, Schulzgen, Axel, Pensky, Marianna, University of Central Florida
- Abstract / Description
-
Driven by the advances in signal processing and ubiquitous availability of high-speed low-cost computing resources over the past decade, computational imaging has seen the growing interest. Improvements on spatial, temporal, and spectral resolutions have been made with novel designs of imaging systems and optimization methods. However, there are two limitations in computational imaging. 1), Computational imaging requires full knowledge and representation of the imaging system called the...
Show moreDriven by the advances in signal processing and ubiquitous availability of high-speed low-cost computing resources over the past decade, computational imaging has seen the growing interest. Improvements on spatial, temporal, and spectral resolutions have been made with novel designs of imaging systems and optimization methods. However, there are two limitations in computational imaging. 1), Computational imaging requires full knowledge and representation of the imaging system called the forward model to reconstruct the object of interest. This limits the applications in the systems with a parameterized unknown forward model such as range imaging systems. 2), the regularization in the optimization process incorporates strong assumptions which may not accurately reflect the a priori distribution of the object. To overcome these limitations, we propose 1) novel optimization frameworks for applying computational imaging on active and passive range imaging systems and achieve 5-10 folds improvement on temporal resolution in various range imaging systems; 2) a data-driven method for estimating the distribution of high dimensional objects and a framework of adaptive sensing for maximum information gain. The adaptive strategy with our proposed method outperforms Gaussian process-based method consistently. The work would potentially benefit high-speed 3D imaging applications such as autonomous driving and adaptive sensing applications such as low-dose adaptive computed tomography(CT).
Show less - Date Issued
- 2019
- Identifier
- CFE0007867, ucf:52784
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007867
- Title
- ADVANCES IN THE OPTO-MECHANICAL DESIGN AND ALIGNMENT OF THE HEHSI IMAGING SPECTROMETER BASED ON A SAGNAC INTERFEROMETER.
- Creator
-
Schreiber, Michael, Ham, Chan, University of Central Florida
- Abstract / Description
-
The High Efficiency HyperSpectral Imager (HEHSI) is a Fourier Transform hyperspectral imager based on a Sagnac interferometer. This thesis research concentrates on the design upgrade and calibration of HEHSI from a proof of concept instrument to a prototype field instrument. Stability is enhanced by removing degrees of freedom and alignment is enhanced by providing for in-situ adjustments. The use of off the shelf components allows for reduced development time and cost constraints. HEHSI is...
Show moreThe High Efficiency HyperSpectral Imager (HEHSI) is a Fourier Transform hyperspectral imager based on a Sagnac interferometer. This thesis research concentrates on the design upgrade and calibration of HEHSI from a proof of concept instrument to a prototype field instrument. Stability is enhanced by removing degrees of freedom and alignment is enhanced by providing for in-situ adjustments. The use of off the shelf components allows for reduced development time and cost constraints. HEHSI is capable of multiple configurations to accommodate sensors and optics with specialized capabilities for multiple wavelength ranges and viewing conditions. With a spectral response of 400 to 1000 nanometers in the visible and very near IR as well as 900 to 1700nm in the Near IR. Creation and use of a real time feedback alignment utility allow quantifiable signal comparison and image alignment. Advances allow for HEHSI to remain aligned during data collection sessions and confirmation of alignment through quantitative measures.
Show less - Date Issued
- 2005
- Identifier
- CFE0000553, ucf:46443
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000553
- Title
- NEUROCOGNITIVE CORRELATES OF BODY IMAGE DISTURBANCE.
- Creator
-
Frei, Elizabeth, Tantleff-Dunn, Stacey, University of Central Florida
- Abstract / Description
-
Body image, broadly defined as an individual's general experience of his or her physical appearance, is a multidimensional phenomenon that has been found to affect functioning throughout the lifetime. Although some degree of dissatisfaction has been found to be a common aspect of the female experience, research suggests that a disturbance in body image can result in a number of clinical complications, particularly the development of an eating disorder (ED). Despite the relationship...
Show moreBody image, broadly defined as an individual's general experience of his or her physical appearance, is a multidimensional phenomenon that has been found to affect functioning throughout the lifetime. Although some degree of dissatisfaction has been found to be a common aspect of the female experience, research suggests that a disturbance in body image can result in a number of clinical complications, particularly the development of an eating disorder (ED). Despite the relationship between body image and EDs, examinations of the cognitive underpinnings of the relationship between body image disturbance and EDs are relatively few and inconclusive. Research indicates that individuals with an ED diagnosis exhibit cognitive rigidity (deficits in set-shifting ability) and weak central coherence(as demonstrated by performance on measures of information processing style). However, research has not established whether individuals with body image disturbance who do not meet criteria for an ED exhibit comparable performance. The aim of the current study was to determine whether individuals with body image disturbance exhibit similar patterns of neuropsychological functioning. A sample of women with high levels of body image disturbance completed a battery of cognitive tests and outcomes were compared to a group of women with little disturbance and also compared with performance of individuals with diagnosed EDs as cited in previous studies. Overall, the results do not clearly indicate that women with body image disturbance have difficulties with set-shifting tasks and global information processing, however some preliminary patterns did emerge. These preliminary findings extend existing theoretical models of body image and have potential to inform clinical efforts aimed at improving treatment protocols for body image disturbance and EDs by targeting these aspects of neurocognition during treatment.
Show less - Date Issued
- 2009
- Identifier
- CFE0002934, ucf:47943
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002934
- Title
- ANALYSIS OF KOLMOGOROV'S SUPERPOSITION THEOREM AND ITS IMPLEMENTATION IN APPLICATIONS WITH LOW AND HIGH DIMENSIONAL DATA.
- Creator
-
Bryant, Donald, Li, Xin, University of Central Florida
- Abstract / Description
-
In this dissertation, we analyze Kolmogorov's superposition theorem for high dimensions. Our main goal is to explore and demonstrate the feasibility of an accurate implementation of Kolmogorov's theorem. First, based on Lorentz's ideas, we provide a thorough discussion on the proof and its numerical implementation of the theorem in dimension two. We present computational experiments which prove the feasibility of the theorem in applications of low dimensions (namely, dimensions...
Show moreIn this dissertation, we analyze Kolmogorov's superposition theorem for high dimensions. Our main goal is to explore and demonstrate the feasibility of an accurate implementation of Kolmogorov's theorem. First, based on Lorentz's ideas, we provide a thorough discussion on the proof and its numerical implementation of the theorem in dimension two. We present computational experiments which prove the feasibility of the theorem in applications of low dimensions (namely, dimensions two and three). Next, we present high dimensional extensions with complete and detailed proofs and provide the implementation that aims at applications with high dimensionality. The amalgamation of these ideas is evidenced by applications in image (two dimensional) and video (three dimensional) representations, the content based image retrieval, video retrieval, de-noising and in-painting, and Bayesian prior estimation of high dimensional data from the fields of computer vision and image processing.
Show less - Date Issued
- 2008
- Identifier
- CFE0002236, ucf:47909
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002236
- Title
- LEARNING GEOMETRY-FREE FACE RE-LIGHTING.
- Creator
-
Moore, Thomas, Foroosh, Hassan, University of Central Florida
- Abstract / Description
-
The accurate modeling of the variability of illumination in a class of images is a fundamental problem that occurs in many areas of computer vision and graphics. For instance, in computer vision there is the problem of facial recognition. Simply, one would hope to be able to identify a known face under any illumination. On the other hand, in graphics one could imagine a system that, given an image, the illumination model could be identified and then used to create new images. In this thesis...
Show moreThe accurate modeling of the variability of illumination in a class of images is a fundamental problem that occurs in many areas of computer vision and graphics. For instance, in computer vision there is the problem of facial recognition. Simply, one would hope to be able to identify a known face under any illumination. On the other hand, in graphics one could imagine a system that, given an image, the illumination model could be identified and then used to create new images. In this thesis we describe a method for learning the illumination model for a class of images. Once the model is learnt it is then used to render new images of the same class under the new illumination. Results are shown for both synthetic and real images. The key contribution of this work is that images of known objects can be re-illuminated using small patches of image data and relatively simple kernel regression models. Additionally, our approach does not require any knowledge of the geometry of the class of objects under consideration making it relatively straightforward to implement. As part of this work we will examine existing geometric and image-based re-lighting techniques; give a detailed description of our geometry-free face re-lighting process; present non-linear regression and basis selection with respect to image synthesis; discuss system limitations; and look at possible extensions and future work.
Show less - Date Issued
- 2007
- Identifier
- CFE0001893, ucf:47394
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001893
- Title
- Understanding images and videos using context.
- Creator
-
Vaca Castano, Gonzalo, Da Vitoria Lobo, Niels, Shah, Mubarak, Mikhael, Wasfy, Jones, W Linwood, Wiegand, Rudolf, University of Central Florida
- Abstract / Description
-
In computer vision, context refers to any information that may influence how visual media are understood.(&)nbsp; Traditionally, researchers have studied the influence of several sources of context in relation to the object detection problem in images. In this dissertation, we present a multifaceted review of the problem of context.(&)nbsp; Context is analyzed as a source of improvement in the object detection problem, not only in images but also in videos. In the case of images, we also...
Show moreIn computer vision, context refers to any information that may influence how visual media are understood.(&)nbsp; Traditionally, researchers have studied the influence of several sources of context in relation to the object detection problem in images. In this dissertation, we present a multifaceted review of the problem of context.(&)nbsp; Context is analyzed as a source of improvement in the object detection problem, not only in images but also in videos. In the case of images, we also investigate the influence of the semantic context, determined by objects, relationships, locations, and global composition, to achieve a general understanding of the image content as a whole. In our research, we also attempt to solve the related problem of finding the context associated with visual media. Given a set of visual elements (images), we want to extract the context that can be commonly associated with these images in order to remove ambiguity. The first part of this dissertation concentrates on achieving image understanding using semantic context.(&)nbsp; In spite of the recent success in tasks such as image classi?cation, object detection, image segmentation, and the progress on scene understanding, researchers still lack clarity about computer comprehension of the content of the image as a whole. Hence, we propose a Top-Down Visual Tree (TDVT) image representation that allows the encoding of the content of the image as a hierarchy of objects capturing their importance, co-occurrences, and type of relations. A novel Top-Down Tree LSTM network is presented to learn about the image composition from the training images and their TDVT representations. Given a test image, our algorithm detects objects and determine the hierarchical structure that they form, encoded as a TDVT representation of the image.A single image could have multiple interpretations that may lead to ambiguity about the intentionality of an image.(&)nbsp; What if instead of having only a single image to be interpreted, we have multiple images that represent the same topic. The second part of this dissertation covers how to extract the context information shared by multiple images. We present a method to determine the topic that these images represent. We accomplish this task by transferring tags from an image retrieval database, and by performing operations in the textual space of these tags. As an application, we also present a new image retrieval method that uses multiple images as input. Unlike earlier works that focus either on using just a single query image or using multiple query images with views of the same instance, the new image search paradigm retrieves images based on the underlying concepts that the input images represent.Finally, in the third part of this dissertation, we analyze the influence of context in videos. In this case, the temporal context is utilized to improve scene identification and object detection. We focus on egocentric videos, where agents require some time to change from one location to another. Therefore, we propose a Conditional Random Field (CRF) formulation, which penalizes short-term changes of the scene identity to improve the scene identity accuracy.(&)nbsp; We also show how to improve the object detection outcome by re-scoring the results based on the scene identity of the tested frame. We present a Support Vector Regression (SVR) formulation in the case that explicit knowledge of the scene identity is available during training time. In the case that explicit scene labeling is not available, we propose an LSTM formulation that considers the general appearance of the frame to re-score the object detectors.
Show less - Date Issued
- 2017
- Identifier
- CFE0006922, ucf:51703
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006922
- 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
- EXPRESSION MORPHING BETWEEN DIFFERENT ORIENTATIONS.
- Creator
-
Fu, Tao, Foroosh, Hassan R., University of Central Florida
- Abstract / Description
-
How to generate new views based on given reference images has been an important and interesting topic in the area of image-based rendering. Two important algorithms that can be used are field morphing and view morphing. Field morphing, which is an algorithm of image morphing, generates new views based on two reference images which were taken at the same viewpoint. The most successful result of field morphing is morphing from one person's face to the other one's face. View morphing, which is...
Show moreHow to generate new views based on given reference images has been an important and interesting topic in the area of image-based rendering. Two important algorithms that can be used are field morphing and view morphing. Field morphing, which is an algorithm of image morphing, generates new views based on two reference images which were taken at the same viewpoint. The most successful result of field morphing is morphing from one person's face to the other one's face. View morphing, which is an algorithm of view synthesis, generates in-between views based on two reference views which were taken at different viewpoints for the same object. The result of view morphing is often an animation of moving one object from the viewpoint of one reference image to the viewpoint of the other one.In this thesis, we proposed a new framework that integrates field morphing and view morphing to solve the problem of expression morphing. Based on four reference images, we successfully generate the morphing from one viewpoint with one expression to another viewpoint with a different expression. We also proposed a new approach to eliminate artifacts that frequently occur in view morphing due to occlusions and in field morphing due to some unforeseen combination of feature lines. We solve these problems by relaxing the monotonicity assumption to piece-wise monotonicity along the epipolar lines. Our experimental results demonstrate the efficiency of this approach in handling occlusions for more realistic synthesis of novel views.
Show less - Date Issued
- 2004
- Identifier
- CFE0000070, ucf:46110
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000070
- Title
- THE EFFECTS OF EXPOSURE TO FEMINIST IDEOLOGY ON WOMEN'S BODY IMAGE.
- Creator
-
Peterson, Rachel, Dunn, Stacey, University of Central Florida
- Abstract / Description
-
Body image disturbance has become an increasing problem among women (Cash & Henry, 1995). Thus researchers have begun to focus on methods of prevention and intervention. Programs utilizing psychoeducation and Festinger's cognitive dissonance theory, for example, have been found to reduce body image dissatisfaction and related symptomatology. The information provided and potential impact are limited, however, because the interventions do not offer women an adaptive method of interpreting the...
Show moreBody image disturbance has become an increasing problem among women (Cash & Henry, 1995). Thus researchers have begun to focus on methods of prevention and intervention. Programs utilizing psychoeducation and Festinger's cognitive dissonance theory, for example, have been found to reduce body image dissatisfaction and related symptomatology. The information provided and potential impact are limited, however, because the interventions do not offer women an adaptive method of interpreting the many appearance-related messages they experience. This study sought to determine if exposure to feminist theory of body image may act as a buffer – a filter through which cultural messages about thinness and beauty are challenged. This feminist schema may provide an alternative interpretation of cultural messages, thereby increasing body image satisfaction. Participants were exposed to one of three interventions (feminist, psychoeducational, control). Exposure to the feminist condition resulted in increased physical appearance satisfaction and likelihood to self-identify as a feminist when compared with the control group. While findings were not extensive, they are nonetheless promising due to the brevity of the intervention.
Show less - Date Issued
- 2005
- Identifier
- CFE0000467, ucf:46374
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000467
- Title
- COMPARISON OF SPARSE CODING AND JPEG CODING SCHEMES FOR BLURRED RETINAL IMAGES.
- Creator
-
Chandrasekaran, Balaji, Wei, Lei, University of Central Florida
- Abstract / Description
-
Overcomplete representations are currently one of the highly researched areas especially in the field of signal processing due to their strong potential to generate sparse representation of signals. Sparse representation implies that given signal can be represented with components that are only rarely significantly active. It has been strongly argued that the mammalian visual system is highly related towards sparse and overcomplete representations. The primary visual cortex has overcomplete...
Show moreOvercomplete representations are currently one of the highly researched areas especially in the field of signal processing due to their strong potential to generate sparse representation of signals. Sparse representation implies that given signal can be represented with components that are only rarely significantly active. It has been strongly argued that the mammalian visual system is highly related towards sparse and overcomplete representations. The primary visual cortex has overcomplete responses in representing an input signal which leads to the use of sparse neuronal activity for further processing. This work investigates the sparse coding with an overcomplete basis set representation which is believed to be the strategy employed by the mammalian visual system for efficient coding of natural images. This work analyzes the Sparse Code Learning algorithm in which the given image is represented by means of linear superposition of sparse statistically independent events on a set of overcomplete basis functions. This algorithm trains and adapts the overcomplete basis functions such as to represent any given image in terms of sparse structures. The second part of the work analyzes an inhibition based sparse coding model in which the Gabor based overcomplete representations are used to represent the image. It then applies an iterative inhibition algorithm based on competition between neighboring transform coefficients to select subset of Gabor functions such as to represent the given image with sparse set of coefficients. This work applies the developed models for the image compression applications and tests the achievable levels of compression of it. The research towards these areas so far proves that sparse coding algorithms are inefficient in representing high frequency sharp image features. So this work analyzes the performance of these algorithms only on the natural images which does not have sharp features and compares the compression results with the current industrial standard coding schemes such as JPEG and JPEG 2000. It also models the characteristics of an image falling on the retina after the distortion effects of the eye and then applies the developed algorithms towards these images and tests compression results.
Show less - Date Issued
- 2007
- Identifier
- CFE0001701, ucf:47328
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001701
