Matching Items (499)
Filtering by
- All Subjects: Creative Project
Description
Many learning models have been proposed for various tasks in visual computing. Popular examples include hidden Markov models and support vector machines. Recently, sparse-representation-based learning methods have attracted a lot of attention in the computer vision field, largely because of their impressive performance in many applications. In the literature, many of such sparse learning methods focus on designing or application of some learning techniques for certain feature space without much explicit consideration on possible interaction between the underlying semantics of the visual data and the employed learning technique. Rich semantic information in most visual data, if properly incorporated into algorithm design, should help achieving improved performance while delivering intuitive interpretation of the algorithmic outcomes. My study addresses the problem of how to explicitly consider the semantic information of the visual data in the sparse learning algorithms. In this work, we identify four problems which are of great importance and broad interest to the community. Specifically, a novel approach is proposed to incorporate label information to learn a dictionary which is not only reconstructive but also discriminative; considering the formation process of face images, a novel image decomposition approach for an ensemble of correlated images is proposed, where a subspace is built from the decomposition and applied to face recognition; based on the observation that, the foreground (or salient) objects are sparse in input domain and the background is sparse in frequency domain, a novel and efficient spatio-temporal saliency detection algorithm is proposed to identify the salient regions in video; and a novel hidden Markov model learning approach is proposed by utilizing a sparse set of pairwise comparisons among the data, which is easier to obtain and more meaningful, consistent than tradition labels, in many scenarios, e.g., evaluating motion skills in surgical simulations. In those four problems, different types of semantic information are modeled and incorporated in designing sparse learning algorithms for the corresponding visual computing tasks. Several real world applications are selected to demonstrate the effectiveness of the proposed methods, including, face recognition, spatio-temporal saliency detection, abnormality detection, spatio-temporal interest point detection, motion analysis and emotion recognition. In those applications, data of different modalities are involved, ranging from audio signal, image to video. Experiments on large scale real world data with comparisons to state-of-art methods confirm the proposed approaches deliver salient advantages, showing adding those semantic information dramatically improve the performances of the general sparse learning methods.
ContributorsZhang, Qiang (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2014
Description
Sparse learning is a technique in machine learning for feature selection and dimensionality reduction, to find a sparse set of the most relevant features. In any machine learning problem, there is a considerable amount of irrelevant information, and separating relevant information from the irrelevant information has been a topic of focus. In supervised learning like regression, the data consists of many features and only a subset of the features may be responsible for the result. Also, the features might require special structural requirements, which introduces additional complexity for feature selection. The sparse learning package, provides a set of algorithms for learning a sparse set of the most relevant features for both regression and classification problems. Structural dependencies among features which introduce additional requirements are also provided as part of the package. The features may be grouped together, and there may exist hierarchies and over- lapping groups among these, and there may be requirements for selecting the most relevant groups among them. In spite of getting sparse solutions, the solutions are not guaranteed to be robust. For the selection to be robust, there are certain techniques which provide theoretical justification of why certain features are selected. The stability selection, is a method for feature selection which allows the use of existing sparse learning methods to select the stable set of features for a given training sample. This is done by assigning probabilities for the features: by sub-sampling the training data and using a specific sparse learning technique to learn the relevant features, and repeating this a large number of times, and counting the probability as the number of times a feature is selected. Cross-validation which is used to determine the best parameter value over a range of values, further allows to select the best parameter value. This is done by selecting the parameter value which gives the maximum accuracy score. With such a combination of algorithms, with good convergence guarantees, stable feature selection properties and the inclusion of various structural dependencies among features, the sparse learning package will be a powerful tool for machine learning research. Modular structure, C implementation, ATLAS integration for fast linear algebraic subroutines, make it one of the best tool for a large sparse setting. The varied collection of algorithms, support for group sparsity, batch algorithms, are a few of the notable functionality of the SLEP package, and these features can be used in a variety of fields to infer relevant elements. The Alzheimer Disease(AD) is a neurodegenerative disease, which gradually leads to dementia. The SLEP package is used for feature selection for getting the most relevant biomarkers from the available AD dataset, and the results show that, indeed, only a subset of the features are required to gain valuable insights.
ContributorsThulasiram, Ramesh (Author) / Ye, Jieping (Thesis advisor) / Xue, Guoliang (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2011
Description
Rapid advance in sensor and information technology has resulted in both spatially and temporally data-rich environment, which creates a pressing need for us to develop novel statistical methods and the associated computational tools to extract intelligent knowledge and informative patterns from these massive datasets. The statistical challenges for addressing these massive datasets lay in their complex structures, such as high-dimensionality, hierarchy, multi-modality, heterogeneity and data uncertainty. Besides the statistical challenges, the associated computational approaches are also considered essential in achieving efficiency, effectiveness, as well as the numerical stability in practice. On the other hand, some recent developments in statistics and machine learning, such as sparse learning, transfer learning, and some traditional methodologies which still hold potential, such as multi-level models, all shed lights on addressing these complex datasets in a statistically powerful and computationally efficient way. In this dissertation, we identify four kinds of general complex datasets, including "high-dimensional datasets", "hierarchically-structured datasets", "multimodality datasets" and "data uncertainties", which are ubiquitous in many domains, such as biology, medicine, neuroscience, health care delivery, manufacturing, etc. We depict the development of novel statistical models to analyze complex datasets which fall under these four categories, and we show how these models can be applied to some real-world applications, such as Alzheimer's disease research, nursing care process, and manufacturing.
ContributorsHuang, Shuai (Author) / Li, Jing (Thesis advisor) / Askin, Ronald (Committee member) / Ye, Jieping (Committee member) / Runger, George C. (Committee member) / Arizona State University (Publisher)
Created2012
Description
Computer vision technology automatically extracts high level, meaningful information from visual data such as images or videos, and the object recognition and detection algorithms are essential in most computer vision applications. In this dissertation, we focus on developing algorithms used for real life computer vision applications, presenting innovative algorithms for object segmentation and feature extraction for objects and actions recognition in video data, and sparse feature selection algorithms for medical image analysis, as well as automated feature extraction using convolutional neural network for blood cancer grading.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
ContributorsCao, Jun (Author) / Li, Baoxin (Thesis advisor) / Liu, Huan (Committee member) / Zhang, Yu (Committee member) / Zhang, Junshan (Committee member) / Arizona State University (Publisher)
Created2018
Description
How do you convey what’s interesting and important to you as an artist in a digital world of constantly shifting attentions? For many young creatives, the answer is original characters, or OCs. An OC is a character that an artist creates for personal enjoyment, whether based on an already existing story or world, or completely from their own imagination.
As creations made for purely personal interests, OCs are an excellent elevator pitch to talk one creative to another, opening up opportunities for connection in a world where communication is at our fingertips but personal connection is increasingly harder to make. OCs encourage meaningful interaction by offering themselves as muses, avatars, and story pieces, and so much more, where artists can have their characters interact with other creatives through many different avenues such as art-making, table top games, or word of mouth.
In this thesis, I explore the worlds and aesthetics of many creators and their original characters through qualitative research and collaborative art-making. I begin with a short survey of my creative peers, asking general questions about their characters and thoughts on OCs, then move to sketching characters from various creators. I focus my research to a group of seven core creators and their characters, whom I interview and work closely with in order to create a series of seven final paintings of their original characters.
As creations made for purely personal interests, OCs are an excellent elevator pitch to talk one creative to another, opening up opportunities for connection in a world where communication is at our fingertips but personal connection is increasingly harder to make. OCs encourage meaningful interaction by offering themselves as muses, avatars, and story pieces, and so much more, where artists can have their characters interact with other creatives through many different avenues such as art-making, table top games, or word of mouth.
In this thesis, I explore the worlds and aesthetics of many creators and their original characters through qualitative research and collaborative art-making. I begin with a short survey of my creative peers, asking general questions about their characters and thoughts on OCs, then move to sketching characters from various creators. I focus my research to a group of seven core creators and their characters, whom I interview and work closely with in order to create a series of seven final paintings of their original characters.
ContributorsCote, Jacqueline (Author) / Button, Melissa M (Thesis director) / Dove-Viebahn, Aviva (Committee member) / School of Art (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In the past ten years, the United States’ sound recording industries have experienced significant decreases in employment opportunities for aspiring audio engineers from economic imbalances in the music industry’s digital streaming era and reductions in government funding for career and technical education (CTE). The Recording Industry Association of America reports promises of music industry sustainability based on increasing annual revenues in paid streaming services and artists’ high creative demand. The rate of new audio engineer entries in the sound recording subsection of the music industry is not viable to support streaming artists’ high demand to engineer new music recordings. Offering CTE programs in secondary education is rare for aspiring engineers with insufficient accessibility to pursue a post-secondary or vocational education because of financial and academic limitations. These aspiring engineers seek alternatives for receiving an informal education in audio engineering on the Internet using video sharing services like YouTube to search for tutorials and improve their engineering skills. The shortage of accessible educational materials on the Internet restricts engineers from advancing their own audio engineering education, reducing opportunities to enter a desperate job market in need of independent, home studio-based engineers. Content creators on YouTube take advantage of this situation and commercialize their own video tutorial series for free and selling paid subscriptions to exclusive content. This is misleading for newer engineers because these tutorials omit important understandings of fundamental engineering concepts. Instead, content creators teach inflexible engineering methodologies that are mostly beneficial to their own way of thinking. Content creators do not often assess the incompatibility of teaching their own methodologies to potential entrants in a profession that demands critical thinking skills requiring applied fundamental audio engineering concepts and techniques. This project analyzes potential solutions to resolve the deficiencies in online audio engineering education and experiments with structuring simple, deliverable, accessible educational content and materials to new entries in audio engineering. Designing clear, easy to follow material to these new entries in audio engineering is essential for developing a strong understanding for the application of fundamental concepts in future engineers’ careers. Approaches to creating and designing educational content requires translating complex engineering concepts through simplified mediums that reduce limitations in learning for future audio engineers.
ContributorsBurns, Triston Connor (Author) / Tobias, Evan (Thesis director) / Libman, Jeff (Committee member) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
There has been a recent push for queer fiction, especially in the young adult genre, whose focus is gay and lesbian relationships. This growth is much needed in terms of visibility and the furthering of acceptance, but there are still subjects within the LGBTQ+ community that need to be addressed, including bisexual, asexual, and non-binary erasure. There are many people who claim that these identities do not exist, are labels used as a stepping stone on one's journey to discovering that they are homosexual, or are invented excuses for overtly promiscuous or prudish behavior. The existence of negative stereotypes, particularly those of non-binary individuals, is largely due to a lack of visibility and respectful representation within media and popular culture. However, there is still a dearth of non-binary content in popular literature outside of young adult fiction. Can You See Me? aims to fill the gap in bisexual, asexual, and non-binary representation in adult literature. Each of the four stories that make up this collection deals with an aspect of gender and/or sexuality that has been erased, ignored, or denied visibility in American popular culture. The first story, "We'll Grow Lemon Trees," examines bisexual erasure through the lens of sociolinguistics. A bisexual Romanian woman emigrates to Los Angeles in 1989 and must navigate a new culture, learn new languages, and try to move on from her past life under a dictatorship where speaking up could mean imprisonment or death. The second story "Up, Down, All Around," is about a young genderqueer child and their parents dealing with microaggressions, examining gender norms, and exploring personal identity through imaginary scenarios, each involving an encounter with an unknown entity and a colander. The third story, "Aces High," follows two asexual characters from the day they're born to when they are 28 years old, as they find themselves in pop culture. The two endure identity crises, gender discrimination, erasure, individual obsessions, and prejudice as they learn to accept themselves and embrace who they are. In the fourth and final story, "Mile Marker 72," a gay Mexican man must hide in plain sight as he deals with the death of his partner and coming out to his best friend, whose brother is his partner's murderer.
ContributorsOchser, Jordyn M. (Author) / Bell, Matt (Thesis director) / Free, Melissa (Committee member) / Department of English (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Pandora is a play exploring our relationship with gendered technology through the lens of artificial intelligence. Can women be subjective under patriarchy? Do robots who look like women have subjectivity? Hoping to create a better version of ourselves, The Engineer must navigate the loss of her creation, and Pandora must navigate their new world. The original premiere run was March 27-28, 2018, original cast: Caitlin Andelora, Rikki Tremblay, and Michael Tristano Jr.
ContributorsToye, Abigail Elizabeth (Author) / Linde, Jennifer (Thesis director) / Abele, Kelsey (Committee member) / Department of Information Systems (Contributor) / Economics Program in CLAS (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
After freelancing on my own for the past year and a half, I have realized that one of the biggest obstacles to college entrepreneurs is a fear or apprehension to sales. As a computer science major trying to sell my services, I discovered very quickly that I had not been prepared for the difficulty of learning sales. Sales get a bad rap and very often is the last thing that young entrepreneurs want to try, but the reality is that sales is oxygen to a company and a required skill for an entrepreneur. Due to this, I compiled all of my knowledge into an e-book for young entrepreneurs starting out to learn how to open up a conversation with a prospect all the way to closing them on the phone. Instead of starting from scratch like I did, college entrepreneurs can learn the bare basics of selling their own services, even if they are terrified of sales and what it entails. In this e-book, there are tips that I have learned to deal with my anxiety about sales such as taking the pressure off of yourself and prioritizing listening more than pitching. Instead of trying to teach sales expecting people to be natural sales people, this e-book takes the approach of helping entrepreneurs that are terrified of sales and show them how they can cope with this fear and still close a client. In the future, I hope young entrepreneurs will have access to more resources that handle this fear and make it much easier for them to learn it by themselves. This e-book is the first step.
ContributorsMead, Kevin Tyler (Author) / Sebold, Brent (Thesis director) / Kruse, Gabriel (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
South Korea possesses the only culture to successfully create a transnationality and hybridity formula that is not replicable. So why Korea and why now? The goal of this thesis creative project is to demonstrate the marketing and communications strategies used in the arts and culture industry to drive global awareness and interest in K-Pop. In order to achieve that goal, I created HellotoHallyu.com, a website designed for an audience of Millennials and Generation Z English speakers to increase their awareness of the growth and impact of the Korean Wave in a fun and engaging way. So those who may hear a song by K-Pop idol group BTS on a music awards show in the U.S. can get themselves up-to-speed before diving into the fast-paced world of K-culture gossip sites and forums. Hello to Hallyu delivers consumer-friendly, educational content easily understood by English speakers with no prior knowledge of Korean culture, while still piquing the interest of K-pop connoisseurs. It provides the background necessary for even the most dedicated fans to glean new knowledge of Korea's cultural industry and a new perspective on the content they consume. Hello to Hallyu is based on a combination of secondary and primary research conducted over four semesters beginning Spring 2017 and continuing through Spring 2018. This project is set up as an ever-expanding resource freely available to anyone with internet access. The research required to maintain the site will continue with the Wave. However, the content currently on the site is evergreen, a documentation of the history of the Wave as explained in peer-reviewed articles and by Dr. Ingyu Oh as well as a documentation of my personal experience with Hallyu while in Korea and as a Westerner living in the U.S. The site's goal is to demonstrate the marketing and communications strategies used in the industry to drive global awareness and interest. Through this means, Hello to Hallyu aims to provide fully developed multimedia content intended to increase English speakers' awareness of the growth and impact of the Korean Wave as shown through site visits, content views, and audience engagement.
ContributorsTravis, Lisa Anne (Author) / Hass, Mark (Thesis director) / Shewell, Justin (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05