Graphics and Human Computer Interfaces Commons^™

Misheard Me Oronyminator: Using Oronyms To Validate The Correctness Of Frequency Dictionaries, Jennifer G. Hughes

Master's Theses

In the field of speech recognition, an algorithm must learn to tell the difference between "a nice rock" and "a gneiss rock". These identical-sounding phrases are called oronyms. Word frequency dictionaries are often used by speech recognition systems to help resolve phonetic sequences with more than one possible orthographic phrase interpretation, by looking up which oronym of the root phonetic sequence contains the most-common words.

Our paper demonstrates a technique used to validate word frequency dictionary values. We chose to use frequency values from the UNISYN dictionary, which tallies each word on a per-occurance basis, using a proprietary text corpus, …

An Examination Of Presentation Strategies For Textual Data In Augmented Reality, Kanrawi Kitkhachonkunlaphat

Department of Computer Graphics Technology Degree Theses

Videos with embedded text have been widely used in the past and the text in the videos usually contained valuable information. However, it was difficult for people to fully understand the text in videos displayed on smartphones due to obstructions such as color conflicts between letters and the moving background. Adjustments to texts that would support the human visual system, such as changes to brightness and color contrast, increased legibility of text, and taking into account the phantom illumination (PI) illusion (the optical illusion that increases the perception of brightness in a certain area), should be able to improve peoples’ …

Building Capable, Energy-Efficient, Flexible Visualization And Sensing Clusters From Commodity Tablets, Thomas Delgado Dias, Xian Yan, Konstantin Läufer, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

We explore the application of clusters of commodity tablet devices to problems spanning a “trilogy” of concerns: visualization, sensing, and computation. We conjecture that such clusters provide a low-cost, energy-efficient, flexible, and ultimately effective platform to tackle a wide range of problems within this trilogy. This is a work in progress, and we now elaborate our position and give a preliminary status report.

A wide range of Android tablet devices are available in terms of price and capabilities. “You get what you pay for” w.r.t. display resolution, sensors, and chipset---corresponding to the trilogy. $200 gets one a 1280x800-pixel touch display, …

Mebook: A Novel Device Using Video Self-Modeling To Enhance Literacy Among Children With Asd, Nchuaobah Ukaobah, Ju Shen, Sen-Ching S. Cheung

Computer Science Faculty Publications

The aim is to build a video application, MEBOOK, to overlay features of the protagonist on the face of the reader and replace the scene background with animated video pertinent to the story.

An Architecture For Online Semantic Labeling On Ugvs, Arne Suppe, Luis Navarro-Serment, Daniel Munoz, Drew Bagnell, Martial Hebert

Research Collection School Of Computing and Information Systems

We describe an architecture to provide online semantic labeling capabilities to field robots operating in urban environments. At the core of our system is the stacked hierarchical classifier developed by Munoz et al.,1 which classifies regions in monocular color images using models derived from hand labeled training data. The classifier is trained to identify buildings, several kinds of hard surfaces, grass, trees, and sky. When taking this algorithm into the real world, practical concerns with difficult and varying lighting conditions require careful control of the imaging process. First, camera exposure is controlled by software, examining all of the image’s pixels, …

Unified Entity Search In Social Media Community, Ting Yao, Yuan Liu, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

The search for entities is the most common search behavior on the Web, especially in social media communities where entities (such as images, videos, people, locations, and tags) are highly heterogeneous and correlated. While previous research usually deals with these social media entities separately, we are investigating in this paper a unified, multilevel, and correlative entity graph to represent the unstructured social media data, through which various applications (e.g., friend suggestion, personalized image search, image tagging, etc.) can be realized more effectively in one single framework. We regard the social media objects equally as “entities” and all of these applications …

Personal Informatics In Chronic Illness Management, Haley Macleod, Anthony Tang, Sheelagh Carpendale

Research Collection School Of Computing and Information Systems

Many people with chronic illness suffer from debilitating symptoms or episodes that inhibit normal day-to-day function. Pervasive tools offer the possibility to help manage these conditions, particularly by helping people understand their conditions. But, it is unclear how to design these tools, as prior designs have focused on effortful tracking and many see those tools as a burden to use. We report here on an interview study with 12 individuals with chronic illnesses who collect personal data. We learn that these people are motivated through self-discovery and curiosity. We explore how these concepts may support the design of tools that …

Onespace: Shared Depth-Corrected Video Interaction, David Ledo, Bon Adriel Aseniero, Sebastian Boring, Anthony Tang

Research Collection School Of Computing and Information Systems

Video conferencing commonly employs a video portal metaphor to connect individuals from remote spaces. In this work, we explore an alternate metaphor, a shared depth mirror, where video images of two spaces are merged into a single shared, depth-corrected video. Just as seeing one’s mirror image causes reflective interaction, the shared video space changes the nature of interaction in the video space. We realize this metaphor in OneSpace, where the space respects virtual spatial relationships between people and objects, and in so doing, encourages cross-site, full-body interactions. We report preliminary observations of OneSpace in use, describing the role of depth …

Personalized News Recommender Using Twitter, Satya Srinivasa Nirmal Jonnalagedda

Graduate Theses and Dissertations

Online news reading has become a widely popular way to read news articles from news sources around the globe. With the enormous amount of news articles available, users are easily swamped by information of little interest to them. News recommender systems are one approach to help users find interesting articles to read. News recommender systems present the articles to individual users based on their interests rather than presenting articles in order of their occurrence. In this thesis, we present our research on developing personalized news recommendation system with the help of a popular micro-blogging service "Twitter". The news articles are …

Identifying Robust Sift Features For Improved Image Alignment, Sanjay Abhinav Vemuri

Graduate Theses and Dissertations

In this thesis, we will study different ways to improve feature matching by increasing the quality and reducing the number of SIFT features. We created an algorithm to identify robust SIFT features by evaluating how invariant individual feature points are to changes in scale. This allows us to exclude poor SIFT feature points from the matching process and obtain better matching results in reduced time. We also developed techniques consider scale ratios and changes in object orientation when performing feature matching. This allows us to exclude false-positive feature matches and obtain better image alignment results.

Development Of A Comprehensive Database System For A Highway Safety Engineering And Management, Naveen Veeramisti, Justin Baker, Indira Khanal, Kenny Moupita, Alexander Paz

College of Engineering: Graduate Celebration Programs

In simple words, the objective of this study is to develop a comprehensive database system to provide a data for highway safety engineering and management.

Development Of A Smart Application For Police Crash Reports, Sebastien Bonnet, Victor Molano, Alexander Paz

College of Engineering: Graduate Celebration Programs

• Gaining a significant amount of time to help police work
• Developing a User Friendly Interface
• Optimizing the GPS Gaining a significant amount of time to help police work
• Developing a User Friendly Interface
• Optimizing the bar code scan technology
• Application for MC 75 mobile technology

A Visualization Tool For A Highway Safety Management System, Indira Khanal, Naveen Veeramisti, Justin Baker, Alexander Paz

College of Engineering: Graduate Celebration Programs

• With lot of research, Federal Highway Administration
  has released a highway Safety management System
  software called as SafetyAnalyst (SA)
• SA has a suite of analytical tools to identify and
  manage system-wide safety improvements:
  Network Screening
  Diagnosis and Countermeasure Selection
  Economic Analyses and priority Ranking
  Countermeasure Evaluation
• SA provides a very rudimentary approach to display
  results just in tabular and textual format
• This study proposes a visualization tool that expands
  the output capabilities provided by SafetyAnalyst

Separable Subsurface Scattering: An Opengl Implementation, Michael Tetzlaff

Honors Student Works

The light reflection of many materials, including skin, milk, and marble, are not dominated by direct reflection, but rather by the subsurface scattering of light [1]. Most real-time computer graphics techniques, most notably Phong lighting, do not account for subsurface scattering of the diffuse reflectance term. Recently, however, Jorge Jiminez has produced an efficient technique involving only two screen-space blur passes which can achieve the effect of subsurface scattering in real time[3]. Jiminez’ implementation was in Microsoft’s DirectX, so this project is an attempt to implement his technique in OpenGL, which has free open-source implementations.

Your Brain On Video Games: Ted Talk Annotated Resource List, Jordan D. Dobbs

Undergraduate Research Award

No abstract provided.

Project Writeup On Amethyst: A 3d Adventure Game For Tablets, Adam Hintz

Computer Science and Software Engineering

Amethyst is a point-and-click science fiction adventure game for tablets, developed over two quarters to demonstrate applied principles of computer graphics and software engineering discipline. Using a novel interaction system, players can engage in environmental puzzles. Development of Amethyst required non-trivial quality assurance measures and workflow enhancements. The end result is a functional technical demo showcasing a single level, with the ability to rapidly produce more content.

The Use Of Visual-Based Simulated Environments In Teacher Preparation, Sharon Judge, Jonna Bobzien, Ann Maydosz, Sabra Gear, Petros Katsioloudis

Communication Disorders & Special Education Faculty Publications

While virtual technology for training in the simulation field has a long history in medicine, aviation, and the military, the application of similar emerging and innovative technologies in teacher preparation and education has been limited. TLE TeachLive™ (Teaching Learning Environment, Teaching in a Virtual Environment) [TLE] is an inventive mixed-reality environment (the blending of real and synthetic content) where prospective teachers can interact with a group of virtual students. The purpose of the virtual teaching environment of TLE is to strengthen teacher recruitment, preparation, and retention in education by allowing teachers to improve their skills with virtual students, providing a …

Searching Visual Instances With Topology Checking And Context Modeling, Wei Zhang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Instance Search (INS) is a realistic problem initiated by TRECVID, which is to retrieve all occurrences of the querying object, location, or person from a large video collection. It is a fundamental problem with many applications, and also a challenging problem different from the traditional concept or near-duplicate (ND) search, since the relevancy is defined at instance level. True responses could exhibit various visual variations, such as being small on the image with different background, or showing a non-homography spatial configuration. Based on the Bag-of-Words model, we propose two techniques tailored for Instance Search. Specifically, we explore the use of …

Circular Reranking For Visual Search, Ting Yao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Search reranking is regarded as a common way to boost retrieval precision. The problem nevertheless is not trivial especially when there are multiple features or modalities to be considered for search, which often happens in image and video retrieval. This paper proposes a new reranking algorithm, named circular reranking, that reinforces the mutual exchange of information across multiple modalities for improving search performance, following the philosophy that strong performing modality could learn from weaker ones, while weak modality does benefit from interacting with stronger ones. Technically, circular reranking conducts multiple runs of random walks through exchanging the ranking scores among …

An Investigation And Analysis Of The Vestibulo-Ocular Reflex In A Vibration Environment, Daniel J. Uribe

Theses and Dissertations

Forty years of innovations have greatly improved Helmet-Mounted Displays (HMDs) and their integration into military systems. However, a significant issue with HMDs is the effect of vibration and the associated Vestibulo-Ocular Reflex (VOR). When a human’s head is subject to low-frequency vibration, the VOR stabilizes the eye with respect to objects in the external environment. However, this response is inappropriate in HMDs as the display moves with the user’s head and the VOR blurs the image as it is projected on the human retina. Current compensation techniques suggest increasing the size of displayed graphics or text to compensate for the …