Article View: csd.grad
Article #107The Dissertation Defense for Xu Liu
From: Fatima Bangura
Date: Wed, 05 Nov 2008 15:15
Date: Wed, 05 Nov 2008 15:15
48 lines
4943 bytes
4943 bytes
THE DISSERTATION DEFENSE FOR THE DEGREE OF Ph.D. IN COMPUTER SCIENCE FOR
Xu Liu
Will be held:
DATE: Friday November 21, 2008 at 2:00 p.m.
LOCATION: Room 3258 A.V. Williams Building
TITLE: Computer Vision and Image Processing Techniques for
Mobile Applications
ABSTRACT: Camera phones have penetrated to every corner of society, and
have become a focal point for communications. In our research we extend the
traditional use of such devices to help to bridge the gap between physical
and digital world. Their combined image acquisition, processing, storage and
communication capabilities in a compact, portable device make them an ideal
platform for embedding computer vision and image processing capabilities in
the pursuit of new mobile applications. This dissertation is presented as a
series of computer vision and image processing techniques together with
their applications on the mobile device. We have developed a set of
techniques for ego-motion estimation, enhancement, feature extraction,
perspective correction, object detection, and document retrieval that serve
as a basis for such applications. Our applications include a dynamic video
barcode that can transfer significant amounts of information visually, a
document retrieval system that can retrieve documents from low resolution
snapshots, and a series of applications for the visually impaired such as a
currency reader. Solutions for mobile devices require a fundamentally
different approach than traditional vision techniques that run on
traditional computers, so we consider user-device interaction and the fact
that these algorithms must execute in a resource constrained environment.
For each problem we perform both theoretical and empirical analysis in an
attempt to optimize performance and usability. The thesis makes
contributions related to efficient implementation of image processing and
computer vision techniques, analysis of information theory, feature
extraction and analysis for low quality images, and device usability.
Examining Committee:
COMMITTEE CHAIR: Dr. Larry Davis
Dean's Representative: Dr. Min Wu
Committee Member(s): Dr. David Doermann
Dr. Ben Bederson
Dr. Ashok Agrawala
EVERYONE IS INVITED TO ATTEND THE PRESENTATION PORTION OF THIS DEFENSE
Technical Details
Message-ID:
<mailman.37.1225898525.3898.gradlist@mcfeely.cs.umd.edu>Path:
arc1-ca.pugleaf.net!g2news2.google.com!news4.google.com!goblin2!goblin1!goblin.stu.neva.ru!uio.no!elk.ncren.net!dailyplanet.umd.edu!not-for-mailShow Full Headers
Complete Article Headers
X-Google-Thread: 10f4d5,426a4301ed6891e,start X-Google-Attributes: gid10f4d5,domainid0,public,usenet X-Google-Language: ENGLISH,ASCII-7-bit Path: arc1-ca.pugleaf.net!g2news2.google.com!news4.google.com!goblin2!goblin1!goblin.stu.neva.ru!uio.no!elk.ncren.net!dailyplanet.umd.edu!not-for-mail From: "Fatima Bangura" <fatima@cs.umd.edu> Newsgroups: csd.grad Subject: The Dissertation Defense for Xu Liu Date: Wed, 5 Nov 2008 10:15:57 -0500 Organization: University of Maryland College Park Lines: 49 Sender: dept-bounces@cs.umd.edu Message-ID: <mailman.37.1225898525.3898.gradlist@mcfeely.cs.umd.edu> NNTP-Posting-Host: mcfeely.cs.umd.edu Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Trace: dailyplanet.umd.edu 1225898526 4628 128.8.128.218 (5 Nov 2008 15:22:06 GMT) X-Complaints-To: abuse@umd.edu NNTP-Posting-Date: Wed, 5 Nov 2008 15:22:06 +0000 (UTC) To: <dept@cs.umd.edu> X-CSD-MailScanner-Watermark: 1226502970.39987@XRRAhNdQGGG4hlGwDP/ZJA X-CSD-MailScanner-Watermark: 1226502968.32716@fJevo814cv8hNyevtZ5q0Q X-CSD-MailScanner-Watermark: 1226502957.38253@ULqO4BiU8/j9UFqMnjgonw X-Mailer: Microsoft Office Outlook 11 thread-index: Ack/WWcYqN297Up7SqOMJ+P/hVU3Zg== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.3350 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.0 (bacon.cs.umd.edu [172.24.3.34]); Wed, 05 Nov 2008 10:15:56 -0500 (EST) X-CSD-MailScanner-Information: Please email staff@cs.umd.edu for more information X-MailScanner-ID: mA5FFuDA022638 X-CSD-MailScanner: Found to be clean X-CSD-MailScanner-SpamCheck: not spam, SpamAssassin (not cached, score=0, required 5, autolearn=not spam) X-CSD-MailScanner-From: fatima@cs.umd.edu X-Spam-Status: No X-BeenThere: dept@mcfeely.cs.umd.edu X-Mailman-Version: 2.1.9 Precedence: list Errors-To: dept-bounces@cs.umd.edu X-Mailman-Approved-At: Wed, 05 Nov 2008 10:22:04 -0500 X-BeenThere: gradlist@mcfeely.cs.umd.edu List-Id: CS Graduate Students <gradlist.mcfeely.cs.umd.edu> List-Unsubscribe: <https://mailman.cs.umd.edu/mailman/listinfo/gradlist>, <mailto:gradlist-request@mcfeely.cs.umd.edu?subject=unsubscribe> List-Archive: <https://mailman.cs.umd.edu/mailman/private/gradlist> List-Post: <mailto:gradlist@mcfeely.cs.umd.edu> List-Help: <mailto:gradlist-request@mcfeely.cs.umd.edu?subject=help> List-Subscribe: <https://mailman.cs.umd.edu/mailman/listinfo/gradlist>, <mailto:gradlist-request@mcfeely.cs.umd.edu?subject=subscribe>