Abstract

Searching a digital image library, having large number of digital images or video sequences turned to be more and more important in this multimedia age. As time passes, a growing number of people are using the Internet for searching and browsing through different multimedia databases. To make such searching practical, effective image coding and searching based on image semantics is becoming increasingly important. In current real-world image databases, the prevalent retrieval techniques involve human-supplied text annotations to describe image semantics. These text annotations are then used as the basis for searching, using mature text search algorithms that are available as feeware. The most important part of the problem is to construct minimal meta-data that both preserves the image content and yet is efficient for searching. Once the feature meta-data are generated, they are then stored in permanent storage. To answer a query, the image search engine scans through the previously indexed image database looking for the best match. In today's dynamic Internet world, images are added every second, and updated very frequently. In order to match that pace, image matching, and query algorithms must be able to do the job through dynamic image content rather than pre-indexed content. This work aims to apply, enhance and improve perception-based image understanding techniques that are used to do a detailed image match. Perception based image understanding will enable the software to categorize those images based on the image perceptual characteristics as JND (Just Noticeable difference) and INS (Just Not the same), and simple spatial relationships. The enhancements are applied over the Color Histogram image matching, and include color space conversion, image blocking, and dithering.

School

School of Sciences and Engineering

Date of Award

6-1-2002

Online Submission Date

1-1-2002

First Advisor

Ahmed Rafea

Committee Member 1

Gamal Darwish

Committee Member 2

Amr El Kadi

Committee Member 3

Amr Goneid

Document Type

Thesis

Extent

87 leaves :

Library of Congress Subject Heading 1

Image processing

Library of Congress Subject Heading 2

Image processing

Rights

The author retains all rights with regard to copyright. The author certifies that written permission from the owner(s) of third-party copyrighted matter included in the thesis, dissertation, paper, or record of study has been obtained. The author further certifies that IRB approval has been obtained for this thesis, or that IRB approval is not necessary for this thesis. Insofar as this thesis, dissertation, paper, or record of study is an educational record as defined in the Family Educational Rights and Privacy Act (FERPA) (20 USC 1232g), the author has granted consent to disclosure of it to anyone who requests a copy.

Call Number

Thesis 2002/34

Location

mmbk

Download

Included in

Engineering Commons

Share

COinS