Texture search engine

Texture, an important element in computer graphics, is being widely used today to facilitate the visualization of complex concepts and ideas. With the enormous amount of texture images available, there is a need for an efficient way to search for and retrieve relevant texture images. The focus of...

Full description

Saved in:
Bibliographic Details
Main Author: Soh, Eric Wei Lun.
Other Authors: Henry Johan
Format: Final Year Project
Language:English
Published: 2012
Subjects:
Online Access:http://hdl.handle.net/10356/48507
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-48507
record_format dspace
spelling sg-ntu-dr.10356-485072023-03-03T20:48:28Z Texture search engine Soh, Eric Wei Lun. Henry Johan School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Texture, an important element in computer graphics, is being widely used today to facilitate the visualization of complex concepts and ideas. With the enormous amount of texture images available, there is a need for an efficient way to search for and retrieve relevant texture images. The focus of this project is to improve the speed of a prototype texture search engine. The prototype uses sketches instead of text as inputs for queries, inspired by the idea of Content-based Information Retrieval which focuses on the content of images over descriptive text. The main technique used in this report combines shape context with feature tracking in searching for similar patterns. To improve the efficiency of the prototype, a factoring approach was also introduced. The factoring approach managed to improve the search speed while maintaining a relatively high accuracy of 84% for the alphabetical test cases. In addition, a separate template matching method will also be discussed to provide a means for comparison. Bachelor of Engineering (Computer Science) 2012-04-25T04:43:39Z 2012-04-25T04:43:39Z 2012 2012 Final Year Project (FYP) http://hdl.handle.net/10356/48507 en Nanyang Technological University 38 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Soh, Eric Wei Lun.
Texture search engine
description Texture, an important element in computer graphics, is being widely used today to facilitate the visualization of complex concepts and ideas. With the enormous amount of texture images available, there is a need for an efficient way to search for and retrieve relevant texture images. The focus of this project is to improve the speed of a prototype texture search engine. The prototype uses sketches instead of text as inputs for queries, inspired by the idea of Content-based Information Retrieval which focuses on the content of images over descriptive text. The main technique used in this report combines shape context with feature tracking in searching for similar patterns. To improve the efficiency of the prototype, a factoring approach was also introduced. The factoring approach managed to improve the search speed while maintaining a relatively high accuracy of 84% for the alphabetical test cases. In addition, a separate template matching method will also be discussed to provide a means for comparison.
author2 Henry Johan
author_facet Henry Johan
Soh, Eric Wei Lun.
format Final Year Project
author Soh, Eric Wei Lun.
author_sort Soh, Eric Wei Lun.
title Texture search engine
title_short Texture search engine
title_full Texture search engine
title_fullStr Texture search engine
title_full_unstemmed Texture search engine
title_sort texture search engine
publishDate 2012
url http://hdl.handle.net/10356/48507
_version_ 1759853088058900480