Shape retrieval and matching based on line segments.

A novel local structure based image retrieval (ALSBIR) approach is proposed in this thesis to build a general framework for object / image retrieval. It performs speedy interpretation of input images and retrieval of structurally similar models from large database according to the input. It is first...

Full description

Saved in:
Bibliographic Details
Main Author: Chi, Yan Ling.
Other Authors: Leung, Maylor Karhang
Format: Theses and Dissertations
Published: 2008
Subjects:
Online Access:https://hdl.handle.net/10356/2478
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
id sg-ntu-dr.10356-2478
record_format dspace
spelling sg-ntu-dr.10356-24782023-03-04T00:43:41Z Shape retrieval and matching based on line segments. Chi, Yan Ling. Leung, Maylor Karhang School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval A novel local structure based image retrieval (ALSBIR) approach is proposed in this thesis to build a general framework for object / image retrieval. It performs speedy interpretation of input images and retrieval of structurally similar models from large database according to the input. It is first of its kind to experiment with mixed-object query in shape retrieval. The approach consists of a novel local shape representation inspired by Gestalt psychology and a novel hypercube indexing structure driven by dynamic programming. It can tackle partially occluded objects in a cluttered environment since it employs local information only and does not require separation of whole input objects from complex background. It is able to infer retrieval results from incomplete information of an input by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. The proposed concepts have been compared with the 6 nearest-neighbors shape description. They have the similar performance on single object retrieval. However, the proposed method out-performed the 6 nearest-neighbors on the test of occluded and cluttered object queries. The sensitivity analysis and error analysis shows that the system is robust in the occluded and cluttered environments. DOCTOR OF PHILOSOPHY (SCE) 2008-09-17T09:03:55Z 2008-09-17T09:03:55Z 2007 2007 Thesis Chi, Y. L. (2007). Shape retrieval and matching based on line segments. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/2478 10.32657/10356/2478 Nanyang Technological University application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
topic DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval
spellingShingle DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval
Chi, Yan Ling.
Shape retrieval and matching based on line segments.
description A novel local structure based image retrieval (ALSBIR) approach is proposed in this thesis to build a general framework for object / image retrieval. It performs speedy interpretation of input images and retrieval of structurally similar models from large database according to the input. It is first of its kind to experiment with mixed-object query in shape retrieval. The approach consists of a novel local shape representation inspired by Gestalt psychology and a novel hypercube indexing structure driven by dynamic programming. It can tackle partially occluded objects in a cluttered environment since it employs local information only and does not require separation of whole input objects from complex background. It is able to infer retrieval results from incomplete information of an input by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. The proposed concepts have been compared with the 6 nearest-neighbors shape description. They have the similar performance on single object retrieval. However, the proposed method out-performed the 6 nearest-neighbors on the test of occluded and cluttered object queries. The sensitivity analysis and error analysis shows that the system is robust in the occluded and cluttered environments.
author2 Leung, Maylor Karhang
author_facet Leung, Maylor Karhang
Chi, Yan Ling.
format Theses and Dissertations
author Chi, Yan Ling.
author_sort Chi, Yan Ling.
title Shape retrieval and matching based on line segments.
title_short Shape retrieval and matching based on line segments.
title_full Shape retrieval and matching based on line segments.
title_fullStr Shape retrieval and matching based on line segments.
title_full_unstemmed Shape retrieval and matching based on line segments.
title_sort shape retrieval and matching based on line segments.
publishDate 2008
url https://hdl.handle.net/10356/2478
_version_ 1759856916080623616