Content-based object movie retrieval and relevance feedbacks

Cheng Chieh Chiang, Li Wei Chan, Yi Ping Hung, Greg C. Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Object movie refers to a set of images captured from different perspectives around a 3D object. Object movie provides a good representation of a physical object because it can provide 3D interactive viewing effect, but does not require 3D model reconstruction. In this paper, we propose an efficient approach for content-based object movie retrieval. In order to retrieve the desired object movie from the database, we first map an object movie into the sampling of a manifold in the feature space. Two different layers of feature descriptors, dense and condensed, are designed to sample the manifold for representing object movies. Based on these descriptors, we define the dissimilarity measure between the query and the target in the object movie database. The query we considered can be either an entire object movie or simply a subset of views. We further design a relevance feedback approach to improving retrieved results. Finally, some experimental results are presented to show the efficacy of our approach.

Original languageEnglish
Article number89691
JournalEurasip Journal on Advances in Signal Processing
Volume2007
DOIs
Publication statusPublished - 2007 Aug 1

Fingerprint

Sampling
Feedback
Object-oriented databases

ASJC Scopus subject areas

  • Signal Processing
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Content-based object movie retrieval and relevance feedbacks. / Chiang, Cheng Chieh; Chan, Li Wei; Hung, Yi Ping; Lee, Greg C.

In: Eurasip Journal on Advances in Signal Processing, Vol. 2007, 89691, 01.08.2007.

Research output: Contribution to journalArticle

@article{8e6035b4e4c84abe90bd1c6ed4a2cc62,
title = "Content-based object movie retrieval and relevance feedbacks",
abstract = "Object movie refers to a set of images captured from different perspectives around a 3D object. Object movie provides a good representation of a physical object because it can provide 3D interactive viewing effect, but does not require 3D model reconstruction. In this paper, we propose an efficient approach for content-based object movie retrieval. In order to retrieve the desired object movie from the database, we first map an object movie into the sampling of a manifold in the feature space. Two different layers of feature descriptors, dense and condensed, are designed to sample the manifold for representing object movies. Based on these descriptors, we define the dissimilarity measure between the query and the target in the object movie database. The query we considered can be either an entire object movie or simply a subset of views. We further design a relevance feedback approach to improving retrieved results. Finally, some experimental results are presented to show the efficacy of our approach.",
author = "Chiang, {Cheng Chieh} and Chan, {Li Wei} and Hung, {Yi Ping} and Lee, {Greg C.}",
year = "2007",
month = "8",
day = "1",
doi = "10.1155/2007/89691",
language = "English",
volume = "2007",
journal = "Eurasip Journal on Advances in Signal Processing",
issn = "1687-6172",
publisher = "Springer Publishing Company",

}

TY - JOUR

T1 - Content-based object movie retrieval and relevance feedbacks

AU - Chiang, Cheng Chieh

AU - Chan, Li Wei

AU - Hung, Yi Ping

AU - Lee, Greg C.

PY - 2007/8/1

Y1 - 2007/8/1

N2 - Object movie refers to a set of images captured from different perspectives around a 3D object. Object movie provides a good representation of a physical object because it can provide 3D interactive viewing effect, but does not require 3D model reconstruction. In this paper, we propose an efficient approach for content-based object movie retrieval. In order to retrieve the desired object movie from the database, we first map an object movie into the sampling of a manifold in the feature space. Two different layers of feature descriptors, dense and condensed, are designed to sample the manifold for representing object movies. Based on these descriptors, we define the dissimilarity measure between the query and the target in the object movie database. The query we considered can be either an entire object movie or simply a subset of views. We further design a relevance feedback approach to improving retrieved results. Finally, some experimental results are presented to show the efficacy of our approach.

AB - Object movie refers to a set of images captured from different perspectives around a 3D object. Object movie provides a good representation of a physical object because it can provide 3D interactive viewing effect, but does not require 3D model reconstruction. In this paper, we propose an efficient approach for content-based object movie retrieval. In order to retrieve the desired object movie from the database, we first map an object movie into the sampling of a manifold in the feature space. Two different layers of feature descriptors, dense and condensed, are designed to sample the manifold for representing object movies. Based on these descriptors, we define the dissimilarity measure between the query and the target in the object movie database. The query we considered can be either an entire object movie or simply a subset of views. We further design a relevance feedback approach to improving retrieved results. Finally, some experimental results are presented to show the efficacy of our approach.

UR - http://www.scopus.com/inward/record.url?scp=34547174266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547174266&partnerID=8YFLogxK

U2 - 10.1155/2007/89691

DO - 10.1155/2007/89691

M3 - Article

AN - SCOPUS:34547174266

VL - 2007

JO - Eurasip Journal on Advances in Signal Processing

JF - Eurasip Journal on Advances in Signal Processing

SN - 1687-6172

M1 - 89691

ER -