Structure features for content-based image retrieval

Gerd Brunner, Hans Burkhardt

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

The geometric structure of an image exhibits fundamental information. Various structure-based feature extraction methods have been developed and successfully applied to image processing problems. In this paper we introduce a geometric structure-based feature generation method, called line-structure recognition (LSR) and apply it to content-based image retrieval. The algorithm is adapted from line segment coherences, which incorporate inter-relational structure knowledge encoded by hierarchical agglomerative clustering, resulting in illumination, scale and rotation robust features. We have conducted comprehensive tests and analyzed the results in detail. The results have been obtained from a subset of 6000 images taken from the Corel image database. Moreover, we compared the performance of LSR with Gabor wavelet features.

Original languageEnglish (US)
Pages (from-to)425-433
Number of pages9
JournalLecture Notes in Computer Science
Volume3663
StatePublished - Nov 4 2005
Event27th DAGM (German Association for Pattern Recognition) Symposium, DAGM 2005 - Vienna, Austria
Duration: Aug 31 2005Sep 2 2005

Fingerprint

Content-based Image Retrieval
Image retrieval
Feature extraction
Image processing
Lighting
Geometric Structure
Gabor Wavelet
Line
Image Database
Hierarchical Clustering
Line segment
Feature Extraction
Illumination
Image Processing
Subset

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

@article{49ba5bd747e44852997679ba737c8a9c,
title = "Structure features for content-based image retrieval",
abstract = "The geometric structure of an image exhibits fundamental information. Various structure-based feature extraction methods have been developed and successfully applied to image processing problems. In this paper we introduce a geometric structure-based feature generation method, called line-structure recognition (LSR) and apply it to content-based image retrieval. The algorithm is adapted from line segment coherences, which incorporate inter-relational structure knowledge encoded by hierarchical agglomerative clustering, resulting in illumination, scale and rotation robust features. We have conducted comprehensive tests and analyzed the results in detail. The results have been obtained from a subset of 6000 images taken from the Corel image database. Moreover, we compared the performance of LSR with Gabor wavelet features.",
author = "Gerd Brunner and Hans Burkhardt",
year = "2005",
month = "11",
day = "4",
language = "English (US)",
volume = "3663",
pages = "425--433",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",

}

Structure features for content-based image retrieval. / Brunner, Gerd; Burkhardt, Hans.

In: Lecture Notes in Computer Science, Vol. 3663, 04.11.2005, p. 425-433.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Structure features for content-based image retrieval

AU - Brunner, Gerd

AU - Burkhardt, Hans

PY - 2005/11/4

Y1 - 2005/11/4

N2 - The geometric structure of an image exhibits fundamental information. Various structure-based feature extraction methods have been developed and successfully applied to image processing problems. In this paper we introduce a geometric structure-based feature generation method, called line-structure recognition (LSR) and apply it to content-based image retrieval. The algorithm is adapted from line segment coherences, which incorporate inter-relational structure knowledge encoded by hierarchical agglomerative clustering, resulting in illumination, scale and rotation robust features. We have conducted comprehensive tests and analyzed the results in detail. The results have been obtained from a subset of 6000 images taken from the Corel image database. Moreover, we compared the performance of LSR with Gabor wavelet features.

AB - The geometric structure of an image exhibits fundamental information. Various structure-based feature extraction methods have been developed and successfully applied to image processing problems. In this paper we introduce a geometric structure-based feature generation method, called line-structure recognition (LSR) and apply it to content-based image retrieval. The algorithm is adapted from line segment coherences, which incorporate inter-relational structure knowledge encoded by hierarchical agglomerative clustering, resulting in illumination, scale and rotation robust features. We have conducted comprehensive tests and analyzed the results in detail. The results have been obtained from a subset of 6000 images taken from the Corel image database. Moreover, we compared the performance of LSR with Gabor wavelet features.

UR - http://www.scopus.com/inward/record.url?scp=27244445946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27244445946&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:27244445946

VL - 3663

SP - 425

EP - 433

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -