Trademarks recognition based on local regions similarities

Ahmed Zeggari, Fella Hachouf, Sebti Foufou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper deals with content based image retrieval. We propose a logo recognition algorithm based on local regions, where the trademark (or logo) image is segmented by the clustering of points of interest obtained by Harris corners detector. The minimum rectangle surrounding each cluster is detected forming the regions of interest. Global features such as Hu moments and histograms of each local region are combined to find similar logos in the database. Similarity is measured based on the integrated minimum average distance of the individual components. The results obtained demonstrate tolerance to logos distortions such as rotation, occlusion and noise.

Original languageEnglish (US)
Title of host publication10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
Pages37-40
Number of pages4
DOIs
StatePublished - Dec 23 2010
Event10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010 - Kuala Lumpur, Malaysia
Duration: May 10 2010May 13 2010

Other

Other10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
CountryMalaysia
CityKuala Lumpur
Period5/10/105/13/10

Fingerprint

Trademarks
Image retrieval
Detectors

Keywords

  • Clustering
  • Image color analysis
  • Image segmentation
  • Information retrieval
  • Moments
  • Pattern recognition

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Signal Processing

Cite this

Zeggari, A., Hachouf, F., & Foufou, S. (2010). Trademarks recognition based on local regions similarities. In 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010 (pp. 37-40). [5605559] https://doi.org/10.1109/ISSPA.2010.5605559

Trademarks recognition based on local regions similarities. / Zeggari, Ahmed; Hachouf, Fella; Foufou, Sebti.

10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010. 2010. p. 37-40 5605559.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zeggari, A, Hachouf, F & Foufou, S 2010, Trademarks recognition based on local regions similarities. in 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010., 5605559, pp. 37-40, 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010, Kuala Lumpur, Malaysia, 5/10/10. https://doi.org/10.1109/ISSPA.2010.5605559
Zeggari A, Hachouf F, Foufou S. Trademarks recognition based on local regions similarities. In 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010. 2010. p. 37-40. 5605559 https://doi.org/10.1109/ISSPA.2010.5605559
Zeggari, Ahmed ; Hachouf, Fella ; Foufou, Sebti. / Trademarks recognition based on local regions similarities. 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010. 2010. pp. 37-40
@inproceedings{4af7a5f450de49c0ac933353f19ce6f2,
title = "Trademarks recognition based on local regions similarities",
abstract = "This paper deals with content based image retrieval. We propose a logo recognition algorithm based on local regions, where the trademark (or logo) image is segmented by the clustering of points of interest obtained by Harris corners detector. The minimum rectangle surrounding each cluster is detected forming the regions of interest. Global features such as Hu moments and histograms of each local region are combined to find similar logos in the database. Similarity is measured based on the integrated minimum average distance of the individual components. The results obtained demonstrate tolerance to logos distortions such as rotation, occlusion and noise.",
keywords = "Clustering, Image color analysis, Image segmentation, Information retrieval, Moments, Pattern recognition",
author = "Ahmed Zeggari and Fella Hachouf and Sebti Foufou",
year = "2010",
month = "12",
day = "23",
doi = "10.1109/ISSPA.2010.5605559",
language = "English (US)",
isbn = "9781424471676",
pages = "37--40",
booktitle = "10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010",

}

TY - GEN

T1 - Trademarks recognition based on local regions similarities

AU - Zeggari, Ahmed

AU - Hachouf, Fella

AU - Foufou, Sebti

PY - 2010/12/23

Y1 - 2010/12/23

N2 - This paper deals with content based image retrieval. We propose a logo recognition algorithm based on local regions, where the trademark (or logo) image is segmented by the clustering of points of interest obtained by Harris corners detector. The minimum rectangle surrounding each cluster is detected forming the regions of interest. Global features such as Hu moments and histograms of each local region are combined to find similar logos in the database. Similarity is measured based on the integrated minimum average distance of the individual components. The results obtained demonstrate tolerance to logos distortions such as rotation, occlusion and noise.

AB - This paper deals with content based image retrieval. We propose a logo recognition algorithm based on local regions, where the trademark (or logo) image is segmented by the clustering of points of interest obtained by Harris corners detector. The minimum rectangle surrounding each cluster is detected forming the regions of interest. Global features such as Hu moments and histograms of each local region are combined to find similar logos in the database. Similarity is measured based on the integrated minimum average distance of the individual components. The results obtained demonstrate tolerance to logos distortions such as rotation, occlusion and noise.

KW - Clustering

KW - Image color analysis

KW - Image segmentation

KW - Information retrieval

KW - Moments

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=78650295653&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650295653&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2010.5605559

DO - 10.1109/ISSPA.2010.5605559

M3 - Conference contribution

AN - SCOPUS:78650295653

SN - 9781424471676

SP - 37

EP - 40

BT - 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010

ER -