CFP last date
21 October 2024
Reseach Article

Automated Color Logo Recognition System based on Shape and Color Features

by Souvik Ghosh, Ranjan Parekh
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 118 - Number 12
Year of Publication: 2015
Authors: Souvik Ghosh, Ranjan Parekh
10.5120/20796-3457

Souvik Ghosh, Ranjan Parekh . Automated Color Logo Recognition System based on Shape and Color Features. International Journal of Computer Applications. 118, 12 ( May 2015), 13-20. DOI=10.5120/20796-3457

@article{ 10.5120/20796-3457,
author = { Souvik Ghosh, Ranjan Parekh },
title = { Automated Color Logo Recognition System based on Shape and Color Features },
journal = { International Journal of Computer Applications },
issue_date = { May 2015 },
volume = { 118 },
number = { 12 },
month = { May },
year = { 2015 },
issn = { 0975-8887 },
pages = { 13-20 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume118/number12/20796-3457/ },
doi = { 10.5120/20796-3457 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T23:01:29.606079+05:30
%A Souvik Ghosh
%A Ranjan Parekh
%T Automated Color Logo Recognition System based on Shape and Color Features
%J International Journal of Computer Applications
%@ 0975-8887
%V 118
%N 12
%P 13-20
%D 2015
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper proposes an automated system for rotation and scale invariant color logo recognition. Colored logo images are recognized using one shape feature namely Moments Invariant and a color feature namely Color Moments. Shape of the logo is modeled using the first two central normalized Hu's invariant moments while color is modeled using the mean, standard deviation, skewness and kurtosis calculated from the color channels. Each image is scaled and rotated by arbitrary amounts before being submitted to the recognition engine. Classification is done using Manhattan and Euclidean distances. Experimental verification is obtained using a data set of 900 images divided into 75 classes. The proposed approach is highly scalable and robust providing accuracy results comparable to the state of the art.

References
  1. Soffer, A. and Samet, H. 1998. Using negative shape features for logo similarity matching. In Proceedings of IEEE Fourteenth International Conference on Pattern Recognition, pp. 571-573.
  2. Mikolajczyk, K. and Schimd, C. 2005. A Performance Evaluation of Local Descriptors. In Proceedings of the IEEE International Conference on Pattern Analysis and Machine Intelligence, pp. 1615-1630.
  3. Xia, L. , Qi, F. and Zhou, Q. 2008. A Learning-based Logo Recognition Algorithm Using SIFT and Efficient Correspondence Matching. In Proceedings of the IEEE International Conference on Information and Automation (ICIA), pp. 1767-1772.
  4. Li, H. and Zheng, Y. 2009. A Research on Logo Recognition in the E-business. In Proceedings of the IEEE International Conference on International Computation & Technology (ICICTA), pp. 281-285.
  5. Arafat, S. and Saleem, M. 2009. Comparative Analysis of Invariant Schemes for Logo Classification. In Proceedings of the IEEE International Conference on Emerging Technologies (ICET), pp. 256-261.
  6. Zhu, G. and Doermann, D. 2009. Logo Matching for Document Image Retrieval. In Proceedings ofTenth International Conference on Document Analysis and Recognition, pp. 606-610.
  7. Wahdan, O. , Omar, K. and Nasrudin, M. 2011. Logo Recognition System Using Angular Radial Transform Descriptors. Journal of Computer Science, pp. 1416-1422.
  8. Zhang, Z. , Wang, X. , Anwar, W. and Jiang, Z. 2014. A Comparison of Moments-Based Logo Recognition Methods. Hindawi Publishing Corporation.
  9. Hu, M-K. 1962. Visual pattern recognition by moment invariants. In Proceedings of IRE Transactions on Information Theory, pp. 179-187.
Index Terms

Computer Science
Information Sciences

Keywords

Logo Recognition Moments Invariant Color Moments Rotation and Scale Invariance.