ABSTRACT
In this paper, we propose a novel rotation and scale invariant method for colour logo retrieval and classification, which involves performing a simple colour segmentation and subsequently describing each of the resultant colour components based on a set of topological and colour features. A polar representation is used to represent the logo and the subsequent logo matching is based on Cyclic Dynamic Time Warping (CDTW). We also show how combining information about the global distribution of the logo components and their local neighbourhood using the Delaunay triangulation allows to improve the results. All experiments are performed on a dataset of 2500 instances of 100 colour logo images in different rotations and scales.
- Z. Ahmed and H. Fella. Logos extraction on picture documents using shape and colour density. IEEE International Symposium on Industrial Electronics, ISIE, pages 2492--2496, 2008.Google ScholarCross Ref
- F. Cesarini, E. Francesconi, M. Gori, S. Marinai, J. Q. Sheng, and G. Soda. A neural-based architecture for spot-noisy logo recognition. 4th International Conference on Document Analysis and Recognition, pages 175--179, 1997. Google ScholarDigital Library
- J. Chen, M. K. Leung, and Y. Gao. Noisy logo recognition using line segment hausdorff distance. Pattern recognition, pages 943--955, 2003.Google Scholar
- A. Clavelli and D. Karatzas. Text segmentation in colour posters from the spanish civil war era. In Proceedings of the Tenth International Conference on Document Analysis and Recognition, ICDAR09, pages 181--185, 2009. Google ScholarDigital Library
- R. den Hollander and A. Hanjalic. Logo recognition in video stills by string matching. International Conference on Image Processing, ICIP, pages 517--520, 2003.Google ScholarCross Ref
- M. Diligenti, M. Gori, M. Maggini, and E. Martinelli. Adaptive graphical pattern recognition for the classification of company logos. Pattern Recognition, pages 2049--2061, 2001.Google Scholar
- D. Doermann, E. Rivlin, and I. Weiss. Applying algebraic and differential invariants for logo recognition. Machine Vision and Applications, pages 73--86, 1996. Google ScholarDigital Library
- D. Doermann, E. Rivlin, and I. Weiss. Logo recognition using geometric invariants. Proceedings of the Second International Conference on Document Analysis and Recognition, pages 894--897, 2002.Google Scholar
- E. Francesconi, P. Frasconi, M. Gori, S. Marinai, J. Q. Sheng, G. Soda, and A. Sperduti. Logo recognition by recursive neural networks. the Second International Workshop on Graphics Recognition, Algorithms and Systems, pages 104--117, 1998. Google ScholarDigital Library
- A. Gordo and E. Valveny. A rotation invariant page layout descriptor for document classification and retrieval. 10th International Conference on Document Analysis and Recognition, ICDAR09, pages 481--485, 2009. Google ScholarDigital Library
- M. Gori, M. Maggini, S. Marinai, J. Q. Sheng, and G. Soda. Edge back propagation for noisy logo recognition. Pattern Recognition, pages 103--110, 2003.Google Scholar
- A. Hesson and D. Androutsos. Logo and trademark detection in image using wavelet co-occurrence histograms. IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, pages 1233--1236, 2008.Google ScholarCross Ref
- J. Luo and D. Crandall. colour object detection using spatial colour joint probability functions. IEEE Transaction On Image Processing, pages 1443--1453, 2006. Google ScholarDigital Library
- T. D. Pham. Variogram-based feature extraction for neural-network recognition of logos. Applications of Artificial Neural Networks in Image Processing, pages 22--29, 2003.Google ScholarCross Ref
- R. Phan and D. Androutsos. Logo and trademark retrieval in general images database using colour edge gradient co-occurrence histograms. 4th International Conference on Image Analysis and Recognition, ICIAR, pages 674--685, 2007. Google ScholarDigital Library
- R. Phan and D. Androutsos. Content-based retrieval of logo and trademarks in unconstrained color image databases using color edge gradient co-occurrence histograms. Computer Vision and Image Understanding, pages 66--84, 2009. Google ScholarDigital Library
- R. Phan, J. Chia, and D. Androutsos. Colour logo and trademark detection in unconstrained images using colour edge gradient co-occurrence histograms. Canadian Conference on Electrical and Computer Engineering, CCECE, pages 531--534, 2008.Google ScholarCross Ref
- A. Wheeler. Designing Brand Identity. John Wiley and Sons, 2006.Google Scholar
- L. Xia, F. Qi, and Q. Zhou. A learning based logo recognition algorithm using sift and efficient correspondence matching. International Conference on Information and Automation, ICIA, pages 1767--1772, 2008.Google Scholar
- G. Zhu and D. Doermann. Automatic document logo detection. Ninth International Conference on Document Analysis and Recognition, ICDAR, pages 864--868, 2007. Google ScholarDigital Library
- G. Zhu and D. Doermann. Logo matching for document image retrieval. 10th International Conference on Document Analysis and Recognition, ICDAR, pages 606--610, 2009. Google ScholarDigital Library
- K. J. Zyga, S. Division, J. Schroeder, and R. Price. Logo recognition using retinal coding. Conference Record of the Thirty-Eighth Asilomar Conference on Signals Systems and Computers, pages 1549--1553, 2004.Google ScholarCross Ref
Recommendations
Skin color enhancement based on favorite skin color in HSV color space
Skin color enhancement based on favorite skin color is proposed to make skin color displayed on large screen flat panel TVs agree with human favorite skin color. A robust skin detection method in different intensity is obtained after analyzing the ...
Content-based retrieval of logo and trademarks in unconstrained color image databases using Color Edge Gradient Co-occurrence Histograms
In this paper, we present an algorithm that extends the Color Edge Co-occurrence Histogram (CECH) object detection scheme on compound color objects, for the retrieval of logos and trademarks in unconstrained color image databases. We introduce more ...
Color image watermarking based on quaternion Fourier transform and improved uniform log-polar mapping
Graphical abstractDisplay Omitted A robust blind color image watermarking scheme is proposed.An improved uniform log-polar mapping method is used to resist geometric attacks.A dual watermark is embedded into quaternion discrete Fourier transform ...
Comments