An Effective Solution for Trademark Retrieval by Combining Pseudo Zernike Moments and SIFT Features

Abstract:

This paper proposes a trademark retrieval algorithm combining the image global features and local features. Firstly, extract pseudo Zernike moments of the retrieved image and sort them according to similarity. Candidate images are formed. Then, the SIFT features are used for matching the query image accurately with candidate images. Experimental results show that this method not only keeps high precision- recall of SIFT features and is superior than the method based on the single pseudo Zernike moments feature, but also improves effective retrieval speed compared to the single SIFT features. This method can be well applied to the trademark image retrieval system.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 777-780
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.777
• Online since: February 2012
• Authors: Zhen Hai Wang
• Keywords: Content Based Image Retrieval(CBIR), Pseudo Zernike Moments(PZM), Scale Invariant Feature Transform (SIFT), Trademark

References

[1] H. Qi, et al.:Pattern Recognition 43 (2010) 2017–2027.

[2] M.H. Hung, C.H. Hsieh, C.-M. Kuo: J. Visual Commun. Image Representation 17 (5) (2006) 970–985.

[3] D.-F. Shen, J. Li, H.T. Chang, H.H.P. Wu: Proceedings of IEEE International Conference on Image Processing 2005, vol. III, 2005, p.177–180.

[4] Q. Li, J. Edwards, in: The Fourth International Conference on Computer and Information Technology, 2004, p.722–729.

[5] A.K. Jain, A. Vailaya:Pattern Recognition 31 (5) (1998) 1369–1390.

[6] W.-Y. Kim, Y.-S. Kim:Signal Process. Image Commun. 16 (1–2) (2000) 95–102.

[7] C.H. Wei, et al.:Pattern Recognition 42 (2008) 386–394.

[8] D. G. Lowe. : International Journal of Computer Vision 60(2) (2004) 91-110.

[9] Ying-Han Pang, et al.:IEICE Electronics Express, 2(3) (2005) 70-75.