Abstract

Automated recognition of objects from images plays an important role in many computer vision systems such as robot navigation, object manipulation and content based image retrieval. In this study, an approach for object recognition based on Dual Tree Complex Wavelet Transform (DTCWT) is proposed. The proposed approach attempts to extract the detailed information of objects from the multi scale representation by DTCWT. The proposed system is tested on Columbia Object Image Library (COIL-100). All the objects are considered for the classification based on nearest neighbor classifier. The results show that the maximum recognition accuracy achieved by the proposed approach is 97.03%.

Keywords:

Dual tree complex wavelet transform, nearest neighbor classifier, object recognition, wavelet transform,

References

1. Amores, J., N. Sebe and P. Radeva, 2007. Context-based object-class recognition and retrieval by generalized correlograms. IEEE T. Pattern Anal., 29(10): 1818-1833.
   CrossRef    PMid:17699925    
2. Belongie, S., J. Malik and J. Puzicha, 2002. Shape matching and object recognition using shape contexts. IEEE T. Pattern Anal., 24(4): 509-522.
   CrossRef    
3. Boshra, M. and B. Bhanu, 2000. Predicting performance of object recognition. IEEE T. Pattern Anal., 22(9): 956-969.
   CrossRef    
4. Choi, M.J., T. Antonio and S.W. Alan, 2012. A tree-based context model for object recognition. IEEE T. Pattern Anal., 34(2): 240-252.
   CrossRef    PMid:21670482    
5. Diplaros, A., T. Gevers and I. Patras, 2006. Combining color and shape information for illumination-viewpoint invariant object recognition. IEEE T. Image Process., 15(1): 1-11.
   CrossRef    PMid:16435532    
6. Gevers, T. and A.W.M. Smeulders, 1999. Color-based object recognition. Pattern Recogn., 32(3): 453-464.
   CrossRef    
7. Han, X.H., Y.W. Chen and X. Ruan, 2012. Multilinear supervised neighborhood embedding of a local descriptor tensor for scene/object recognition. IEEE T. Image Process., 21(3): 1314-1326.
   CrossRef    PMid:21937347    
8. Kim, K., K. Joongbae, K. Sangseung, K. Jaehong and L. Jaeyeon, 2012. Object recognition for cell manufacturing system. Proceedings of the 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp: 512-514.
   CrossRef    
9. Kingsbury, N.G., 1998. The dual-tree complex wavelet transform: A new technique for shift invariance and directional filters. Proceeding of the 8th IEEE DSP Work-shop. Bryce Canyon.
   PMCid:PMC1756055    
10. Linde, O. and T. Lindeberg, 2004. Object recognition using composed receptive field histograms of higher dimensionality. Proceedings of the 17th International Conference on Pattern Recognition, 2: 1-6.
    CrossRef    
11. Naik, S.K. and C.A. Murthy, 2007. Distinct multicolored region descriptors for object recognition. IEEE T. Pattern Anal., 29(7): 1291-1296.
    CrossRef    
12. Nene, S.A., S.K. Nayar and H. Murase, 1996. Columbia object image library (COIL-100). Technical Report CUCS-006-96, February 1996.
    
13. Pham, T.V. and A.W.M. Smeulders, 2006. Sparse representation for coarse and fine object recognition. IEEE T. Pattern Anal., 28(4): 555-567.
    CrossRef    PMid:16566505    
14. Selesnick, I.W., R.G. Baraniuk and N.G. Kingsbury, 2005. The dual-tree complex wavelet transform. IEEE Signal Proc. Mag., 22(6): 123-151.
    CrossRef    
15. Wang, M., W. Yanling, L. Guangda and Z. Xiang-Dong, 2010. Object recognition via adaptive multi-level feature integration. Proceedings of the 12th International Asia-Pacific on Web Conference (APWEB), pp: 253-259.
    CrossRef    
16. Yang, J., T. Yonghong, D. Ling-Yu, H. Tiejun and G. Wen, 2012. Group-sensitive multiple kernel learning for object recognition. IEEE T. Image Process., 21(5): 2838-2852.
    CrossRef    PMid:22249707    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.