A Multiresolution Approach for Content-Based Image Retrieval Using Wavelet Transform of Local Binary Pattern
The emergence of low cost digital cameras and other image capturing devices has created a huge amount of different types of images. Accessing images easily requires proper arrangement and indexing of images. This has made image retrieval an important problem of Computer Vision. This paper attempts to decompose a Local Binary Pattern (LBP) image at multiple resolution to extract structural arrangement of pixels more efficiently than processing a single scale of the LBP image. LBP descriptors of the 2-D gray scale image are computed followed by computation of Discrete Wavelet Transform (DWT) coefficients of the resulting 2-D LBP image. Finally, construction of feature vector is done through Gray-Level Co-occurrence Matrix. Performance of the proposed method is tested on two benchmark datasets, Corel-1K and Corel-5K, and measured in terms of Precision and Recall. The experimental results demonstrate that the proposed method outperforms some of the other state-of-the-art methods, which proves the effectiveness of the proposed method.
KeywordsContent-Based Image Retrieval Local Binary Pattern Discrete Wavelet Transform Gray-Level Co-occurrence Matrix Multiresolution LBP
This work was supported by the Brain Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2016M3C7A1905477), and the Basic Science Research Program through the NRF funded by the Ministry of Education (NRF-2017R1D1A1B03036423).
- 1.Dutta, R., Joshi, D., Li, J., Wang, J.Z.: Image retrieval: ideas, influences, and trends of the new age. ACM Comput. Surv. 40(2), 5:1–5:60 (2008)Google Scholar
- 6.Srivastava, P., Prakash, O., Khare, A.: Content-based image retrieval using moments of wavelet transform. In: International Conference on Control Automation and Information Sciences, Gwangju, South Korea, pp. 159–164 (2014)Google Scholar
- 14.Xia, Yu., Wan, S., Jin, P., Yue, L.: Multi-scale local spatial binary patterns for content-based image retrieval. In: Yoshida, T., Kou, G., Skowron, A., Cao, J., Hacid, H., Zhong, N. (eds.) AMT 2013. LNCS, vol. 8210, pp. 423–432. Springer, Cham (2013). https://doi.org/10.1007/978-3-319-02750-0_45 CrossRefGoogle Scholar
- 16.Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Prentice Hall Press, Englewood Cliffs (2002)Google Scholar
- 18.http://wang.ist.psu.edu/docs/related/. Accessed Oct 2017
- 19.http://www.ci.gxnu.edu.cn/cbir/. Accessed Oct 2017