Total views : 125

Content based Image Retrieval using Global Correlation Vector and Zernike Moments

Affiliations

  • Department of Electronics and Communication Engineering, GMR Institute of Technology, Rajam – 532127,Andhra Pradesh, India

Abstract


Content Based Image Retrieval (CBIR) using color and shape features is discussed in this paper. Global Correlation Vector (GCV) is used for extracting color features and shape features are extracted by using Zernike Moments. The GCV is a combination of Color Histogram and Structure Element Correlation (SEC), by which it overcomes the problems that are encountered from either Color Histogram or SEC methods. Due to rotation invariance and fast computation Zernike Moments are suitable for image retrieval. The performance of our method is evaluated on Corel Gallery Magic database using the metrics such as Precision and Recall. The simulation results show that the performance of this method is superior to other existing methods.

Keywords

Corel Gallery, Global Correlation Vector (GCV), HSV Color Space, Precision and Recall, Structure Element Correlation (SEC), Zernike Moments.

Full Text:

 |  (PDF views: 158)

References


  • Rui Y, Huang TS, Chang SF. Image retrieval: Current techniques, promising directions, and open issues. J Vis Commun Image Represent. 1999; 10(1):9–62.
  • Datta R, Li J, Wang JZ. Content-based image retrieval: Approaches and trends of the new age. Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval, ACM; 2005. p. 253–62.
  • Penatti OAB, Silva FB, Valle E, et al. Visual word spatial arrangement for image retrieval and classification. Pattern Recogn. 2014; 47(2):705–20.
  • El Alami ME. A new matching strategy for content based image retrieval system. Appl Soft Comput. 2014; 14:407–18.
  • Swain MJ, Ballard DH. Color indexing. Int J Comput Vis.1991; 7(1):11–32.
  • Ojala T, Pietikainen M, Maenpaa T. Multiresolution grayscale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002; 24(7):971–87.
  • Dalal N, Triggs B. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2008; 2005. p. 886–93.
  • Huang J, Kumar SR, Mitra M, et al. Image indexing using color correlograms. Proceedings, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 1997. p. 762–8.
  • Hu MK. Visual pattern recognition by moment invariants.IRE Transactions on information Theory. 1962; 8(2):179– 87.
  • Teague MR. Image theory via general theory of moments. J Opt Soc Am. 1980; 70(80):920–30.
  • Singha M, Hemachandran K. Performance analysis of color spaces in image retrieval. Assam Univ J. 2011; 7(2).
  • Liu GH, Li ZY, Zhang L, et al. Image retrieval based on microstructure descriptor. Pattern Recogn. 2011; 44(9):2123– 33.
  • Wang X, Wang Z. The method for image retrieval based on multi-factors correlation utilizing block truncation coding.Pattern Recogn. 2014; 47(10):3293–303.
  • Liao SX, Pawlak M. On the accuracy of Zernike moments for image analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1999 Jan; 20(12):1358–64.
  • Mukudan R, Ong SH, Lee PA. Image analysis by tchebichef moments. IEEE Transactions on Image Processing. 2001; 10(9):1357–64.
  • Liao SX, Pawlak M. On the accuracy of Zernike moments for image analysis.
  • Feng L, Wu J, Liu S, Zhang H. Global correlation descriptor: A novel image representation for image retrieval. J Vis Commun. Image Represent. 2015; 33:104–14.
  • Chaudhari R, Patil AM. Content based image retrieval using color and shape features. 2012; 1(5):386–92.
  • Soman S. Content based image retrieval using advanced color and texture features. International Conference in Computational Intelligence; 2012. p. 1–5.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.