Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Adaptive learning region importance for region-based image retrieval

This study addresses the issue of region representation in region-based image retrieval (RBIR). In order to reduce the user's burden of selecting the region of interest, a statistical index called visual region importance (RI) is constructed to describe the region. By learning from user's current and historical feedback information, visual RI can be automatically updated and semantic RI can be obtained. Furthermore, adaptive learning RI and memory learning RI (MLRI) techniques for RBIR system have been presented. Specifically, the MLRI can mitigate the negative influence of interference regions well. Extensive experiments on the Corel-1000 dataset and the Caltech-256 dataset demonstrate that the proposed frameworks are effective, are robust and achieve significantly better performance than the other existing methods.

References

    1. 1)
      • 4. Zdziarski, Z., Dahyot, R.: ‘Feature selection using visual saliency for content-based image retrieval’. IET Irish Signals and Systems Conf. (ISSC 2012), 2012, p. 46.
    2. 2)
    3. 3)
    4. 4)
      • 10. Ducksbury, P.G., Varga, M.J.: ‘Region based image content descriptors and representation’. Sixth Int. Conf. on Image Processing and its Applications’, IET Computer Vision, 1997, pp. 561565.
    5. 5)
      • 13. Jing, F., Zhang, B., Lin, F.Z., Ma, W.Y., Zhang, H.J.: ‘A novel region-based image retrieval method using relevance feedback’. 2001 ACM Workshop on Multimedia: Multimedia Information Retrieval, Ottawa, Canada, September–October 2001, pp. 2831.
    6. 6)
      • 11. Parashar, A.: ‘Region based image retrieval systems’. National Conf. on Signal and Image Processing Applications’, IET Computer Vision, 2009, p. 55.
    7. 7)
      • 28. Wood, M.E.J., Thomas, B.T., Campbell, N.W.: ‘Iterative refinement by relevance feedback in content based digital image retrieval’ (ACM Multimedia, New York, 1998), pp. 1320.
    8. 8)
    9. 9)
      • 16. Li, J., Wang, J.Z., Wiederhold, G.: ‘IRM: integrated region matching for image retrieval’. Eighth ACM Int. Conf. on Multimedia, Los Angeles, CA, USA, October 2000, 8 (2), pp. 147156.
    10. 10)
    11. 11)
    12. 12)
    13. 13)
      • 3. Lowe, D.: ‘Object recognition from local scale-invariant features’. Proc. of Int. Conf. on Computer Vision, September 1999, pp. 11501157.
    14. 14)
      • 21. Cord, M., Gosselin, P.H.: ‘Image retrieval using long-term semantic learning’. Proc. Int. Conf. Image Processing, 2006, pp. 29092912.
    15. 15)
      • 6. Baeza-Yates, R., Ribeiro-Neto, B.: ‘Modern information retrieval’ (Addison-Wesley, ACM Press, New York, 1999).
    16. 16)
    17. 17)
    18. 18)
    19. 19)
      • 27. Wang, J.Z., Du, Y.P.: ‘Scalable integrated region-based image retrieval using IRM and statistical clustering’. Proc. First ACM/IEEE-CS Joint Conf. Digital Libraries., 2001, pp. 268277.
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
    26. 26)
      • 19. Wang, X.Y., Li, Y.W., Yang, H.Y., Chen, J.W.: ‘An image retrieval scheme with relevance feedback using feature reconstruction and SVM reclassification’, Pattern Recognit. Neuro Comput., 2014, 127, (15), pp. 214230.
    27. 27)
      • 9. Cai, L.J., Yang, X.H., Li, S.C., Li, D.F.: ‘Relevance feedback based on particle swarm optimization for image retrieval’. Proc. of the 2012 Int. Conf. on Infor. Tech. and Software Engineering Lecture Notes in Electrical Engineering, 2013, no. 212, pp. 749756.
    28. 28)
    29. 29)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0119
Loading

Related content

content/journals/10.1049/iet-cvi.2014.0119
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address