Advertisement

Probabilistic Model Based Image Retrieval Using Hypothesis Testing

Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 154)

Abstract

This paper proposes a new approach for content based image retrieval (CBIR). This approach introduces the hypothesis testing into CBIR. The problem of image retrieval is first restated as the process of image verification between the query image and the images in the database after which the candidate images return. This verification process is then translated as a hypothesis testing problem where the query image claims it is a member of the image class where the reprehensive image in the database belongs to. The images accepted by the hypothesis serve as the candidate images and rank according to the value the test ratio takes. The paper intensively studies the problem of constructing background model, image model and scoring by test ratio. The experimental results show satisfying results of the novel approach.

Keywords

Feature Vector Gaussian Mixture Model Image Retrieval Query Image Image Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arnold W.M. Smeulders, Marcel Worring, Simone Santini, Amarnath Gupta, Ramesh Jain, Content-Based Image Retrieval at the End of the Early Years, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1349–1380, Dec. 2000.Google Scholar
  2. 2.
    M. Flickner, et.al. Query By Image and Video Content: The QBIC System, Computer, 1995, 28(9): 23–31Google Scholar
  3. 3.
    Dempster. N. Laird, and, D. Rubin, maximum likelihood from incomplete data via the EM algorithm, J. Royal stat. soc, vol.39, pp: 1–38, 1977.Google Scholar
  4. 4.
    Jeff. A. Bilmes, A Gentle Tutorial of the EM Algorithm and Its Application to Parameter Estimation for Gauss, Technical Report, U.C. Berkeley, TR-97-021, 1998.Google Scholar
  5. 5.
    Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains Gauvain, J.-L.; Chin-Hui Lee Speech and Audio Processing, IEEE Transactions on Volume 2, Issue 2, Apr 1994, pp: 291–298Google Scholar
  6. 6.
    Reynolds, Douglas A., Quatieri, Thomas F., and Dunn, Robert B., Speaker Verification Using Adapted Gaussian Mixture Models, Digital Signal Processing, 10 (2000), 19–41.Google Scholar
  7. 7.
    K. Jain and A. Vailaya, Image Retrieval Using Color and Shape, Pattern Recognition, Vol. 29, pp. 1233–1244, 1996.Google Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  1. 1.School of AutomationBeijing Institute of TechnologyBeijingChina

Personalised recommendations