DOI QR코드

DOI QR Code

Content-Based Image Retrieval Based on Relevance Feedback and Reinforcement Learning for Medical Images

  • Lakdashti, Abolfazl (Department of Computer Engineering, University College of Rouzbahan) ;
  • Ajorloo, Hossein (Department of Computer Engineering, Sharif University of Technology)
  • Received : 2010.04.07
  • Accepted : 2010.10.25
  • Published : 2011.04.30

Abstract

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

Keywords

References

  1. R. Greenes and J. Brinkley, "Imaging Systems," Medical Informatics: Computer Applications in Healthcare, 2nd ed., Springer, vol. 21, no. 13-14, 2000, pp. 485-538.
  2. T. Pun, G. Gerig, and O. Ratib, "Image Analysis and Computer Vision in Medicine," Computerized Medical Imaging Graphics, vol. 18, no. 2, 1994, pp. 85-96. https://doi.org/10.1016/0895-6111(94)90017-5
  3. S. Beretti, A. Bimbo, and P. Pala, "Content-Based Retrieval of 3D Cellular Structures," Proc. 2nd Int. Conf. Multimedia Exposition, Tokyo, Japan, 2001, pp. 1096-1099.
  4. S. Orphanoudakis, C. Chronaki, and S. Kostomanolakis, "$I^{2}C$: A System for the Indexing, Storage, and Retrieval of Medical Images by Content," Medical Informatics, vol. 19, no. 2, 1994, pp. 109-122. https://doi.org/10.3109/14639239409001378
  5. P. Aggarwal, H.K. Sardana, and G. Jindal, "Content Based Medical Image Retrieval: Theory, Gaps and Future Directions," ICGST-GVIP J., vol. 9, no. 2, 2009, pp. 27-37.
  6. S. Sedghi, M. Sandersona, and P. Clougha, "A Study on the Relevance Criteria for Medical Images," Pattern Recognition Letters, Elsevier, vol. 29, no. 15, 2008, pp. 2046-2057. https://doi.org/10.1016/j.patrec.2008.07.003
  7. L. Zhang, F. Lin, and B. Zhang, "Support Vector Machine Learning for Image Retrieval," IEEE Int. Conf. Image Process., vol. 2, Oct. 2001, pp. 721-724.
  8. Y. Chen, J. Wang, and R. Krovetz, "An Unsupervised Learning Approach to Content-Based Image Retrieval," 7th Int. Symp. Signal Process. Appl., Paris, vol. 1, July 2003, pp. 197-200.
  9. Y. Chen, X. Zhou, and T. Huang, "One-Class SVM for Learning in Image Retrieval," IEEE Conf. Image Process., vol. 1, Oct. 2001, pp. 34-37.
  10. X. Xua et al., "Using Relevance Feedback with Short-Term Memory for Content-Based Spine X-Ray Image Retrieval," Neurocomputing, Elsevier, vol. 72, no. 10-12, June 2009, pp. 2259-2269. https://doi.org/10.1016/j.neucom.2008.12.029
  11. E. Pekalska and R.P.W. Duin, "Classifiers for Dissimilarity-Based Pattern Recognition," 15th Int. Conf. Pattern Recog., vol. 2, 2000, pp. 12-16.
  12. E. Pekalska and R.P.W. Duin, "Classifiers for Dissimilarity-Based Pattern Recognition," 18th Int. Conf. Pattern Recog., vol. 3, 2006, pp. 137-140.
  13. M. Harandi, M. Ahmadabadi, and B. Araabi, "Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition," Int. J. Computer Vision, Aug. 2008, pp. 191-204.
  14. H. Takagi, "Interactive Evolutionary Computation: Fusion of the Capabilities of EC Optimization and Human Evaluation," Proc. IEEE, vol. 89, no. 9, Sept. 2001, pp. 1275-1296. https://doi.org/10.1109/5.949485
  15. C.-C. Lai and Y.-C. Chen, "Color Image Retrieval Based on Interactive Genetic Algorithm," Lect. Notes Computer Science, Next-Generation Applied Intelligence, Springer, vol. 5579, 2009, pp. 343-349.
  16. S. Rho, E. Hwang, and M.K. Kim, "Music Information Retrieval Using a GA-Based Relevance Feedback," Proc. Int. Conf. Multimedia Ubiquitous Engineering, 2007, pp. 739-744.
  17. Interactive Genetic Algorithm," Congress Image Signal Process., vol. 2, 2008, pp. 500-504.
  18. A. Lakdashti and M.S. Moin, "A New Content-Based Image Retrieval Approach Based on Pattern Orientation Histogram," LNCS, Springer, vol. 4418, 2007, pp. 587-595.
  19. J. R. Jr., Relevance Feedback in Information Retrieval: The SMART System, G. Salton, Ed., Prentice Hall, 1971.
  20. X. He et al., "Learning a Semantic Space from User's Relevance Feedback for Image Retrieval," IEEE Trans. Circuits Syst. Video Technology, vol. 13, no. 1, Jan. 2003, pp. 39-48. https://doi.org/10.1109/TCSVT.2002.808087
  21. F. Jing et al., "Support Vector Machines for Region-Based Image Retrieval," Int. Conf. Multimedia Expo (IEEE Computer Soc.), Baltimore, Maryland, vol. 2, 2003, pp. 21-24.