Combining Features Evaluation Approach in Content-Based Image Search for Medical Applications

Part of the Studies in Computational Intelligence book series (SCI, volume 473)

Abstract

In this paper we propose an approach for a feature combination helping to distinguish searched images from databases by retrieving relevant images. The retrieval effectiveness of 11 well known image features, commonly used in Content Based Image Retrieval (CBIR) systems, is investigated. We suggest a combined features approach including features’ performance comparison of 57 various medical image categories from IRMA Database. The most informative 3 features, adaptive to image categories, are defined. Based on experiments and image similarity accuracy analysis we suggest a set of 3 low level features Color Layout, Edge Histogram and DCT Coefficients. The developed approach achieves better similar images retrieval results for more image classes. The results show an accuracy improvement of 14.49% on Mean Average Precision (MAP). The comparison is done to the same type performance measure of the best individual feature in different medical image categories.

Keywords

CBIR image similarity search feature selection query by example visual features medical images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Veltkamp, R., Tanase, M.: Content-Based Image Retrieval Systems: A Survey. UU–CS 2000–34. Utrecht, The Netherlands: Utrecht University: Information and Computing Sciences (2000)Google Scholar
  2. 2.
    Muller, H., Michoux, N., Bandon, D., Geissbuhler, A.: A Review of Content-Based Image Retrieval Systems in Medical Applications – Clinical Benefits and Future Directions. Int. J. Medical Informatics, 1–23 (2004)Google Scholar
  3. 3.
    Dy, J., Brodley, C., Kak, A., Broderick, L., Aisen, A.: Unsupervised Feature Selection Applied to Content-Based Retrieval of Lung Images. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(3) (2003)Google Scholar
  4. 4.
    Hersh, W., Müller, H., Kalpathy-Cramer, J.: The ImageCLEFmed Medical Image Retrieval Task Test Collection. Proceedings of J. Digital Imaging, 648–655 (2009)Google Scholar
  5. 5.
    Coelho, F., Ribeiro, C.: Evaluation of Global Descriptors for Multimedia Retrieval in Medical Applications. In: Database and Expert Systems Applications (DEXA) Workshop, pp. 127–131 (2010)Google Scholar
  6. 6.
    Shyu, C., Pavlopoulou, C., Kak, A., Brodley, C., Broderick, L.: Using Human Perceptual Categories for Content – Based Retrieval from a Medical Image Database. Computer Vision and Image Understanding 88, 119–151 (2002)MATHCrossRefGoogle Scholar
  7. 7.
    Petrakis, E., Faloutsos, C.: Similarity searching in medical image databases. IEEE Trans. Knowledge and Data Engineering 9(3), 435–447 (1997)CrossRefGoogle Scholar
  8. 8.
    Lux, M., Chatzichristofis, S.: LIRe: Lucene Image Retrieval – An Extensible Java CBIR Library. In: Proceedings of the 16th ACM International Conference on Multimedia, Vancouver, Canada, pp. 1085–1088 (2008)Google Scholar
  9. 9.
    Swain, M.J., Ballard, D.H.: Color Indexing. International Journal of Computer Vision 7(1), 11–32 (1991)CrossRefGoogle Scholar
  10. 10.
    Chang, S.F., Sikora, T., Puri, A.: Overview of the MPEG–7 Standard. IEEE Transactions on Circuits and Systems for Video Technology 11(6), 688–695 (2001)CrossRefGoogle Scholar
  11. 11.
    Deselaers, T., Keysers, D., Ney, H.: Features for Image Retrieval: An Experimental Comparison. Information Retrieval 11(2), 77–107 (2008)CrossRefGoogle Scholar
  12. 12.
    Müller, H., Müller, W., Squire, D.M., Marchand-Maillet, S., Pun, T.: Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals. Pattern Recognition Letters (Special Issue on Image and Video Indexing) 22(5), 593–601 (2001)MATHCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  1. 1.Department of Radio Communications and Video TechnologiesTechnical University of SofiaSofiaBulgaria

Personalised recommendations