A Medical Image Fusion Method Based on Visual Models

  • Qu Jingyi
  • Jia Yunfei
  • Du Ying
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7368)


A new method of medical image fusion is proposed in this paper, which is based on human visual models and IHS color space. Retina-inspired difference of Gaussian model is adopted to enhance the spatial information of anatomical images. Also, 2D Log-Gabor model of primary visual cortex is used to enhance the spectrum information of functional images. The statistical analyses tools such as average gradient and entropy are demonstrated that the proposed algorithm does considerably increase spatial information content and reduce the color distortion compared to the counterpart fusion methods. In the proposed fused images the color information is least distorted, the spatial details are as clear as the original anatomical images, and the integration of color and spatial features was normal.


image fusion visual models IHS color space difference of Gaussian model 2D Log-Gabor model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Calvini, P., Massone, A.M., Nobili, F.M., et al.: Fusion of the MR image to SPECT with possible correction for partial volume effects. IEEE Transactions on Nuclear Science 53(1), 189–197 (2006)CrossRefGoogle Scholar
  2. 2.
    Tu, T.M., Su, S.C., Shyu, H.C., et al.: A new look at IHS-like image fusion methods. Information Fusion 2(3), 177–186 (2001)CrossRefGoogle Scholar
  3. 3.
    Gonzalez, M., Saleta, J.L., Catalan, R.G., et al.: Fusion of multispectral and panchromatic images using improved IHS and PCA mergers based on wavelet decomposition. IEEE Transaction on Geoscience and Remote Sensing 42(6), 1291–1299 (2004)CrossRefGoogle Scholar
  4. 4.
    Pohl, C., Van Genderen, J.L.: Multisensor image fusion in remote sensing: concepts methods and applications. International Journal of Remote Sensing 19(5), 823–854 (1998)CrossRefGoogle Scholar
  5. 5.
    Zhang, H., Liu, L., Lin, N.: A novel wavelet medical image fusion method. In: International Conference on Multimedia and Ubiquitous Engineering, pp. 548–553 (April 2007)Google Scholar
  6. 6.
    Zheng, Y., Essock, E.A., Hansen, B.C., et al.: A new metric based on extended spatial frequency and its application to DWT based fusion algorithms. Information Fusion 8(2), 177–192 (2007)CrossRefGoogle Scholar
  7. 7.
    Tu, T.M., Cheng, W.C., Chang, C.P., et al.: Best tradeoff for high resolution image fusion to preserve spatial details and minimize color distortion. IEEE Geoscience and Remote Sensing Letters 4(2), 302–306 (2007)CrossRefGoogle Scholar
  8. 8.
    Zhao, W., Huang, J.J., Tian, B.: An image fusion algorithm based on receptive field model. Acta Electronica Sinica 36(9), 1665–1669 (2008)Google Scholar
  9. 9.
    Miao, Q.G., Wang, B.S.: A novel image fusion algorithm based on local contrast and adaptive PCNN. Chinese Journal of Computers 31(5), 875–880 (2008)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Ghassemian, H.: A retina based multi-resolution image fusion. In: IGRSS 2001, pp. 709–711 (July 2001)Google Scholar
  11. 11.
    Daneshvar, S., Ghassemian, H.: MRI and PET image fusion by combining IHS and retina-inspired models. Information Fusion 11(2), 114–123 (2010)CrossRefGoogle Scholar
  12. 12.
    Benoit, A., Caplier, A., Durette, B., et al.: Using human visual system modeling for bio-inspired low level image processing. Computer Vision and Image Understanding 114(7), 758–773 (2010)CrossRefGoogle Scholar
  13. 13.
    Fischer, S., Roubek, F., Perrinet, L.: Self-invertible 2D Log-Gabor wavelets. International Journal of Computer Vision 75(2), 231–246 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Qu Jingyi
    • 1
  • Jia Yunfei
    • 1
  • Du Ying
    • 2
  1. 1.Tianjin Key Laboratory for Advanced Signal ProcessingCivil Aviation UniversityTianjinChina
  2. 2.School of ScienceEast China University of Science and TechnologyShanghaiChina

Personalised recommendations