Advertisement

Data Fusion Approach to MR Image Recognition Through Tissue Characterization

  • S. Dellepiane
  • C. S. Regazzoni
  • S. B. Serpico
  • C. Vernazza
Part of the International Centre for Mechanical Sciences book series (CISM, volume 307)

Abstract

Abstract Image understanding systems usually attain their goals by processing and recognizing data provided by only one sensor, or by separately utilizing predefined operation modes of a single sensor. This paper deals with the problem of integrating information provided by different sources into a common recognition framework, in order to improve the overall reliability of the system.

A final organ map has been obtained through this information merging process, weighting the fuzzy membership values assigned to each region of a recognized organ with the different degrees of reliability of the sensor. Preliminary recognition results, more accurate than those yielded by than from a single channel recognition system, are presented and discussed.

Keywords

Recognition Process Fuzzy Membership Recognition Result Certainty Factor Left Portion 
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]
    M. Gado, F. III Hodges, K. Sartor, Principles of interpretation of MR images of the brain”,XIV Congress of the European Society of Neuroradiology, CIC Edizioni Internazionali, Udine, September ‘87, pp.43–60Google Scholar
  2. [2]
    Amar Mitiche and J.K. Aggarwa1,”Multiple sensor integration/fusion through image processing: a review”, Optical Engineering 25(3), Journal of the SPIE Society Austin Texas, March ‘86, pp. 380–386Google Scholar
  3. [3]
    G. Capocaccia, A. Damasio, C. Regazzoni, G. Vernazza, “Data Fusion Approach to Obstacle Detection and Identification” SPIE Cambridge Symposium on Optical and Opto-Electronic Engineering, Cambridge (MA), SPIE Vol. 1003, November 1988 (in press).Google Scholar
  4. [4]
    G. Vernazza, S.B. Serpico, S. Dellepiane, “A knowledge-based system for biomedical image processing and .recognition”, IEEE Trans. on Circuit & Systems, Special Issue on Image Processing and application, Nov. 1987, pp. 11399–11416.Google Scholar
  5. [5]
    S.B. Serpico, F. Sturaro, G. Vernazza, S. Dellepiane“Fuzzy reasoning approach to understanding of 2-D NMR images”, IX Conf. IEEE Eng. in Med. & Biol. Soc. Conf., Boston (USA), Nov. 1987, pp. 1980 – 1981.Google Scholar

Copyright information

© Springer-Verlag Wien 1989

Authors and Affiliations

  • S. Dellepiane
    • 1
  • C. S. Regazzoni
    • 1
  • S. B. Serpico
    • 1
  • C. Vernazza
    • 1
  1. 1.Université di GenovaGenovaItaly

Personalised recommendations