A novel CT image dynamic fuzzy retrieval method using curvelet transform

  • Authors:

  • Guangming Zhang;Zhiming Cui;Shengrong Gong

  • Affiliations:

  • The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China;The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China;The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China

  • Venue:
  • HPCA'09 Proceedings of the Second international conference on High Performance Computing and Applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Curvelet transform as time-frequency and multiresolution analysis tool is often used in the domain of image processing, especially for image characteristic extraction. This paper proposes a novel CT image retrieval method which is combining curvelet transform and dynamic fuzzy theory. Firstly, the image was decomposed by curvelet transform to obtain the different subbands coefficients. Then the entropy from certain subband was calculated, and a membership function based on dynamic fuzzy theory was constructed to adjust the weight of coefficients similarity. At last a model was constructed to obtain the similarity degree for CT image retrieval. The precision of our model could be applied to CT image retrieval practically.