Cluster

Project summary:

In this paper, we propose a novel feature, named histogram of compressed scattering coefficients (HCSCs), for medical image retrieval. Given a medical image, the scattering coefficients, obtained by the scattering transform, are stable to deformations and preserve high-frequency information. To efficiently handle these coefficients, a compression operation is carried out to reduce the dimension of the scattering coefficients. Finally, a bag-of-words (BoW) histogram of the compressed scattering coefficients is used as the texture feature of the medical image. HCSCs features are easy to implement yet discriminative because it takes both advantages of scattering transform and the BoW model. Experiments are carried out to evaluate the proposed HCSCs features, and state-of-the-art performance is obtained for medical CT images retrieval.

Experimental results:

Reference:

Rushi Lan, and Yicong Zhou*, “Medical Image Retrieval via Histogram of Compressed Scattering Coefficients,” IEEE Journal of Biomedical and Health Informatics, in press, 2016.