STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Image Processing & Pattern Recognition Progress

A Multimodal Image Fusion based on NonSubsampled Contourlet Transform and Sparse Representation

  1. Leena Chandrashekar

Abstract

Detection of tumors in the brain is vital in diagnosis of brain cancer. Doctors suggest numerous scans like CT, MRI, PET, and SPECT for estimating the type of cancer, size and location of the tumor and the aging or spread of cancer. A single imaging technique is not sufficient for correct diagnosis of the disease. In case the scans are ambiguous, it can lead doctors to incorrect diagnosis, which can be unsafe to the patient. The solution to this problem is fusing images from different scans containing complementary information to generate accurate images with minimum uncertainty. There are many ways of fusing images; the techniques considered in this paper are based on Multiscale transforms and Sparse Representation. By using, these 2 techniques a novel image fusion algorithm is proposed. NSCT and NSCT-SR are implemented and results are reported on 12 pairs of CT and MRI images. The experimental results show superior performance in terms of contrast, PSNR, UIQI and SSIM for the proposed technique.

Keywords

Support