Contourlet

About: Contourlet is a research topic. Over the lifetime, 3533 publications have been published within this topic receiving 38980 citations.

A novel multiscale transform decomposition based multi-focus image fusion framework

Abstract: In this work, we propose a novel multiscale transform decomposition model for multi-focus image fusion to get a better fused performance. The motivation of the proposed fusion framework is to make full use of the decomposition characteristics of multiscale transform. The nonsubsampled contourlet transform (NSCT) is firstly used to decompose the source multi-focus images into low-frequency (LF) and several high-frequency (HF) bands to separate out the two basic characteristics of source images, i.e., principal information and edge details. The common “average” and “max-absolute” fusion rules are performed on low- and high-frequency components, respectively, and a basic fusion image is generated. Then the difference images between the basic fused image and the source images are calculated, and the energy of the gradient (EOG) of difference images are utilized to refine the basic fused image by integrating average filter and median filter. Visual and quantitative using fusion metrics like VIFF, QS, MI, QAB/F, SD, QPC and running time comparisons to state-of-the-art algorithms demonstrate the out-performance of the proposed fusion technique.

Image amalgamation method based on mixed multi-resolution decomposition

Abstract: The invention discloses a mixed multi-resolution decomposition-based method for image fusion. The method comprises the following steps: performing the nonsubsampled contourlet decomposition of two source images to obtain coefficients of high frequency and low frequency subbands; calculating an energy value of the high frequency subband according to the coefficient of the high frequency subband, and selecting a coefficient with the largest energy value as a transformation coefficient of a fused high frequency contourlet; further performing the static wavelet transformation of the coefficient of the low frequency subband, fusing a high frequency component of the coefficient of the low frequency subband by using a wavelet coefficient energy value maximization method, fusing a low frequency component of the coefficient of the low frequency subband by using an average method to obtain a transformation coefficient of static wavelets; and performing the inverse transformation of the transformation coefficient of the static wavelets to obtain a fused image. The method has the combined advantages of the static wavelet transformation and the contourlet transformation in expressing differentimage characteristics, and can effectively improve the quality of a fusion result image and achieve ideal fusion effect.

Weighted-PCA Based Multimodal Medical Image Fusion in Contourlet Domain

Abstract: Multimodal medical image fusion is used to fuse the complementary features from diverse modalities and abandon the superfluous information. The fusion of structural medical images-computed tomography (CT) and magnetic resonance imaging (MRI) scans provides to deliver an extensive fused image consisting of obligatory anatomical minutiae to improve medical diagnosis. This paper presents a weighted principal component analysis (PCA) based approach for multimodal fusion in Contourlet domain. The sole aim of using Contourlet transform is because of its adeptness to capture visual geometrical structures and anisotropy. Further, weighted PCA assists in reducing the dimensionality of the source images as well as helps in better selection of principal components. Maximum and minimum fusion rules are then applied to fuse the decomposed coefficients. Image quality assessment (IQA) is carried out using standard fusion metrics quantitatively to assess the fused image both in terms of information content as well as quality of reconstruction. Simulation results with the proposed fusion method depict an effective fusion response in comparison to other state-of-art approaches.