A novel medical image fusion method based on the multi-scale geometric analysis tool

作者：Shen Yu^*; Dang Jian Wu; Wang Yang Ping; Feng Xin; Luo Wei Wei

来源：Journal of Optoelectronics - Laser, 2013, 24(12): 2446-2451.

• Beamlet Transform
• Clustering segmentation
• Contourlet transform
• Low frequency regions
• Multi-scale geometric analysis
• Non subsampled contourlet transform (NSCT)
• Subband coefficients
• Translational invariance

This study proposes a novel medical image fusion method based on the multi-scale geometric analysis tool-non-subsampled contourlet transform (NSCT) and Beamlet transform. The NSCT is applied to image processing field because of its directional, anisotropic and translational invariance properties. Beamlet transform has the advantage of perfect line feature detection ability. At first, this algorithm decomposes the images by the NSCT. In high frequency region, it uses the Beamlet transform to make edge detection. Then it uses the edge density difference value of the clustering segmentation to get the coefficient fusion rules. In low frequency region, this algorithm uses the standard variance coefficient of partial region to get the fusion rules. After that, it performs consistency correction for the fused coefficients. Finally, it gets the reconstructed image by the inverse NSCT transform on the fused high frequency and low frequency subband coefficients. The experiment results show that compared with traditional fusion methods, this algorithm can effectively diminish the fusion image ambiguity caused by the noise. It enhances the linear details presentation ability and increases the information amount.

• 出版日期2013