Volume 40, Number 6, December 2022
|Page(s)||1414 - 1421|
|Published online||10 February 2023|
Image fusion method based on JBF and multi-order local region energy
School of Physics and Electrical Engineering, Weinan Normal University, Weinan 714099, China
2 School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
针对多模态医学图像融合方法融合质量差、计算效率低等问题。提出了一种基于联合双边滤波(JBF)与多阶局部区域能量(MLNE)的图像融合方法。该方法将输入图像分解成能量层和结构层, 对于能量层与结构层的融合分别提出了基于MLNE和局部区域L2范数取大值的融合方案, 融合能量层和结构层相加获得融合图像。1组不同模态的医学图像融合实验结果证明, 文中提出的方法在融合性能、计算效率、视觉评价等方面都优于其他的对比方法。
To address the poor fusion quality and low computational efficiency of multimodal medical image fusion methods. In this paper, an image fusion method based on joint bilateral filtering (JBF) and multi-order local region energy (MLNE) is proposed. The method firstly decomposes the input image into energy and structure layers; then for the fusion of energy and structure layers, a fusion scheme based on MLRE and local area L2 norm taking large values is proposed respectively; finally, the fused energy and structure layers are summed to obtain the fused image. The experimental results of medical image fusion with one groups of different modalities prove that the present method outperforms other comparative methods in terms of fusion performance, computational efficiency, and visual evaluation.
Key words: joint bilateral filter / multi-order local regional energy / medical image fusion / L2 norm
关键字 : 联合双边滤波 / 多阶局部区域能量 / 医学图像融合 / L2范数
© 2022 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.