Image Fusion Algorithm of Focal Region Detection and TAM-SCM Based on SHT Domain

基于SHT域TAM-SCM与焦聚区域检测的图像融合算法

School of Automation, Northwestern Polytechnical University, Xi’an 710129, China

Received: 6 March 2018

Abstract

The selection of texture information and block ringing effect in multi-focus fusion process, a new multi-focus image fusion algorithm based on Three Activity Measures (TAM) excitation Spiking Cortical Model, (SCM) in shearlet (SHT) domain is proposed. Firstly, in SHT domain, using local spatial frequency (SF), local energy of gradient (EOG) and different measurements (SF, EOG, and local laplace energy sum (SML)) motivated SCM selected the texture information and construct the initial fusion image (P). Then, the focal region was extracted from the significant feature of the difference between the image P and the original image. Finally, the joint focus area produces fusion images. To verify the superiority of the proposed algorithm, compare the results of this paper with seven competing methods. Experimental results show that the algorithm can produce clear edges, good visual perception and less distortion.

摘要

针对聚焦图像融合过程中细节信息的选取和振铃效应问题，提出了一种基于剪切波（shearlet，SHT）域3种活跃量测（three activity measures，TAM）激发脉冲皮发神经元模型（spiking cortical model，SCM）的多聚焦图像融合新算法。首先，在SHT域，采用局部空间频率（space frequency，SF）和局部梯度能量（energy of gradient，EOG）及不同量测（SF，EOG和局部拉普拉斯能量和（sum-modified-Laplacian，SML））激励SCM模型选择纹理信息并构造初始融合图像P。然后，计算图像P与原图像之间差异的显著性特征提取焦距区域。最后，联合聚焦区域产生融合图像。为了验证提出算法的优越性，将文中结果与7种竞争的方法比较，实验结果表明新算法获得了清晰的边缘，产生了良好的视觉感知和较少的失真。