NSST与改进SCM模型相结合的多聚焦图像融合算法  

A Multi-Focus Image Fusion Algorithm Based on NSST and Improved SCM Model

作　　者：魏辉琪 刘增力[1] WEI Huiqi;LIU Zengli(Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《电视技术》2021年第4期25-29,共5页Video Engineering

基　　金：国家自然科学基金项目(No.61271007)。

摘　　要：当前的图像融合方法存在运算数据量大和运算时间较长的弊端,为了改进这一不足,提出一种新算法。将图像经过Opencv降噪处理,去除冗余信息,再计算边缘能量(Energy of Edge,EOE),根据高低频信息特性选择融合规则,通过逆变换重构出融合后的图像。作为图像融合过程的第一步也是至关重要的一步,图像配准直接影响着最终融合图像的质量,因此通过Opencv对图像进行降噪处理会使得图像更加清晰,提高融合后的图像质量。仿真结果表明,与其他方法相对比,利用该算法融合出的图像在图像质量和运算时间方面都有所改进。The current image fusion methods have the disadvantages of large amount of data and long operation time.In order to solve this problem,a new algorithm is proposed in this paper.After the image is processed by Opencv noise reduction,the redundant information is removed,,then the Energy of Edge(EOE)is calculated,and the fusion rules are selected according to the high and low frequency information characteristics,then the fused image is reconstructed by inverse transformation.In Image Fusion,image registration,as the first step of image fusion,is also a crucial step,which directly affects the final quality of the fused image,improving image quality after fusion.The simulation results show that compared with other methods,the image quality and operation time are improved.

关 键 词：非下采样剪切波 脉冲发放皮层模型 图像融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]