基于àtrous-NSCT变换和区域特性的图像融合方法  

Image Fusion Method Based on àtrous-NSCT Transform and Region Characteristic

作　　者：曹义亲[1] 曹婷 黄晓生[1] CAO Yi-qin;CAO Ting;HUANG Xiao-sheng(College of Software,East China Jiaotong University,Nanchang 330013,China)

机构地区：[1]华东交通大学软件学院

出　　处：《计算机科学》2019年第6期270-276,共7页Computer Science

基　　金：国家自然科学基金项目(61365008);江西省科技支撑计划项目(20161BBE50081);江西省教育厅科技项目(GJJ150522,GJJ150526)资助

摘　　要：针对àtrous小波变换与NSCT这两种多尺度变换的优缺点,通过引入àtrous-NSCT变换工具,提出了一种基于àtrous-NSCT变换和区域特性的图像融合方法。此方法将区域平均梯度作为活性测度,以系数取大的融合方法完成低频子带图像的融合;选用基于区域方差加权自适应模型的融合方法完成高频子带图像的融合,通过àtrous逆变换处理获得融合后的最终结果。在实验中将新提出的方法与其他5种多尺度融合方法进行比较,结果表明,当新型多尺度变换的分解层数为4时,所获得的融合结果在主观视觉与客观评价两方面的性能都得到了明显的提升。Aiming at the advantages and disadvantages of two kinds of multi-scale transforms ofàtrous wavelet transform and NSCT,through introducingàtrous-NSCT transform tool,this paper proposed an image fusion method based onàtrous-NSCT transform and region characteristics.This method regards the regional average gradient as the activity measure,and makes use of the fusion method with large coefficient to complete the low-frequency sub-band image fusion.Then,it utilizes the fusion method based on adaptive model with regional variance weighting for high-frequency sub-band images to complete the fusion,thus obtaining the final fusion results throughàtrous inverse transform process.In the experiment,the proposed method was compared with other five multi-scale fusion methods.The experimental results show that the fusion results obtained by the proposed method are significantly improved in both subjective vision and objective evaluation as the number of decomposition layers of the new multi-scale transformation is 4.

关 键 词：àtrous-NSCT变换 区域平均梯度 活性测度 区域方差加权 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]