基于插值与NSQCT域融合的图像超分辨率重建  

Image super-resolution reconstruction based on interpolation and NSQCT fusion

作　　者：殷明[1] 庞纪勇 褚标[1] 魏远远[1] 

机构地区：[1]合肥工业大学数学学院,合肥230009

出　　处：《电子测量与仪器学报》2015年第10期1440-1448,共9页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(11172086);安徽省自然科学基金(1308085MA09);安徽省教育厅自然科学研究重点(KJ2013A216)资助项目

摘　　要：为了提高图像的分辨率和较好地保留图像的细节信息,提出一种基于插值与非下采样四元数轮廓波变换(NSQCT)域融合相结合的单幅图像超分辨率重建算法。首先对源图像进行软判决自适应插值和三次样条插值;然后对两幅插值图像进行NSQCT分解,对于低频子带系数,提出了基于区域平均梯度、区域能量和S函数相结合的自适应加权融合规则;对于高频子带系数,提出了一种基于改进的拉普拉斯能量和与加权分析法相结合的融合规则;最后对融合系数进行NSQCT逆变换得到高分辨率重建图像。实验结果表明,本文方法在峰值信噪比、结构相似性及视觉效果上均优于一些经典的重建算法。In order to improve the image resolution and well reserve the detail information of image,a novel singleimage super-resolution reconstruction algorithm based on interpolation and non-subsampled quaternion contourlet transform（NSQCT） fusion is proposed.Firstly,the source image is separately interpolated by soft-decision adaptive interpolation（SAI） and cubic spline interpolation（CSI）.Then the NSQCT is adopted to decompose the two interpolated images.For the low frequency sub-band coefficients,an adaptive weighted fusion method combining the regional average gradient,regional energy with Sigmoid function is presented,while for the high frequency subband coefficients,a fusion rule based on the new Sum-modified Laplacian combined with the weighted analysis is presented.Finally,the high resolution image is obtained by performing the inverse NSQCT on the fused coefficients.The experimental results show that the proposed algorithm outperforms those classical reconstruction algorithms in terms of peak signal-to-noise ratio,structural similarity as well as visual quality.

关 键 词：超分辨率重建 软判决自适应插值 非下采样四元数轮廓波变换 图像融合 自适应加权 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN911.73[自动化与计算机技术—计算机科学与技术]