基于小波分析和多项式细分定位的超分辨率图像重建算法  

Super-resolution Reconstruction Method Based on Wavelet Analysis and Polynomial Subdivision Location

作　　者：贺清碧[1] 黄大荣[1] 杨永琴[2] 

机构地区：[1]重庆交通大学信息科学与工程学院,重庆400074 [2]重庆交通大学数学与统计学院,重庆400074

出　　处：《计算机科学》2016年第3期313-316,共4页Computer Science

基　　金：国家自然科学基金项目(61004118);重庆市高等学校优秀人才技术计划项目(2014-18);重庆市教委自然科学基金项目(KJ120422)资助

摘　　要：图像超分辨率重建是图像增强和图像复原研究中的一项重要课题,广泛应用于高清晰电视、医学成像和遥感成像等领域。在小波分析边缘检测的基础上,通过多项式细分算法定位亚像素边缘,将图像分为平滑区域、边缘区域和微细边缘区域。根据不同的区域特性,采用不同的插值方式进行超分辨率图像重建。仿真结果显示所提算法重建的高分辨率图像边界部分清晰自然,其主观判断和客观评价结果明显好于传统重建算法,从而验证了本算法的可行性和有效性。Image super-resolution reconstruction is an important task in the study of image enhancement and image restoration.It is widely used in the fields of high definition television,medical imaging and remote sensing imaging,etc.In this paper,the wavelet analysis was adopted to detect the pixel edges,and the polynomial subdivision algorithm was used to locate the sub-pixel edges.Therefore,the original image was divided into three parts,namely smoothing region,neighborhood edge region and minuteness edge region.According to different regional characteristics,the different interpolation methods were carried out to realize the image super-resolution reconstruction.The simulation results show that the boundary of reconstructed high resolution image is clear and natural,and the subjective judgment and objective evaluation are better than traditional reconstruction algorithm.The method in this paper achieves good effects and reaches good feasibility and validity.

关 键 词：小波分析 多项式细分 亚像素 超分辨率重建 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]