微型电脑应用2018，Vol.34Issue(3)：9-13,5.
基于保边IBP和结构相似性的超分辨率图像重建算法
A Super Resolution Image Reconstruction Algorithm Based on Edge-Protecting Iterative Back Projection and Structural Similarity
摘要
Abstract
As the traditional super resolution algorithms cannot balance the reconstruction effect and the running speed.A new SR algorithm that combines edge-protecting iterative back projection algorithm (IBP) and structural similarity is proposed.Firstly,anisotropic diffusion is added to the traditional IBP to enhance the edges and texture,it can take into account the speed of the algorithm.Then in order to obtain more prior knowledge,structural similarity is added to the algorithm to make the reconstruction image more natural and delicate.Finally,the ratio of peak signal to noise and structural similarity are used to evaluate algorithm results.The data results show that the proposed algorithm has the highest PSNR value and SSIM value.The experimental graph results show that the image's texture can be well reserved,the images are more natural and accuracy.And the running speed is not serious behind the traditional IBP,so it is with good usability.关键词
超分辨率/保边性/迭代反投影/结构相似性/SSIMKey words
Super resolution/Edge-protecting/Iterative back projection/Structural similarity/SSIM分类
信息技术与安全科学引用本文复制引用
卜宇,梁传君..基于保边IBP和结构相似性的超分辨率图像重建算法[J].微型电脑应用,2018,34(3):9-13,5.基金项目
新疆维吾尔自治区自然科学基金项目(2013211A031) （2013211A031）
