中国光学, 2016, 9 (5): 532, 网络出版: 2016-10-19   

稀疏阈值的超分辨率图像重建

Super-resolution image reconstruction based on sparse threshold
作者单位
1 中国科学院 长春光学精密机械与物理研究所 应用光学国家重点实验室,吉林 长春 130033
2 中国科学院大学,北京 100049
摘要
为了解决基于字典学习的超分辨重构算法耗时过长的问题,提出了基于稀疏阈值模型的图像超分辨率重建方法。首先,将联合字典理论与图像块稀疏阈值方法相结合,训练得到高、低分辨率过完备图像字典对。接着,通过稀疏阈值OMP算法对图像特征块进行稀疏表示。然后,通过高分辨率字典重构出初始的超分辨图像。最后,通过改进迭代反投影算法对初始的超分辨图像进行全局优化,从而进一步提高图像重构质量。实验结果表明,超分辨图像重构平均峰值信噪比(PSNR)为301 dB,平均结构自相似度(SSIM)为0937 9,平均计算时间为102 s。有效提高了超分辨重构的速度,改善了重构高分辨图像的质量。
Abstract
In order to solve the problem of the time consuming of the super-resolution reconstruction algorithm based on dictionary learning, a method of super-resolution image reconstruction based on sparse threshold model is proposed. First of all, the over-complete dictionary couple based on the theory of joint dictionary by method of sparse threshold is obtained. And then, the sparse representation of feature block image is represented by sparse threshold OMP algorithm. Then, the initial super-resolution image is reconstructed by the high resolution dictionary. Finally, the global optimization of the initial super-resolution image is improved by the modified iterative back projection algorithm, which can improve the quality of reconstructed image. The experimental results show that the average peak signal to noise ratio(PSNR) is 301 dB; the average structure self-similarity(SSIM) is 0937 9; the average computation time is 102 s. This method can improve not only the speed of super-resolution reconstruction, but also the quality of reconstructed high resolution images.

何阳, 黄玮, 王新华, 郝建坤. 稀疏阈值的超分辨率图像重建[J]. 中国光学, 2016, 9(5): 532. HE Yang, HUANG Wei, WANG Xin-hua, HAO Jian-kun. Super-resolution image reconstruction based on sparse threshold[J]. Chinese Optics, 2016, 9(5): 532.

本文已被 7 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!