超分辨率图像模糊区域边界优化修复仿真

Super-resolution image blur region boundary optimization repair simulation

针对现有的超分辨率图像模糊区域边界优化修复方法存在的峰值信噪比较低、平均绝对误差值较大等问题,提出了一种基于贝叶斯的超分辨率图像模糊区域边界优化修复方法,首先对待修复超分辨率图像模糊区域进行边界检测和小波降噪操作,然后对确定的边界破损位置进行小波特征提取,分析模糊区域边界破损点的向量量化数据。通过贝叶斯方法实现对超分辨率图像模糊区域边界优化修复。仿真实验结果表明,采用所提方法可以在高峰值信噪比、低平均绝对误差值的情况下完成对超分辨率图像模糊区域边界优化修复,且用时较短。

Aiming at the problems of low peak signal-to-noise ratio and large average absolute error in the existing super-resolution image blur region boundary optimization repair method, a Bayesian-based super-resolution image blur region boundary optimization is proposed. In this method, the boundary detection and wavelet denoising operations of the super-resolution image blurred region are firstly treated, then the wavelet feature extraction is performed on the determined boundary damage location, and the vector quantization data of the boundary damage point of the fuzzy region are analyzed. The Bayesian method is used to optimize the boundary of the super-resolution image blur region. The simulation results show that the proposed method can optimize the boundary of the super-resolution image blur region with high peak signal-to-noise ratio and low average absolute error, and the time is short.