An Adaptive Weighted Alternating Minimization Algorithm for Color Images Reconstruction In the Field of Automation
2018 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)(2018)
摘要
Along with the developing of digital image processing technology, there are more and more applications of digital images in the field of automation. However, during the process of the imaging, acquisition and transmission, digital images are often degraded due to the noise and other external environmental influence. This eventually leads to quite a lot of difficulties for the application of these degraded images in actual automation production. In a total variation (TV) minimization framework, the novel algorithm is designed to establish a connection between an alternating minimization method and half-quadratic regularization for color images reconstruction. Our contributions are threefold. Firstly, the novel algorithm uses the idea of a new bisection which shows a strong convergence while preserving texture details. Secondly, the proposed algorithm is able to determine optimal value of the regularization parameter automatically and converges with the speed of
$2^{k}$
. Lastly, our approach is quite general and has strong adaptation and robustness ability during the process of color image reconstruction.
更多查看译文
关键词
Image reconstruction,Mathematical model,Gold,Color,Signal to noise ratio,Standards,Minimization
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要