摘要
针对很难使用一种图像复原技术来满足实际的成像系统应用需求的情况,提出了一种基于无参考图像质量评价的自动图像复原技术。该技术在图像复原中引入图像质量评价,使图像复原技术变为主动图像复原。为应对图像降质过程的复杂性,介绍了基于图像质量评价的多模式图像复原框架。为适应由于图像复原过程的病态性导致的图像误差问题,提出了一种新的无参考图像质量评价方法,该算法通过在图像质量算子中引入图像相似矩阵和图像复原趋势矩阵,使其能适应复原对于图像结构或噪声结构变化。实验表明该图像质量评价算子的有效性,可以满足自动图像复原对图像质量评价算法的要求。
It is difficult to use a kind image restoration to satisfy the real imaging system due to the complexity of the image degradation process.Aiming at this problem,a new image restoration technique based on the no-reference image quality assessment（IQA）metric is proposed.The image restoration is changed to an active process by use of the IQA technique.Considering the complexity of image degradation process,the multi-modal image restoration base on the IQA technique is proposed.Aiming at the error of the restoration due to the ill-posed problems of the image restoration process,a no-reference IQA metric for the image restoration is proposed.The image similar matrix and the image restoration matrix are introduced in this metric,and it can adapt to the change of image structure,noise structure or the noise quantity due to the image restoration.The validity of the IQA metric is validated by the experiments.And it can be used in the active image restoration.
出处
《传感技术学报》
CAS
CSCD
北大核心
2012年第7期930-935,共6页
Chinese Journal of Sensors and Actuators
基金
国家高新技术研究发展863计划(G107302)
关键词
图像处理
自动图像复原
图像质量评价
奇异值分解
image processing
automatic image restoration
image quality assessment
singular value decomposition
