视觉信息的随机共振  

Stochastic Resonance of Visual Information

作　　者：冷永刚[1] 王太勇[1] 李瑞欣[1] 邹海林[2] 郭焱[2] 

机构地区：[1]天津大学机械工程学院,天津300072 [2]山东工商学院计算机系,烟台264005

出　　处：《天津大学学报（自然科学与工程技术版）》2004年第6期480-484,共5页Journal of Tianjin University：Science and Technology

基　　金：国家自然科学基金资助项目(50175081);国家"863"高科技研究计划资助项目(2002AA414420).

摘　　要：通过噪声的概率分布论述了噪声在图像处理中增强或弱化视觉效果的作用,阐明了随机共振图像产生的机理,即在一定噪声强度条件下,图像视觉质量可以达到最佳效果.证明了不仅是噪声强度,而且噪声的类型同样会影响视觉质量.通过两种典型噪声的比较分析,得出了在各种类型的噪声中,以添加线性分布的均匀随机噪声所产生的随机共振图像质量效果为最好的结论,本研究为图像表述、目标识别、视觉理解等工程应用提供了一种方法.最后,为自动实现图像的随机共振,给出了一个最佳噪声强度的快速搜索算法.In terms of the probability distribution of noise, the role of noise strengthening or weakening the visual perception property in image processing is analyzed, and the mechanism of the stochastic resonance (SR) image is clearly illustrated, i.e., under a certain amount of noise intensity, the visual quality of an image can be resonated to an optimal state. In the present work, it is proved that not only the noise intensity but also its type can affect the visual perception quality. By means of the comparison of two types of typical noise, a conclusion is deduced of all kinds of noise the uniform random noise characterized by the linear distribution probability is able to produce the highest perceptual quality of the stochastic resonance image.The research provides a kind of method for such engineering application as visual understanding, image description,target detection,etc.In the end, a fast search algorithm of the optimal noise intensity for automatic realization of the stochastic resonance image has been finally provided.

关 键 词：视觉信息 随机共振 噪声 

分 类 号：O414.2[理学—理论物理]