基于广义线性系统和非锐化掩膜的图像增强算法  

Image enhancement algorithm based on generalized linear system and unsharp masking

作　　者：范日召 何斌[1] 刘燕君[3] 李军凯[4] 陈洋君 FAN Ri-zhao HE Bin LIU Yan- jun LI Jun-kai CHEN Yang- jun(Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033？ China University of Chinese Academy of Sciences , Beijing 100049,China Shenzhen Institute of Advanced Technology . Chinese Academy of Sciences ,Shenzhen 518055 , China Northeastern University ,Shenyang 110819 , China)

机构地区：[1]中国科学院长春光学精密机械与物理研究所,吉林长春130033 [2]中国科学院大学,北京100049 [3]中国科学院深圳先进技术研究院,广东深圳518055 [4]东北大学,辽宁沈阳110819

出　　处：《液晶与显示》2016年第10期973-982,共10页Chinese Journal of Liquid Crystals and Displays

基　　金：广东省引进创新科研团队项目(No.2011S013)

摘　　要：为了解决非锐化掩膜图像增强方法的噪声增益、光晕现象和数据溢出的问题,提出一种基于广义线性系统和非锐化掩膜的图像增强算法。算法首先采用双边滤波器和广义线性减法对图像进行处理,获取图像细节层和基础层;然后对图像细节层和基础层分别进行自适应增益处理和对比度增强处理;最后采用广义线性加法将两者相加,实现图像的增强。并对3种不同类型的图像进行测试,结果表明:本文提出的算法很好地抑制了噪声干扰和光晕现象,增强了图像的对比度和细节,视觉效果良好,信息熵分别提高了10.9012%、16.0143%和9.1878%。表明了提出的基于广义线性系统和非锐化掩膜图像增强算法的合理有效性。In order to solve the problem that unsharp masking suffers from noise over-enhancement,halo effect and data overflow,an image enhancement algorithm based on generalized linear system and unsharp masking is proposed.Firstly,the algorithm adopts bilateral filter and generalized subtraction to decompose image and obtains the detail layer and the root layer.Then the detail layer and the root layer are dealt with adaptive gain control and contrast enhancement operation,respectively.Finally,the generalized addition is adopted to carry out superposition to realize image enhancement.And the test experiments for three different types of images are carried out.The outcome shows that the proposed algorithm can get good results in restraining noise and halo effect,enhancing contrast and detail of image and obtaining fine visual effect.The entropy of images is increased by 10.9012%,16.014 3% and 9.1878% respectively.It indicates that the image enhancement algorithm based on generalized linear system and unsharp masking is reasonable and effective.

关 键 词：非锐化掩膜 图像增强 广义线性系统 细节层 基础层 

分 类 号：TP911.73[自动化与计算机技术]