基于广义线性系统和非锐化掩膜的图像增强算法

摘要

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 pro-posed 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%,1 6.014 3%and 9.1878% respectively.It indicates that the image enhancement algorithm based on generalized lin-ear system and unsharp masking is reasonable and effective.%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。