基于信息熵引导耦合复杂度调节模型的红外图像增强算法

Infrared image enhancement algorithm based on information entropy guided coupled with complexity adjustment model

为了解决当前较多红外图像增强方法依靠图像的直方图来增强图像,没有考虑图像所含信息量的大小,导致增强结果存在边缘模糊等不足,设计了信息熵引导耦合复杂度调节模型的红外图像增强算法。引入非局部均值滤波方法,将图像中的噪声去除的同时保留图像的细节内容。再利用信息熵函数,测量出图像所含信息量大小,以计算自适应分割阈值,将图像自适应的分割成两部分,并基于直方图均衡化方法,对分割后的子图进行对比度增强,从而求取富含信息量的对比度增强图像。根据图像的灰度级大小,建立复杂度测量函数,计算出图像的细节丰富程度;构造复杂度调节模型,根据图像的细节丰富程度,对图像的细节进行不同程度的增强,以获取边缘等细节特征清晰的细节增强图像。实验结果显示,较当前红外图像增强算法而言,所提算法可更好的提升增强后图像边缘等细节特征的清晰度。

In order to solve the problem as the edge blur in the enhancement results induced by using the histogram of the image to enhance the image,without considering the amount of image information in most infrared image enhancement methods,this paper designs an infrared image enhancement algorithm based on information entropy guided coupled with complexity adjustment model.The nonlocal mean filtering method is introduced to remove the noise in the image while preserving the details of the image.Then the information entropy function is used to measure the amount of information contained in the image,which is used to establish an adaptive segmentation threshold.The image is adaptively divided into two parts.Through the histogram equalization process,the contrast of the segmented sub image is enhanced,and then the contrast enhanced image rich in information is obtained.According to the gray level,the complexity measurement function is constructed to measure the detail richness of the image.And the complexity adjustment model is constructed to enhance the details of the image in different degrees according to the detail richness of the image,and then obtain the detail enhanced image with clear edge and other detail features.The experimental results show that,compared with the current infrared image enhancement algorithm,this algorithm can better enhance the clarity of the edge and other details of the enhanced image.