基于自适应直方图均衡化耦合拉普拉斯变换的红外图像增强算法  

Infrared image enhancement algorithm based on adaptive histogram equalization coupled with Laplace transform

作　　者：吕侃徽[1] 张大兴[2] LV Kanhui;ZHANG Daxing(School of Information Technology,Zhejiang Financial College,Hangzhou 310018,China;School of Computer,Hangzhou Dianzi University,Hangzhou 310018,China)

机构地区：[1]浙江金融职业学院信息技术学院,浙江杭州310018 [2]杭州电子科技大学计算机学院,浙江杭州310018

出　　处：《光学技术》2021年第6期747-753,共7页Optical Technique

基　　金：国家自然科学基金(61572160,61272391);浙江省自然科学基金资助项目(LY20F020002);浙江省科技厅科研项目(15ZJSS1024);浙江省省属高校基本科研业务费项目资金资助(2021ZD08)。

摘　　要：当前较多红外图像增强方法利用图像灰度特征增强图像,这类方法忽略了图像灰度分布的不均匀性,导致增强结果存在细节丢失和对比度不理想等问题,为了克服上述问题,提出了一种自适应直方图均衡化耦合拉普拉斯变换的红外图像增强算法。将输入图像进行均匀分割后,借助洛伦兹曲线的基尼系数,求取了图像灰度分布的不均匀性程度,从而构造了自适应的上、下限阈值,用于对图像进行自适应直方图均衡化,以实现对图像进行对比度增强;引入平滑滤波方法,去除图像中的噪声。并在传统拉普拉斯变换的基础上,融入图像像素值的对角二阶导数信息,形成8邻域拉普拉斯变换,以完成图像边缘等细节内容的锐化处理,以增强图像清晰度;利用本算法对不同红外图像进行了增强实验,结果显示,本算法具有更好的增强质量,其输出图像拥有更高的对比度和清晰度,呈现出更好的视觉效果。At present,many infrared image enhancement methods use image gray features to enhance the image.These methods ignore the non-uniformity of image gray distribution,resulting in the loss of details and unsatisfactory contrast.In order to overcome the above problems,an infrared image enhancement algorithm based on adaptive histogram equalization coupled with Laplace transform is proposed.Firstly,after the input image is evenly segmented,the degree of non-uniformity of image gray distribution is calculated with the help of Gini coefficient of Lorentz curve.Based on the degree of non-uniformity of image gray distribution,the adaptive upper and lower thresholds are constructed to realize adaptive histogram equalization for image contrast enhancement.Then,the smooth filtering method is introduced to remove the noise in the image.Based on the traditional Laplace transform,the eight neighborhood Laplace transform is formed by integrating the diagonal second derivative information of image pixel value,which is used to sharpen the image edge and other details,so as to enhance the image clarity.Finally,the algorithm is used to enhance different infrared images.The experimental results show that the contrast and clarity of the enhanced image are better,and the visual effect is better.

关 键 词：红外图像增强 直方图均衡化 自适应阈值 平滑滤波 拉普拉斯变换 灰度不均匀性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]