联合最大熵的改进Niblack红外图像分割算法  

Improved Niblack infrared image segmentation algorithm based on joint maximum entropy

作　　者：李云红[1] 刘畅 李传真 周小计 苏雪平 任劼[1] 高子明 LI Yunhong;LIU Chang;LI Chuanzhen;ZHOU Xiaoji;SU Xueping;REN Jie;GAO Ziming(School of Electronics and Information, Xi′an Polytechnic University, Xi′an 710048, China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048

出　　处：《西北大学学报（自然科学版）》2022年第2期256-261,共6页Journal of Northwest University（Natural Science Edition）

基　　金：国家自然科学基金(61727819,61902301);陕西省科技厅自然科学基础研究重点项目(2022JZ-35);陕西省教育厅自然科学基础研究计划项目(19JK0364);国家级大学生创新创业训练计划项目(202110709002)。

摘　　要：针对红外图像在分割过程中容易产生过分割和边缘断裂的问题,该文提出了一种联合最大熵的改进Niblack红外图像分割算法。首先,根据图像的像素矩阵确定邻域窗口,再利用图像整体与局部的灰度值信息选取修正系数,改善了传统Niblack参数选择方法的不足;然后,通过局部邻域熵确定背景因子,实现图像的背景分类;最后,采取最大熵法和改进的Niblack法对不同类别的图像进行分割。实验证明,该文算法和Niblack法、OTSU法、最大熵法和分水岭法相比,分割交并比IoU平均值为0.8335,相比该文其他对比算法均有所提高,同时平均误分率仅为0.0164。An improved Niblack infrared image segmentation algorithm combined with maximum entropy is presented to overcome the shortcomings of over-segmentation and edge breakage in infrared image segmentation.Firstly,the neighborhood window is determined according to the pixel matrix of the image,then the correction factor is selected using the gray value information of the whole and local image,which improves the shortage of traditional Niblack′s parameter selection method.Then,the background factor is determined by the local neighborhood entropy to classify the image.Finally,the images of different categories are segmented by the maximum entropy method and the improved Niblack method.Experiments show that compared with Niblack,OTSU,maximum entropy and watershed methods,the average IoU of the algorithm in this paper is 0.8335.It′s higher than other comparison algorithms,and the average error rate is only 0.0164.

关 键 词：图像分割 红外图像 Niblack法 最大熵法 背景因子 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]