基于数学形态学的路面裂纹图像分割方法  

Pavement Crack Image Segmentation Method Based on Mathematical Morphology

作　　者：刘训星 张海民 LIU Xun-xing;ZHANG Hai-min(College of Information and Finance and Economics,Xuancheng Vocational and Technical College,Xuancheng 242000,China;School of Computer and Software Engineering,Anhui Institute of Information Engineering,Wuhu 241000,China)

机构地区：[1]宣城职业技术学院信息与财经学院,安徽宣城242000 [2]安徽信息工程学院计算机与软件工程学院,安徽芜湖241000

出　　处：《辽东学院学报（自然科学版）》2023年第2期130-135,共6页Journal of Eastern Liaoning University:Natural Science Edition

基　　金：安徽省教育厅自然科学重点研究项目(KJ2021A1423);安徽高校自然科学重点研究项目(KJ2021A1206);安徽高等学校省级质量工程项目(2022zygzts053)。

摘　　要：已有裂纹图像分割方法无法对较小裂纹特征进行具体描述,导致路面图像中的裂纹提取结果不全面等问题,为此提出基于数学形态学的路面裂纹图像分割方法。采用空间域处理方法对原始图像像素进行增强处理,通过正变换及逆变换得到新的路面裂纹图像,并划分出图像中的噪声类型;使用灰度值表示噪声,使用均值滤波法中的3×3模板表示离散图像的裂纹元素与噪声元素,并对路面裂纹图像进行去噪处理;利用经典数学形态学理论,对路面裂纹图像结构元素进行表达,在膨胀和腐蚀处理过程中判断裂纹的形式变化,实现裂纹分割。单一裂纹图像和复杂裂纹图像的实验结果表明:所提方法可以有效提取裂纹特征值,特征提取率为99.5%,并在不同噪声条件下具有较高的分割效率,可以满足路面裂纹检测需求。Aiming at the problem that the existing crack image segmentation methods cannot describe the characteristics of small cracks in detail,resulting in incomplete crack extraction results in pavement images,a pavement crack image segmentation method based on mathematical morphology is proposed.The spatial domain processing method is used to enhance the original image pixels,and the new pavement crack image is obtained by positive and inverse transformation,and the noise types in the image are divided.The gray value is used to represent the noise,and the 3×3 template in the mean filtering method is used to represent the crack elements and noise elements of the discrete image,and the pavement crack image is denoised.Using the classical mathematical morphology theory,the structural elements of the pavement crack image are expressed,and the form change of the crack is judged during the expansion and corrosion treatment process to realize the crack segmentation.The experimental results of single crack image and complex crack image show that the proposed method can effectively extract crack feature values,the feature extraction rate is 99.5%,and has high segmentation efficiency under different noise conditions,which can meet the needs of pavement detection.

关 键 词：数学形态学 路面裂纹 图像处理 分割方法 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]