联合小波变换和RSF模型的CT图像分割方法  

CT Image Segmentation Method Combining Wavelet Transform and RSF Model

作　　者：王珏[1,2] 张秀英[1,2] 蔡玉芳 卢艳平[1,2] Jue Wang;Xiuying Zhang;Yufang Cai;Yanping Lu(College of Optoelectronic Engineering,Chongqing University,Chongqing 400044,China;Engineering Research Center of Industrial Computed Tomography Nondestructive Testing,Ministry of Education,Chongqing University,Chongqing 400044,China)

机构地区：[1]重庆大学光电工程学院,重庆400044 [2]重庆大学工业CT无损检测教育部工程研究中心,重庆400044

出　　处：《光学学报》2020年第21期51-59,共9页Acta Optica Sinica

基　　金：国家科技重大专项(2017-VII-0011-0106)。

摘　　要：为解决工业计算机层析成像(CT)图像的伪影和弱边缘问题,提出一种基于小波变换的图像区域可伸缩拟合能量最小化分割方法,实现图像边缘的精确定位,从而提高图像测量精度。首先,采用小波变换对图像进行预处理,降低金属伪影。然后,采用所提方法精确分割图像,提高感兴趣区域边缘的定位精度。实际数据测量结果表明,所提方法可有效降低图像弱边缘的影响,测量相对误差低于0.7%,相较Chan-Vese算法,测量精度提高了1.4倍,满足实际测量需求。To solve the problems of artifacts and weak edges of industrial computed tomography (CT) images, an image region-scalable fitting energy minimization segmentation method based on wavelet transform is proposed to achieve the accurate positioning of image edges, and improve the image measurement accuracy. First, the wavelet transform is used to preprocess the image in order to reduce metal artifacts. Then, the proposed method is employed to accurately segment the image, which aims to improve the location accuracy of the edge of the region of interest. Actual data measurement results show that the proposed method can effectively reduce the effect on weak edges of the images, and the relative error of measurement is less than 0.7%, which is 1.4 times higher than that of the Chan-Vese algorithm and meets the requirements of measurement applications.

关 键 词：图像处理 CT图像测量 区域可伸缩拟合能量最小化 小波变换 弱边缘分割 CHAN-VESE模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]