Automated grain boundary detection using the level set method

作     者：Lu, Bibo Cui, Min Liu, Qiang Wang, Yangang 

作者机构：Jilin Univ Coll Math Changchun 130012 Peoples R China Henan Polytech Univ Sch Comp Sci & Technol Jiaozuo 454000 Peoples R China China Univ Petr Basin & Reservoir Res Ctr Beijing 102249 Peoples R China Chinese Acad Sci Comp Network Informat Ctr Supercomp Ctr Beijing 100190 Peoples R China 

出 版 物：《COMPUTERS & GEOSCIENCES》 (计算机与地学)

年 卷 期：2009年第35卷第2期

页      面：267-275页

核心收录：

学科分类：08[工学] 0708[理学-地球物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China, NSFC, (10531040, 10671082, 10801061) Henan Polytechnic University, HPU Major State Basic Research Development Program of China, (G2005CB422107) 

主　　题：Grain boundary detection The level set method Automated image segmentation Strain analysis 

摘      要：In this paper, we detect the grain boundary by using a novel automated algorithm which is based on the level set method (the LSM). The LSM starts with only one initial closed curve which can be arbitrary in both shape and location in the microphotograph. The curve splits and merges repeatedly until it reaches the boundaries of the objects. The evolution depends on the structure of the image. This method requires simple and feasible constraints which ensure the exclusion of the objects unsuitable for reliable measurements and strain analysis. The LSM has the following three advantages: (1) with a single image as input, segmentation is automated without human intervention, (2) the grain boundary detected by the LSM is a closed curve, and (3) simple post-processing maintains the shape of the boundary. The segmentation and strain analysis by the LSM are demonstrated and the results are compared with those from hand-drawn method. (c) 2008 Elsevier Ltd. All rights reserved.