Ore Image Segmentation Method Based on U-Net and Watershed

作     者：Hui Li Chengwei Pan Ziyi Chen Aziguli Wulamu Alan Yang 

作者机构：School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijing100083China School of Computer and Communication EngineeringUniversity of Science and Technology BeijingBeijing100083China Beijing Key Laboratory of Knowledge Engineering for Materials ScienceBeijing100083China Amphenol AssembleTechHouston77070USA 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2020年第65卷第10期

页      面：563-578页

核心收录：

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

基　　金：This work was supported by The National Natural Science Foundation of China(Grant 61801019) 

主　　题：Image segmentation ore grain size U-Net watershed algorithm 

摘      要：Ore image segmentation is a key step in an ore grain size analysis based on image *** traditional segmentation methods do not deal with ore textures and shadows in ore images well Those methods often suffer from under-segmentation and *** this article,in order to solve the problem,an ore image segmentation method based on U-Net is *** adjust the structure of U-Net to speed up the processing,and we modify the loss function to enhance the generalization of the *** the collection of the ore image,we design the annotation standard and train the network with the annotated ***,the marked watershed algorithm is used to segment the adhesion *** experimental results show that the proposed method has the characteristics of fast speed,strong robustness and high *** has great practical value to the actual ore grain statistical task.