Symmetry-aware recursive image similarity exploration for materials microscopy

作     者：Tri N.M.Nguyen Yichen Guo Shuyu Qin Kylie S.Frew Ruijuan Xu Joshua C.Agar 

作者机构：Department of Materials Science and EngineeringLehigh UniversityBethlehemPA 18015USA Department of Computer Science and EngineeringLehigh UniversityBethlehemPA 18015USA Department of Mechanical EngineeringLehigh UniversityBethlehemPA 18015USA Department of Applied PhysicsStanford UniversityStanfordCA 94305USA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2021年第7卷第1期

页      面：1508-1521页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：T.N.M.N.acknowledges primary support from the Nano/Human Interfaces Presidential Initiative and secondary support from National Science Foundation under grant TRIPODS+X:RES-1839234 Y.G.,J.C.A.,S.Q.,and K.S.F.acknowledge primary support from National Science Foundation under grant TRIPODS+X:RES-1839234 We graciously acknowledge all experimentalists who were involved in collecting the data used in this study.Contributors include Prof.Lane Martin and Ramamoorthy Ramesh.We want to recognize all trainees that took part in collecting this data,including Liv Dedon,Shishir Pandya,Anoop Damodaran,Sahar Saremi,Anoop Damodaran,Zhuhang Chen,Ran Gao,Shang-lin Hsu,Julia Mundy,Arvind Dasgupta,Gabe Velarde,Xiaoyan Lu,Sujit Das,Ajay Yadav,Bhagwati Prasad,James Clarkson,David Pesquera,Jieun Kim,Megha Acharya,Suraj Cheema,Eduardo Lupi,Wenbo Zhao,Lei Zhang,Margaret McCarter,Hongling Hu,and Derek Meyers 

主　　题：interactive image similarity 

摘      要：In pursuit of scientific discovery,vast collections of unstructured structural and functional images are acquired;however,only an infinitesimally small fraction of this data is rigorously analyzed,with an even smaller fraction ever being *** method to accelerate scientific discovery is to extract more insight from costly scientific experiments already ***,data from scientific experiments tend only to be accessible by the originator who knows the experiments and ***,there are no robust methods to search unstructured databases of images to deduce correlations and ***,we develop a machine learning approach to create image similarity projections to search unstructured image *** improve these projections,we develop and train a model to include symmetry-aware *** an exemplar,we use a set of 25,133 piezoresponse force microscopy images collected on diverse materials systems over five *** demonstrate how this tool can be used for interactive recursive image searching and exploration,highlighting structural similarities at various length *** tool justifies continued investment in federated scientific databases with standardized metadata schemas where the combination of filtering and recursive interactive searching can uncover synthesis-structure-property *** provide a customizable open-source package(https://***/m3-learning/Recursive_Symmetry_Aware_Materials_Microstructure_Explorer)of this interactive tool for researchers to use with their data.