Handle URI:
http://hdl.handle.net/10754/597655
Title:
Bayesian object classification of gold nanoparticles
Authors:
Konomi, Bledar A.; Dhavala, Soma S.; Huang, Jianhua Z.; Kundu, Subrata; Huitink, David; Liang, Hong; Ding, Yu; Mallick, Bani K.
Abstract:
The properties of materials synthesized with nanoparticles (NPs) are highly correlated to the sizes and shapes of the nanoparticles. The transmission electron microscopy (TEM) imaging technique can be used to measure the morphological characteristics of NPs, which can be simple circles or more complex irregular polygons with varying degrees of scales and sizes. A major difficulty in analyzing the TEM images is the overlapping of objects, having different morphological properties with no specific information about the number of objects present. Furthermore, the objects lying along the boundary render automated image analysis much more difficult. To overcome these challenges, we propose a Bayesian method based on the marked-point process representation of the objects. We derive models, both for the marks which parameterize the morphological aspects and the points which determine the location of the objects. The proposed model is an automatic image segmentation and classification procedure, which simultaneously detects the boundaries and classifies the NPs into one of the predetermined shape families. We execute the inference by sampling the posterior distribution using Markov chainMonte Carlo (MCMC) since the posterior is doubly intractable. We apply our novel method to several TEM imaging samples of gold NPs, producing the needed statistical characterization of their morphology. © Institute of Mathematical Statistics, 2013.
Citation:
Konomi BA, Dhavala SS, Huang JZ, Kundu S, Huitink D, et al. (2013) Bayesian object classification of gold nanoparticles. The Annals of Applied Statistics 7: 640–668. Available: http://dx.doi.org/10.1214/12-aoas616.
Publisher:
Institute of Mathematical Statistics
Journal:
The Annals of Applied Statistics
KAUST Grant Number:
KUS-CI-016-04
Issue Date:
Jun-2013
DOI:
10.1214/12-aoas616
Type:
Article
ISSN:
1932-6157
Sponsors:
Supported in part by the Texas Norman Hackerman Advanced Research Program under Grant
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorKonomi, Bledar A.en
dc.contributor.authorDhavala, Soma S.en
dc.contributor.authorHuang, Jianhua Z.en
dc.contributor.authorKundu, Subrataen
dc.contributor.authorHuitink, Daviden
dc.contributor.authorLiang, Hongen
dc.contributor.authorDing, Yuen
dc.contributor.authorMallick, Bani K.en
dc.date.accessioned2016-02-25T12:43:49Zen
dc.date.available2016-02-25T12:43:49Zen
dc.date.issued2013-06en
dc.identifier.citationKonomi BA, Dhavala SS, Huang JZ, Kundu S, Huitink D, et al. (2013) Bayesian object classification of gold nanoparticles. The Annals of Applied Statistics 7: 640–668. Available: http://dx.doi.org/10.1214/12-aoas616.en
dc.identifier.issn1932-6157en
dc.identifier.doi10.1214/12-aoas616en
dc.identifier.urihttp://hdl.handle.net/10754/597655en
dc.description.abstractThe properties of materials synthesized with nanoparticles (NPs) are highly correlated to the sizes and shapes of the nanoparticles. The transmission electron microscopy (TEM) imaging technique can be used to measure the morphological characteristics of NPs, which can be simple circles or more complex irregular polygons with varying degrees of scales and sizes. A major difficulty in analyzing the TEM images is the overlapping of objects, having different morphological properties with no specific information about the number of objects present. Furthermore, the objects lying along the boundary render automated image analysis much more difficult. To overcome these challenges, we propose a Bayesian method based on the marked-point process representation of the objects. We derive models, both for the marks which parameterize the morphological aspects and the points which determine the location of the objects. The proposed model is an automatic image segmentation and classification procedure, which simultaneously detects the boundaries and classifies the NPs into one of the predetermined shape families. We execute the inference by sampling the posterior distribution using Markov chainMonte Carlo (MCMC) since the posterior is doubly intractable. We apply our novel method to several TEM imaging samples of gold NPs, producing the needed statistical characterization of their morphology. © Institute of Mathematical Statistics, 2013.en
dc.description.sponsorshipSupported in part by the Texas Norman Hackerman Advanced Research Program under Granten
dc.publisherInstitute of Mathematical Statisticsen
dc.subjectBayesian shape analysisen
dc.subjectGranulometryen
dc.subjectImage processingen
dc.subjectImage segmentationen
dc.subjectMarkov chain monte carloen
dc.subjectNanoparticlesen
dc.subjectObject classificationen
dc.titleBayesian object classification of gold nanoparticlesen
dc.typeArticleen
dc.identifier.journalThe Annals of Applied Statisticsen
dc.contributor.institutionTexas A and M University, College Station, United Statesen
kaust.grant.numberKUS-CI-016-04en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.