Bayesian object classification of gold nanoparticles

Bledar A. Konomi, Soma S. Dhavala, Jianhua Z. Huang, Subrata Kundu, David Huitink, Hong Liang, Yu Ding, Bani K. Mallick

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


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.
Original languageEnglish (US)
Pages (from-to)640-668
Number of pages29
JournalThe Annals of Applied Statistics
Issue number2
StatePublished - Jun 2013
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): KUS-CI-016-04
Acknowledgements: Supported in part by the Texas Norman Hackerman Advanced Research Program under Grant
This publication acknowledges KAUST support, but has no KAUST affiliated authors.


Dive into the research topics of 'Bayesian object classification of gold nanoparticles'. Together they form a unique fingerprint.

Cite this