ePrints

Variational Bayesian Sub-group Adaptive Sparse Component Extraction for Diagnostic Imaging System

Lookup NU author(s): Dr Bin Gao, Dr Wai Lok Woo, Professor Gui Yun TianORCiD, Dr Martin Johnston

Downloads

• Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of an article that has been published in its final definitive form by IEEE, 2018.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

IEEE A novel unsupervised sparse component extraction algorithm is proposed for detecting micro defects when employing a thermography imaging system. The proposed approach is developed using the Variational Bayesian framework. This enables a fully automated determination of the model parameters and bypasses the need for human intervention in manually selecting the appropriate image contrast frames. An internal sub-sparse grouping mechanism and adaptive fine-tuning strategy have been built to control the sparsity of the solution. The proposed algorithm is computationally affordable and yields a high accuracy objective performance. Experimental tests on both artificial and natural defects have been conducted to verify the efficacy of the proposed method.

Publication metadata

Author(s): Gao B, Lu P, Woo WL, Tian GY, Zhu Y, Johnston M

Publication type: Article

Publication status: Published

Journal: IEEE Transactions on Industrial Electronics

Year: 2018

Volume: 65

Issue: 10

Pages: 8142-8152

Print publication date: 01/10/2018

Online publication date: 05/02/2018

Acceptance date: 02/04/2016

Date deposited: 27/02/2018

ISSN (print): 0278-0046

ISSN (electronic): 1557-9948

Publisher: IEEE

URL: https://doi.org/10.1109/TIE.2018.2801809

DOI: 10.1109/TIE.2018.2801809

Altmetrics

Share