Variational Bayesian Subgroup Adaptive Sparse Component Extraction for Diagnostic Imaging System

Bin Gao, Peng Lu, Wai Lok Woo, Gui Yun Tian, Yuyu Zhu, Martin Johnston

Research output: Contribution to journalArticlepeer-review

59 Citations (Scopus)

Abstract

A novel unsupervised sparse component extraction algorithm is proposed for detecting micro defects while 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 subsparse 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.
Original languageEnglish
Pages (from-to)8142-8152
Number of pages11
JournalIEEE Transactions on Industrial Electronics
Volume65
Issue number10
Early online date5 Feb 2018
DOIs
Publication statusPublished - Oct 2018

Keywords

  • Diagnostic imaging system
  • electromagnetic thermography
  • low-rank decomposition
  • sparse decomposition
  • variational Bayesian (VB)

Fingerprint

Dive into the research topics of 'Variational Bayesian Subgroup Adaptive Sparse Component Extraction for Diagnostic Imaging System'. Together they form a unique fingerprint.

Cite this