Failure detection on electronic systems using thermal images and metaheuristic algorithms

Gustavo R. Hernandez, Mario A. Navarro, Noe Ortega-Sanchez, Diego Oliva, Marco Perez-Cisneros

Research output: Contribution to journalArticle

Abstract

Segmentation is considered an important part of image processing. There are commonly used segmentation techniques to improve the thresholding process, such as Otsu and Kapur. The use of these techniques allows us to find the regions of interest in an image by accurately grouping the pixel intensity levels. On the other hand, the use of thermal images makes it possible to obtain information about the temperature of an object and to capture the infrared radiation of the electromagnetic spectrum through cameras that transform the radiated energy into heat information. The segmentation of this kind of images represents a challenging problem that requires a huge computational effort. This work proposes the use of metaheuristic algorithms, combined with segmentation techniques and applied to thermal images, to detect faults and contribute to the preventive maintenance of electronic systems.

Original languageEnglish
Article number9111672
Pages (from-to)1371-1380
Number of pages10
JournalIEEE Latin America Transactions
Volume18
Issue number8
DOIs
Publication statusPublished - Aug 2020
Externally publishedYes

Keywords

  • Electronic systems
  • Image segmentation
  • Metaheuristic algorithms
  • Preventive maintenance
  • Thermographic analysis
  • Thresholding

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Failure detection on electronic systems using thermal images and metaheuristic algorithms'. Together they form a unique fingerprint.

  • Cite this

    Hernandez, G. R., Navarro, M. A., Ortega-Sanchez, N., Oliva, D., & Perez-Cisneros, M. (2020). Failure detection on electronic systems using thermal images and metaheuristic algorithms. IEEE Latin America Transactions, 18(8), 1371-1380. [9111672]. https://doi.org/10.1109/TLA.2020.9111672