Infrared image non-rigid registration based on regional information entropy demons algorithm

Published

Conference Paper

© 2015 SPIE. Infrared imaging fault detection which is treated as an ideal, non-contact, non-destructive testing method is applied to the circuit board fault detection. Since Infrared images obtained by handheld infrared camera with wide-Angle lens have both rigid and non-rigid deformations. To solve this problem, a new demons algorithm based on regional information entropy was proposed. The new method overcame the shortcomings of traditional demons algorithm that was sensitive to the intensity. First, the information entropy image was gotten by computing regional information entropy of the image. Then, the deformation between the two images was calculated that was the same as demons algorithm. Experimental results demonstrated that the proposed algorithm has better robustness in intensity inconsistent images registration compared with the traditional demons algorithm. Achieving accurate registration between intensity inconsistent infrared images provided strong support for the temperature contrast..

Full Text

Duke Authors

Cited Authors

  • Lu, C; Ma, L; Yu, M; Cui, S; Wu, Q

Published Date

  • January 1, 2015

Published In

Volume / Issue

  • 9449 /

Electronic International Standard Serial Number (EISSN)

  • 1996-756X

International Standard Serial Number (ISSN)

  • 0277-786X

International Standard Book Number 13 (ISBN-13)

  • 9781628415650

Digital Object Identifier (DOI)

  • 10.1117/12.2075406

Citation Source

  • Scopus