Loading...

Mono-modal image registration via correntropy measure

Ghaffari, A ; Sharif University of Technology | 2013

575 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianMVIP.2013.6779983
  3. Publisher: IEEE Computer Society , 2013
  4. Abstract:
  5. The registration of images is a fundamental task in numerous applications in medical image processing. Similarity measure is an important key in intensity based image registration. Here, we propose correntropy measure as similarity measure in mono modal setting. Correntropy is a important measure between two random variables based on information theoretic learning and kernel methods. This measure is useful in non-Gaussian signal processing. In this paper, this measure is used in image registration. Here, we analytically illustrate that this measure is robust in presence of spiky noise (impulsive noise). The experimental results show that the proposed similarity has better performance than traditional intensity-based similarity measures such as Mutual information and SSD
  6. Keywords:
  7. Computer vision ; Signal processing ; Better performance ; Correntropy ; Free-form deformation ; Information theoretic learning ; Mutual informations ; NonGaussian signals ; Similarity measure ; Spiky noise ; Image registration
  8. Source: Iranian Conference on Machine Vision and Image Processing, MVIP ; Sept , 2013 , Pages 223-226 ; 21666776 (ISSN) ; 9781467361842 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6779983