À propos de cet article
Publié en ligne: 10 mars 2014
Pages: 321 - 336
Reçu: 20 juil. 2013
Accepté: 12 févr. 2014
DOI: https://doi.org/10.21307/ijssis-2017-658
Mots clés
© 2014 Daode Zhang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Image-matching is a basic task in image procession used to (geometrically) match two or more images such as different times, different sensors and different view points. Improved image-matching technology has been widely applied in medical image, remote sensing image, computer vision military and so on. What put forward at the present can be most divided into matching method based on gray and features. The article presents a scheme that is based on subtraction images matching with dynamic selection of templates, which overcomes these more sensitive disadvantages like gray, rotate, deformation and occlusion to achieve accurate calibration for different images.