An image fusion method based on content cognition

摘要

A cognition-based image fusion algorithm for multi-source images is put forward in this paper. The fusion process is guided by the abstract representation acqui red by the prior knowledge which implies human deep understandings for the targets and the scene. Different fusion rules are applied for contents of different importance, which make the image fusion more free and flexible. Image fusion tests for visible and infrared image are conducted. And we compare our fusion results with that of region-based fusion algorithms. Both experimental results and image fusion quality indexes show the superiorities of the fusion algorithm based on content cognition.