We propose a method to extract thin occlusions from multi-focus images. The occluders are various shapes of arbitrarily thin noise (e.g., fences, window shutters, tree branches and football nets). The proposed method can recognize and extract the thin occlusions in a variety of complex scenes by using color similarity and image registration. Experimental results on real images show the validity of the proposed method.

Date Published: 8 March 2017
PDF: 6 pages
Proc. SPIE 10255, Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016, 1025540 (8 March 2017); doi: 10.1117/12.2268111

Published in SPIE Proceedings Vol. 10255:
Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016
Yueguang Lv; Jialing Le; Hesheng Chen; Jianyu Wang; Jianda Shao, Editor(s)