Abstract
We demonstrate that a neural network can be trained to learn the transformation from dirty to clean segments of a painting. The inputs to the network are pixels belonging to dirty paint segments and the desired output are pixels from clean segments. We find that the transformation from dirty to clean portions is nonlinear which is contrary to the assumption of some of the previous works on digital cleaning. Finally, we used the neural network to virtually clean a digital image of Fernando Amorsolo’s Malacañang by the River.
© 2010 Optical Society of America
PDF ArticleMore Like This
V. F. Rodríguez-Esquerre, A. Dourado-Sisnando, and Fabrício G. S. Silva
JTuB25 Integrated Photonics Research, Silicon and Nanophotonics (IPR) 2010
Tomi Pitkäaho, Aki Manninen, and Thomas J. Naughton
Th3A.1 Digital Holography and Three-Dimensional Imaging (DH) 2019
Lei Tian and George Barbastathis
DMC4 Digital Holography and Three-Dimensional Imaging (DH) 2010