File(s) under permanent embargo
A convolutional neural network for pixelwise illuminant recovery in colour and spectral images
conference contributionposted on 2018-01-01, 00:00 authored by Antonio Robles-KellyAntonio Robles-Kelly, Ran Wei
Here, we present a pixelwise illuminant recovery method for both, trichromatic and multi or hyperspectral images which employs a convolutional neural nettwork. The network used here is based upon the simple, yet effective architecture employed by the CIFARIO-quick net. The network is trained using a loss function which employs the angular difference between the target illuminant and the estimated one as the data term. The loss used here also includes a regularisation term which encourages smoothness in the spectral domain. Moreover, the network takes, at input, a tensor which is constructed making use of an image patch at different scales. This allows the network to predict the illuminant per-pixel using locally supported multiscale information. We illustrate the utility of our method for both, colour and hyperspectal illuminant recovery and compare our results against other techniques elsewhere in literature.
EventPattern Recognition. International Conference (24th : 2018 : Beijing, China)
Pagination109 - 114
Place of publicationPiscataway, N.J.
Publication classificationE Conference publication; E1 Full written paper - refereed
Title of proceedingsICPR 2018 : Proceedings of the 24th International Conference on Pattern Recognition