Colour constancy : biologically-inspired contrast variant pooling mechanism
Akbarinia, Arash (Centre de Visió per Computador (Bellaterra, Catalunya))
Gil Rodríguez, Raquel (Universitat Pompeu Fabra. Departament de Tecnologies de la Informació i les Comunicacions)
Parraga, Carlos Alejandro (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Data:	2017
Resum:	Pooling is a ubiquitous operation in image processing algorithms that allows for higher-level processes to collect relevant low-level features from a region of interest. Currently, max-pooling is one of the most commonly used operators in the computational literature. However, it can lack robustness to outliers due to the fact that it relies merely on the peak of a function. Pooling mechanisms are also present in the primate visual cortex where neurons of higher cortical areas pool signals from lower ones. The receptive fields of these neurons have been shown to vary according to the contrast by aggregating signals over a larger region in the presence of low contrast stimuli. We hypothesise that this contrast-variant-pooling mechanism can address some of the shortcomings of maxpooling. We modelled this contrast variation through a histogram clipping in which the percentage of pooled signal is inversely proportional to the local contrast of an image. We tested our hypothesis by applying it to the phenomenon of colour constancy where a number of popular algorithms utilise a max-pooling step (e. g. White-Patch, Grey-Edge and Double-Opponency). For each of these methods, we investigated the consequences of replacing their original max-pooling by the proposed contrast-variant-pooling. Our experiments on three colour constancy benchmark datasets suggest that previous results can significantly improve by adopting a contrast-variant-pooling mechanism.
Ajuts:	Ministerio de Economía y Competitividad TIN2013-41751-P Ministerio de Economía y Competitividad TIN2013-49982-EXP
Drets:	Tots els drets reservats.
Llengua:	Anglès
Document:	Comunicació de congrés ; recerca ; Versió publicada
Publicat a:	British Machine Vision Conference. Imperial College London (London), 4-7 Sep. 2017

Adreça original al programa del congrés: http://www.bmva.org/bmvc/2017/index.html

14 p, 24.8 MB

El registre apareix a les col·leccions:
Contribucions a jornades i congressos > Ponències i comunicacions > Ponències i comunicacions de la UAB