Modelling surface color discrimination under different lighting environments using image chromatic statistics and convolutional neural networks
Ponting, S.; Morimoto, T.; Smithson, H. E.
Show abstract
We modeled discrimination thresholds for object colors under different lighting environments [1]. Firstly we built models based on chromatic statistics, testing 60 models in total. Secondly we trained convolutional neural networks (CNNs), using 160,280 images labeled either by the ground-truth or by human responses. No single chromatic statistics model was sufficient to describe human discrimination thresholds across conditions, while human-response-trained CNNs nearly perfectly predicted human thresholds. Guided by region-of-interest analysis of the network, we modified the chromatic statistics models to use only the lower regions of the objects, which substantially improved performance.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions 97%
- Deep neural networks trained for estimating albedo and illumination achieve lightness constancy differently than human observers. 96%
- Visual discrimination of optical material properties: a large-scale study 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Sensitivity to the slope of the amplitude spectrum is dependent on the spectral slopes of recently viewed environments: A visual adaptation study in modified reality 96%
- Explaining #TheShoe based on the optimal color hypothesis: The role of chromaticity vs. luminance distribution in ambiguous image 95%
- The influence of stereopsis on visual saliency in a proto-object based model of selective attention 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.