Evaluating CNN-based semantic food segmentation across illuminants

In this paper we aim to explore the potential of Deep Convolutional Neural Networks (DCNNs) on food image segmentation where semantic segmentation paradigm is used to separate food regions from the non-food regions. Specifically, we are interested in evaluating the performance of an efficient DCNN with respect to variability in illumination conditions that can be found in food images taken in real scenarios. To this end we have designed an experimental setup where the network is trained on images rendered as if they were taken under nine different illuminants. We evaluate the food vs. non-food segmentation performance of the network in terms of standard Intersection over Union (IoU) measure. The results of this experimentation are reported and discussed.