Food image analysis has been one of the most important tasks accomplished for automatic dietary monitoring. In this work, we address semantic segmentation of food images with Deep Learning. Additionally, we explore food and non-food segmentation by getting advantage of supervised learning. Specifically, we have experimented SegNet model on these two food-related computer vision tasks. Experimental results show that followed approach brings appealing results on semantic food segmentation and significantly advances on food and non-food segmentation.