We have used a pre trained Convolutional Neural Network as a feature extractor to train an image category classifier. After working on two benchmark databases, we got the success rate of 99.5% which is higher than the accuracy achieved using bag of features (BoF) and SURF.
Fastfood4
Recognition and Classification of Fast-Food Images
Food recognition and calorie extraction using Bag-of-SURF and Spatial Pyramid Matching methods