Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2016, Director: Petia Radeva
In this work we are going to experiment with convolutional neural networks with the objective of recognizing food related environments. Through our project we are going to analyze which sections of the images are being targeted to classify the image in one category or in other.
Lastly we are going to benchmark how much the nets are learning using confusion matrices to visualize which categories are harder to classify.