organised by

 

 

Invited Talks

Food Recognition based on Deep Learning

Prof. Petia Radeva

University de Barcelona

The analysis of people's nutrition habits is one of the most important mechanisms for applying a thorough monitorisation of several medical conditions e.g. obesity, that affect a high percentage of the global population. Methods for automatically logging one's meals could not only make the process easier, but also make it objective to the user's point of view and interpretability. Automatic food recognition is a Machine Learning and Computer Vision problem that has not received enough attention in the literature, partly due to the complex nature of the problem: high amount of often ambiguous categories of food, lack of big datasets covering the diet of people, big variation in meals appearance from the same categories or among different geographical cuisines, etc. In this talk, we will show how deep learning applied to the food detection and food recognition problems can help to automatically analyze and store the user's food diary and will introduce the largest database for food recognition that contains more than 900 meals from all over the world and poses new challenges for Machine Learning and Computer Vision communities.

Biography

Petia Radeva is Tenured Associate professor at the Universitat de Barcelona (UB), Department of Mathematics and Informatics, where from 2009 to 2013 she was Director of Computer Science Undergraduate Studies. Petia Radeva is Head of the Consolidated Group Computer Vision at the University of Barcelona (CVUB) (www.ub.edu/cvub) and Head of the Medical Imaging Laboratory of Computer Vision Center (www.cvc.uab.es). Petia Radeva’s research interests are on Development of learning-based approaches (specially, deep learning) for computer vision, and their application to health. Currently, she is involved on projects that study the application of wearable cameras and life-logging, to extract visual diary of individuals to be used for memory reinforcement of patients with mental diseases (e.g. Mild cognitive impairment). Moreover, she is exploring how to extract semantically meaningful events that characterize lifestyle and healthy habits of people from egocentric data. She is Associate editor of the International Journal on Pattern Recognition and the International Journal of Visual Communication and Image Representation. She obtained the IAPR Fellow award in 2016, the »Aurora Pons Porrata» award from CIARP in 2016, the ICREA award from the Catalonian Government in 2014 and the »Antonio Caparrós» award for the best technology transfer project of UB in 2013.

presentation © Shutterstock presentation © Petra Perner presentation © Shutterstock