Analysing dietary data

External Member

David Ahmedt-Aristizabal

Description

Abstract: Many people become interested in keeping track of daily diet to help them control nutrition intake. The propose system should identify whether the image captured was food or nor, apply semantic segmentation to find the location of the food, predict size of the segmented food and produce health advices based on the content estimation. Dataset: public datasets (e.g. Food101).

 Contact: David Ahmedt-Aristizabal

 

Updated:  1 June 2019/Responsible Officer:  Head of School/Page Contact:  CECS Marketing