Personal dietary assessment using mobile devices
Abstract
In this thesis, we investigate image segmentation and classification methods for automatically identifying food items. In this work, color and texture features are used to design the image classification method. The goal is to use these image analysis techniques to create a novel food recording method using a mobile device that will provide an accurate account of daily food and nutrient intake. We also have designed an User-Interface for a Windows Mobile Device which lets the user to "record" foods consumed by capturing the before and after images of the meal. The user-interface also lets the user label the food items.
Degree
M.S.E.C.E.
Advisors
Delp, Purdue University.
Subject Area
Electrical engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.