Food volume estimation based on stereo image analysis

Eating disorder may involve the consumption of excessive amounts of food, more than the human body needs. Numerous related efforts have been devoted to dietary assessment programs that require a daily self-logging and manual identification of food type and volume, which are analyzed later by a computer or a mobile device. This is known to be a challenging task especially when it involves accurate logging of the amount and time of the food intake. For these reasons, the need for a fully automatic approach to carry out all the tasks of food intake detection, food type classification, and dietary assessment has been the point of focus in many recent works [1].