Abstract
Knowing the amounts of energy and nutrients in an individual’s diet is important for maintaining health and preventing chronic diseases. As electronic and AI technologies advance rapidly, dietary assessment can now be performed using food images obtained from a smartphone or a wearable device. One of the challenges in this approach is to computationally measure the volume of food in a bowl from an image. This problem has not been studied systematically despite the bowl being the most utilized food container in many parts of the world, especially in Asia and Africa. In this paper, we present a new method to measure the size and shape of a bowl by adhering a paper ruler centrally across the bottom and sides of the bowl and then taking an image. When observed from the image, the distortions in the width of the paper ruler and the spacings between ruler markers completely encode the size and shape of the bowl. A computational algorithm is developed to reconstruct the three-dimensional bowl interior using the observed distortions. Our experiments using nine bowls, colored liquids, and amorphous foods demonstrate high accuracy of our method for food volume estimation involving round bowls as containers. A total of 228 images of amorphous foods were also used in a comparative experiment between our algorithm and an independent human estimator. The results showed that our algorithm overperformed the human estimator who utilized different types of reference information and two estimation methods, including direct volume estimation and indirect estimation through the fullness of the bowl.
Highlights
Image-based dietary assessment using a wearable camera or a smartphone has been increasingly adopted in the study of nutrition and health [1,2,3,4,5,6,7,8,9,10]
Despite the importance of diet in maintaining human health and preventing chronic diseases, at present, the amount of food still cannot be gauged from images objectively and reliably
One of the challenges is that the bowl as a common food container cannot be measured with acceptable accuracy in the two-dimensional image space
Summary
Image-based dietary assessment using a wearable camera (e.g., eButton) or a smartphone has been increasingly adopted in the study of nutrition and health [1,2,3,4,5,6,7,8,9,10]. A special imaging sensor called a depth sensor has been used to produce depth on a per-pixel basis from which food volume can be estimated [22,23,24,25,26] Another effective approach uses a pair of stereo cameras separated by a distance. The 3D surface is reconstructed from the observed distortion [30,31] These sensor-based approaches are effective, the depth and structured light sensors are costly. Their sizes, weights, and power consumptions cause additional concerns when they are utilized within a wearable device. Current food volume estimation methods mostly use ordinary images (i.e., RGB images) in two dimensions (2D)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
