Work

Image enhancement and quality measures for dietary assessment using mobile devices

Year: 2012

Type: conference-paper

Abstract: Measuring accurate dietary intake is considered to be an open research problem in the nutrition and health fields. We are developing a system, known as the mobile device food record (mdFR), to automatically identify and quantify foods and beverages consumed based on analyzing meal images captured with a mobile device. The mdFR makes use of a fiducial marker and other contextual information to calibrate the imaging system so that accurate amounts of food can be estimated from the scene. Food identification is a difficult problem since foods can dramatically vary in appearance. Such variations may arise not only from non-rigid deformations and intra-class variability in shape, texture, color and other visual properties, but also from changes in illumination and viewpoint. To address the color consistency problem, this paper describes illumination quality assessment methods implemented on a mobile device and three post color correction methods.

Source: Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE

DOI: 10.1117/12.909949

Authors: Chang Xu, Fengqing Zhu, Nitin Khanna, Carol J. Boushey, Edward J. Delp

Institutions: Purdue University West Lafayette, University of Hawaii Cancer Center

Language: English

Topic: Image Processing Techniques and Applications

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDG: Zero hunger

Open Access status: green

Funders: National Cancer Institute, National Institute of Diabetes and Digestive and Kidney Diseases