Experiences in building a real-world eating recogniser

• Main Authors: SEN, Sougata, SUBBARAJU, Vigneshwaran, MISRA, Archan, BALAN, Rajesh Krishna, LEE, Youngki
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: False positive and false negatives; Food imageIn-buildings; Inertial sensor; Real-world; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/3719; https://ink.library.smu.edu.sg/context/sis_research/article/4721/viewcontent/p7_sen__1_.pdf
• Institution: Singapore Management University

In this paper, we describe the progressive design of the gesture recognition module of an automated food journaling system - Annapurna. Annapurna runs on a smartwatch and utilises data from the inertial sensors to first identify eating gestures, and then captures food images which are presented to the user in the form of a food journal. We detail the lessons we learnt from multiple in-the-wild studies, and show how eating recognizer is refined to tackle challenges such as (i) high gestural diversity, and (ii) non-eating activities with similar gestural signatures. Annapurna is finally robust (identifying eating across a wide diversity in food content, eating styles and environments) and accurate (false-positive and false-negative rates of 6.5% and 3.3% respectively).