DocumentCode :
2951549
Title :
A New Texture Feature for Improved Food Recognition Accuracy in a Mobile Phone Based Dietary Assessment System
Author :
Rahman, Md Hafizur ; Pickering, M.R. ; Kerr, D. ; Boushey, C.J. ; Delp, E.J.
Author_Institution :
Sch. of Eng. & Inf. Technol., Univ. of New South Wales, Canberra, ACT, Australia
fYear :
2012
fDate :
9-13 July 2012
Firstpage :
418
Lastpage :
423
Abstract :
Poor diet is one of the key determinants of an individual´s risk of developing chronic diseases. Assessing what people eat is fundamental to establishing the link between diet and disease. Food records are considered the best approach for assessing energy intake however paper-based food recording is cumbersome and often inaccurate. Researchers have begun to explore how mobile devices can be used to reduce the burden of recording nutritional intake. The integrated camera in a mobile phone can be used for capturing images of food consumed. These images are then processed to automatically identify the food items for record keeping purposes. In such systems, the accurate classification of food items in these images is vital to the success of such a system. In this paper we will present a new method for generating texture features from food images and demonstrate that this new feature provides greater food classification accuracy for a mobile phone based dietary assessment system.
Keywords :
cameras; diseases; feature extraction; food products; image classification; image texture; medical computing; mobile computing; object recognition; records management; chronic diseases; energy intake assessment; food consumption; food item classification; food item identification; food recognition accuracy; food records; image capture; integrated camera; mobile phone based dietary assessment system; nutritional intake recording; texture feature generation; Databases; Feature extraction; Filter banks; Filtering algorithms; Gabor filters; Mobile handsets; Vectors; Dietary assessment; Gabor filters; object recognition; scale invariance; texture features;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo Workshops (ICMEW), 2012 IEEE International Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-2027-6
Type :
conf
DOI :
10.1109/ICMEW.2012.79
Filename :
6266420
Link To Document :
بازگشت