View Item 

Efficient superpixel based segmentation for food image analysis

Access Status
Fulltext not available
Authors
Wang, Y.
Liu, C.
Zhu, F.
Boushey, Carol
Delp, E.
Date
2016
Type
Conference Paper

Metadata
Show full item record
Citation
Wang, Y. and Liu, C. and Zhu, F. and Boushey, C. and Delp, E. 2016. Efficient superpixel based segmentation for food image analysis, in Proceedings of the International Conference on Image Processing, Sep 25-28 2016, pp. 2544-2548. Phoenix, AZ, USA: IEEE.
Source Title
Proceedings - International Conference on Image Processing, ICIP
DOI
ISBN
School
School of Public Health
URI
Collection
Abstract

In this paper, we propose a segmentation method based on normalized cut and superpixels. The method relies on color and texture cues for fast computation and efficient use of memory. The method is used for food image segmentation as part of a mobile food record system we have developed for dietary assessment and management. The accurate estimate of nutrients relies on correctly labelled food items and sufficiently well-segmented regions. Our method achieves competitive results using the Berkeley Segmentation Dataset and outperforms some of the most popular techniques in a food image dataset.