Using graph cut segmentation for food calorie measurement

Calorie measurement systems that run on smart phones allow the user to take a picture of the food and measure the number of calories automatically. In order to identify the food accurately in such systems, image segmentation, which partitions an image into different regions, plays an important role. In this paper, we present the implementation of Graph cut segmentation as a means of improving the accuracy of our food classification and recognition system. Graph cut based method is well-known to be efficient, robust, and capable of finding the best contour of objects in an image, suggesting it to be a good method for separating food portions in a food image for calorie measurement. In this paper, we provide the analysis of the Graph cut algorithm as applied to food recognition. We also perform a number of experiments where we used results from the segmentation phase to the Support Vector Machine (SVM) classification model. The results show an improvement in the accuracy of food recognition, especially mixed food where accuracy increases by 15% compared to our previous work [10].

[1]  Shervin Shirmohammadi,et al.  Measuring Calorie and Nutrition From Food Image , 2014, IEEE Transactions on Instrumentation and Measurement.

[2]  Kiyoharu Aizawa,et al.  Image-based Calorie Content Estimation for Dietary Assessment , 2011, 2011 IEEE International Symposium on Multimedia.

[3]  Shervin Shirmohammadi,et al.  An image procesing approach for calorie intake measurement , 2012, 2012 IEEE International Symposium on Medical Measurements and Applications Proceedings.

[4]  Gareth Funka-Lea,et al.  Graph Cuts and Efficient N-D Image Segmentation , 2006, International Journal of Computer Vision.

[5]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[6]  Mingui Sun,et al.  3D/2D model-to-image registration for quantitative dietary assessment , 2012, 2012 38th Annual Northeast Bioengineering Conference (NEBEC).

[7]  Lee Humphreys,et al.  It's Time to Eat! Using Mobile Games to Promote Healthy Eating , 2010, IEEE Pervasive Computing.

[8]  B. Achiriloaie,et al.  VI REFERENCES , 1961 .

[9]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Corby K. Martin,et al.  Quantification of food intake using food image analysis , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Mingui Sun,et al.  Determination of food portion size by image processing , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  Olga Veksler,et al.  Semiautomatic segmentation with compact shape prior , 2009, Image Vis. Comput..

[13]  Yoshihiro Saeki,et al.  Proposal of Food Intake Measuring System in Medical Use and Its Discussion of Practical Capability , 2005, KES.

[14]  Abdulsalam Yassine,et al.  Cloud-based SVM for food categorization , 2015, Multimedia tools and applications.

[15]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.