Towards Computer Vision Powered Color-Nutrient Assessment of Puréed Food

Kaylen J. Pfisterer, Robert Amelard, Braeden Syrnyk, Alexander Wong
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
With one in four individuals afflicted with malnutrition, computer vision may provide a way of introducing a new level of automation in the nutrition field to reliably monitor food and nutrient intake. In this study, we present a novel approach to modeling the link between color and vitamin A content using transmittance imaging of a puréed foods dilution series in a computer vision powered nutrient sensing system via a fine-tuned deep autoencoder network, which in this case was trained to
more » ... t the relative concentration of sweet potato purées. Experimental results show the deep autoencoder network can achieve an accuracy of 80% across beginner (6 month) and intermediate (8 month) commercially prepared puréed sweet potato samples. Prediction errors may be explained by fundamental differences in optical properties which are further discussed.
doi:10.1109/cvprw.2019.00068 dblp:conf/cvpr/PfistererASW19 fatcat:zgv33ispdfgb5njob4bermpnti