Towards computer vision powered color-nutrient assessment of pureed food
This work addresses malnutrition by providing an automated method for nutrient monitoring, but it is incremental as it focuses on a specific food type and uses existing deep learning techniques.
The study tackled the problem of automating nutrient assessment by modeling the link between color and vitamin A content in pureed foods using a computer vision system, achieving 80% accuracy in predicting sweet potato puree concentrations.
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 pureed 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 predict the relative concentration of sweet potato purees. Experimental results show the deep autoencoder network can achieve an accuracy of 80% across beginner (6 month) and intermediate (8 month) commercially prepared pureed sweet potato samples. Prediction errors may be explained by fundamental differences in optical properties which are further discussed.