Utilizing Mask R-CNN for Solid-Volume Food Instance Segmentation and Calorie Estimation

Abstract

To prevent or deal with chronic diseases, using a smart device, automatically classifying food categories, estimating food volume and nutrients, and recording dietary intake are considered challenges. In this work, a novel real-time vision-based method for solid-volume food instance segmentation and calorie estimation is utilized, based on Mask R-CNN. In order to address the proposed method in real life, distinguishing it from other methods which use 3D LiDARs or RGB-D cameras, this work applies RGB images to train the model and uses a simple monocular camera to test the result. Gimbap is selected as an example of solid-volume food to show the utilization of the proposed method. Firstly, in order to improve detection accuracy, the proposed labeling approach for the Gimbap image datasets is introduced, based on the posture of Gimbap in plates. Secondly, an optimized model to detect Gimbap is created by fine-tuning Mask R-CNN architecture. After training, the model reaches AP (0.5 IoU) of 88.13% for Gimbap1 and AP (0.5 IoU) of 82.72% for Gimbap2. mAP (0.5 IoU) of 85.43% is achieved. Thirdly, a novel calorie estimation approach is proposed, combining the calibration result and the Gimbap instance segmentation result. In the fourth section, it is also shown how to extend the calorie estimation approach to be used in any solid-volume food, such as pizza, cake, burger, fried shrimp, oranges, and donuts. Compared with other food calorie estimation methods based on Faster R-CNN, the proposed method uses mask information and considers unseen food. Therefore, the method in this paper outperforms the accuracy of food segmentation and calorie estimation. The effectiveness of the proposed approaches is proven.