Vision-based food nutrition estimation via RGB-D fusion network

AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review

OBJECTIVE

Human error estimating food intake is a major source of bias in nutrition research. Artificial intelligence (AI) methods may reduce bias, but the overall accuracy of AI estimates is unknown. This study was a systematic review of peer-reviewed journal articles comparing fully automated AI-based (e.g. deep learning) methods of dietary assessment from digital images to human assessors and ground truth (e.g. doubly labelled water).

MATERIALS AND METHODS

Literature was searched through May 2023 in four electronic databases plus reference mining. Eligible articles reported AI estimated volume, energy, or nutrients. Independent investigators screened articles and extracted data. Potential sources of bias were documented in absence of an applicable risk of bias assessment tool.

RESULTS

Database and hand searches identified 14,059 unique publications; fifty-two papers (studies) published from 2010 to 2023 were retained. For food detection and classification, 79% of papers used a convolutional neural network. Common ground truth sources were calculation using nutrient tables (51%) and weighed food (27%). Included papers varied widely in food image databases and results reported, so meta-analytic synthesis could not be conducted. Relative errors were extracted or calculated from 69% of papers. Average overall relative errors (AI vs. ground truth) ranged from 0.10% to 38.3% for calories and 0.09% to 33% for volume, suggesting similar performance. Ranges of relative error were lower when images had single/simple foods.

CONCLUSIONS

Relative errors for volume and calorie estimations suggest that AI methods align with - and have the potential to exceed - accuracy of human estimations. However, variability in food image databases and results reported prevented meta-analytic synthesis. The field can advance by testing AI architectures on a limited number of large-scale food image and nutrition databases that the field determines to be adequate for training and testing and by reporting accuracy of at least absolute and relative error for volume or calorie estimations.

DPF-Nutrition: Food Nutrition Estimation via Depth Prediction and Fusion

A reasonable and balanced diet is essential for maintaining good health. With advancements in deep learning, an automated nutrition estimation method based on food images offers a promising solution for monitoring daily nutritional intake and promoting dietary health. While monocular image-based nutrition estimation is convenient, efficient and economical, the challenge of limited accuracy remains a significant concern. To tackle this issue, we proposed DPF-Nutrition, an end-to-end nutrition estimation method using monocular images. In DPF-Nutrition, we introduced a depth prediction module to generate depth maps, thereby improving the accuracy of food portion estimation. Additionally, we designed an RGB-D fusion module that combined monocular images with the predicted depth information, resulting in better performance for nutrition estimation. To the best of our knowledge, this was the pioneering effort that integrated depth prediction and RGB-D fusion techniques in food nutrition estimation. Comprehensive experiments performed on Nutrition5k evaluated the effectiveness and efficiency of DPF-Nutrition.

Deep Learning-Based Near-Infrared Hyperspectral Imaging for Food Nutrition Estimation

The limited nutritional information provided by external food representations has constrained the further development of food nutrition estimation. Near-infrared hyperspectral imaging (NIR-HSI) technology can capture food chemical characteristics directly related to nutrition and is widely used in food science. However, conventional data analysis methods may lack the capability of modeling complex nonlinear relations between spectral information and nutrition content. Therefore, we initiated this study to explore the feasibility of integrating deep learning with NIR-HSI for food nutrition estimation. Inspired by reinforcement learning, we proposed OptmWave, an approach that can perform modeling and wavelength selection simultaneously. It achieved the highest accuracy on our constructed scrambled eggs with tomatoes dataset, with a determination coefficient of 0.9913 and a root mean square error (RMSE) of 0.3548. The interpretability of our selection results was confirmed through spectral analysis, validating the feasibility of deep learning-based NIR-HSI in food nutrition estimation.