Search papers, labs, and topics across Lattice.
This paper introduces a deep learning model for estimating Body Mass Index (BMI) from smartphone camera images, trained on a large-scale, newly collected WayBED dataset of 71,322 filtered images. They developed an automatic filtering method based on posture clustering and person detection to curate the dataset, removing low-quality images. The resulting model achieves state-of-the-art performance, with a 7.9% MAPE on the WayBED test set and competitive results on the VisualBodyToBMI dataset, and is deployed on Android devices using the CLAID framework.
A new deep learning model slashes the error rate for BMI estimation from smartphone photos, opening the door to more accessible and convenient health assessments.
Estimating Body Mass Index (BMI) from camera images with machine learning models enables rapid weight assessment when traditional methods are unavailable or impractical, such as in telehealth or emergency scenarios. Existing computer vision approaches have been limited to datasets of up to 14,500 images. In this study, we present a deep learning-based BMI estimation method trained on our WayBED dataset, a large proprietary collection of 84,963 smartphone images from 25,353 individuals. We introduce an automatic filtering method that uses posture clustering and person detection to curate the dataset by removing low-quality images, such as those with atypical postures or incomplete views. This process retained 71,322 high-quality images suitable for training. We achieve a Mean Absolute Percentage Error (MAPE) of 7.9% on our hold-out test set (WayBED data) using full-body images, the lowest value in the published literature to the best of our knowledge. Further, we achieve a MAPE of 13% on the completely unseen~(during training) VisualBodyToBMI dataset, comparable with state-of-the-art approaches trained on it, demonstrating robust generalization. Lastly, we fine-tune our model on VisualBodyToBMI and achieve a MAPE of 8.56%, the lowest reported value on this dataset so far. We deploy the full pipeline, including image filtering and BMI estimation, on Android devices using the CLAID framework. We release our complete code for model training, filtering, and the CLAID package for mobile deployment as open-source contributions.
ETH