Body mass index (BMI) analysis from face images is an interesting and challenging topic in machine learning and computer vision. Recent research shows that facial adiposity is associated with BMI prediction. In this work, we investigate the problem of visual BMI estimation from face images by a two-stage learning framework. BMI-related facial features are learned from the first stage. Then a label distribution based BMI estimator is learned by an optimization procedure that is implemented by projecting the features and assigned labels to a new domain which maximizing the correlation between them. Two label assignment strategies are analyzed for modeling the single BMI value as a discrete probability distribution over a range of BMIs. Extensive experiments are conducted on FIW-BMI, Morph II and VIP_attribute datasets. The experimental results show that the two-stage learning framework improves the performance step by step. More importantly, the proposed BMI estimator efficiently reduces the error. It outperforms regression based methods, two label distribution methods and two deep learning methods in most cases.

面部图像的体重指数（BMI）分析在机器学习和计算机视觉中是一个有趣且具有挑战性的主题。最近的研究表明，面部肥胖与BMI预测有关。在这项工作中，我们通过两阶段学习框架研究了从人脸图像中进行视觉BMI估计的问题。从第一阶段开始学习与BMI有关的面部特征。然后，通过优化程序来学习基于标签分布的BMI估计器，该优化程序通过将特征和分配的标签投影到新域来实现，从而最大化它们之间的相关性。分析了两种标签分配策略，用于将单个BMI值建模为一系列BMI上的离散概率分布。在FIW-BMI，Morph II和VIP_attribute数据集上进行了广泛的实验。实验结果表明，两阶段学习框架逐步提高了性能。更重要的是，提出的BMI估计器有效地减少了误差。在大多数情况下，它的性能优于基于回归的方法，两种标签分配方法和两种深度学习方法。