Predicting Privileged Information for Height Estimation
This work addresses height estimation in computer vision, an incremental improvement for applications like biometrics or healthcare.
The paper tackles the problem of height estimation from images by using a regression-based method that predicts privileged anthropometric ratios, which are not available at test time, to improve accuracy and speed. It reports better performance than the ε-SVR+ algorithm across different genders and height quartiles.
In this paper, we propose a novel regression-based method for employing privileged information to estimate the height using human metrology. The actual values of the anthropometric measurements are difficult to estimate accurately using state-of-the-art computer vision algorithms. Hence, we use ratios of anthropometric measurements as features. Since many anthropometric measurements are not available at test time in real-life scenarios, we employ a learning using privileged information (LUPI) framework in a regression setup. Instead of using the LUPI paradigm for regression in its original form (i.e., ε-SVR+), we train regression models that predict the privileged information at test time. The predictions are then used, along with observable features, to perform height estimation. Once the height is estimated, a mapping to classes is performed. We demonstrate that the proposed approach can estimate the height better and faster than the ε-SVR+ algorithm and report results for different genders and quartiles of humans.