Robust facial landmark detection by probability-guided hourglass network

The absence of local features and global shape constraints severely limits the performance of the hourglass network for facial landmark detection in unconstrained environments. Moreover, diverse feature types and scales may result in low accuracy. This paper proposes a probability-guided hourglass network to enhance the shape constraints for robust facial landmark detection. Firstly, a multi-scale pre-processing module is designed to extract features at different scales. Secondly, based on the heatmaps generated by the stacked hourglass network, the coarse localizations are obtained, while the probability maps are generated with local features. Finally, a probability-based boundary regression method is proposed and the hausdorff distance is modified as the loss function to constrain the feature shape. Adaptive weights are also added to the loss function, which can help relieve the data imbalance problem. Subjective and objective experimental results on the challenging datasets show that this method outperforms the state-of-the-arts on unconstrained conditions.

Automated summary

This paper proposes a probability-guided hourglass network to enhance the shape constraints for robust facial landmark detection in unconstrained environments. The method involves a multi-scale pre-processing module for feature extraction, generating coarse localizations and probability maps based on heatmaps, and a probability-based boundary regression method with modified hausdorff distance as the loss function. The experimental results demonstrate that this method outperforms state-of-the-arts on unconstrained conditions.