Skip to Main content Skip to Navigation
Conference papers

Towards pose-free tracking of non-rigid face using synthetic data

Abstract : The non-rigid face tracking has been achieved many advances in recent years, but most of empirical experiments are restricted at near-frontal face. This report introduces a robust framework for pose-free tracking of non-rigid face. Our method consists of two phases: training and tracking. In the training phase, a large offline synthesized database is built to train landmark appearance models using linear Support Vector Machine (SVM). In the tracking phase, a two-step approach is proposed: the first step, namely initialization, benefits 2D SIFT matching between the current frame and a set of adaptive keyframes to estimate the rigid parameters. The second step obtains the whole set of parameters (rigid and non-rigid) using a heuristic method via pose-wise SVMs. The combination of these aspects makes our method work robustly up to 90° of vertical axial rotation. Moreover, our method appears to be robust even in the presence of fast movements and tracking losses. Comparing to other published algorithms, our method offers a very good compromise of rigid and non-rigid parameter accuracies. This study gives a promising perspective because of the good results in terms of pose estimation (average error is less than 4° on BUFT dataset) and landmark tracking precision (5.8 pixel error compared to 6.8 of one state-of-the-art method on Talking Face video). These results highlight the potential of using synthetic data to track non-rigid face in unconstrained poses.
Document type :
Conference papers
Complete list of metadatas
Contributor : Frédéric Davesne <>
Submitted on : Monday, August 24, 2015 - 11:06:04 PM
Last modification on : Friday, July 31, 2020 - 10:44:08 AM


  • HAL Id : hal-01186445, version 1


Ngoc-Trung Tran, Fakhr-Eddine Ababsa, Maurice Charbit. Towards pose-free tracking of non-rigid face using synthetic data. 4th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2015), Jan 2015, Lisbon, Portugal. pp.37--44. ⟨hal-01186445⟩



Record views