Pose Invariant Face Recognition Using Linear Pose Transformation in Feature Space
Abstract
Recognizing human face is one of the most important part in biometrics. However, drastic change of facial pose makes it a difficult problem. In this paper, we propose linear pose transformation method in feature space. At first, we extracted features from input face image at each pose. Then, we used extracted features to transform an input pose image into its corresponding frontal pose image. The experimental results show that recognition rate with pose transformation is much better than the result without pose transformation.
Cite
Text
Lee and Kim. "Pose Invariant Face Recognition Using Linear Pose Transformation in Feature Space." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-24837-8_20Markdown
[Lee and Kim. "Pose Invariant Face Recognition Using Linear Pose Transformation in Feature Space." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/lee2004eccv-pose/) doi:10.1007/978-3-540-24837-8_20BibTeX
@inproceedings{lee2004eccv-pose,
title = {{Pose Invariant Face Recognition Using Linear Pose Transformation in Feature Space}},
author = {Lee, Hyung-Soo and Kim, Daijin},
booktitle = {European Conference on Computer Vision},
year = {2004},
pages = {211-220},
doi = {10.1007/978-3-540-24837-8_20},
url = {https://mlanthology.org/eccv/2004/lee2004eccv-pose/}
}