Vector Boosting for Rotation Invariant Multi-View Face Detection
Abstract
In this paper, we propose a novel tree-structured multiview face detector (MVFD), which adopts the coarse-to-fine strategy to divide the entire face space into smaller and smaller subspaces. For this purpose, a newly extended boosting algorithm named vector boosting is developed to train the predictors for the branching nodes of the tree that have multicomponents outputs as vectors. Our MVFD covers a large range of the face space, say, +/-45/spl deg/ rotation in plane (RIP) and +/-90/spl deg/ rotation off plane (ROP), and achieves high accuracy and amazing speed (about 40 ms per frame on a 320 /spl times/ 240 video sequence) compared with previous published works. As a result, by simply rotating the detector 90/spl deg/, 180/spl deg/ and 270/spl deg/, a rotation invariant (360/spl deg/ RIP) MVFD is implemented that achieves real time performance (11 fps on a 320 /spl times/ 240 video sequence) with high accuracy.
Cite
Text
Huang et al. "Vector Boosting for Rotation Invariant Multi-View Face Detection." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.246Markdown
[Huang et al. "Vector Boosting for Rotation Invariant Multi-View Face Detection." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/huang2005iccv-vector/) doi:10.1109/ICCV.2005.246BibTeX
@inproceedings{huang2005iccv-vector,
title = {{Vector Boosting for Rotation Invariant Multi-View Face Detection}},
author = {Huang, Chang and Ai, Haizhou and Li, Yuan and Lao, Shihong},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2005},
pages = {446-453},
doi = {10.1109/ICCV.2005.246},
url = {https://mlanthology.org/iccv/2005/huang2005iccv-vector/}
}