@article{ART002778782},
author={Kyung-Shik Jang},
title={Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2021},
volume={26},
number={11},
pages={85-92},
doi={10.9708/jksci.2021.26.11.085}
TY - JOUR
AU - Kyung-Shik Jang
TI - Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform
JO - Journal of The Korea Society of Computer and Information
PY - 2021
VL - 26
IS - 11
PB - The Korean Society Of Computer And Information
SP - 85
EP - 92
SN - 1598-849X
AB - In this paper, a method for effectively detecting rotated face and rotation angle regardless of the rotation angle is proposed. Rotated face detection is a challenging task, due to the large variation in facial appearance. In the proposed polar coordinate transformation, the spatial information of the facial components is maintained regardless of the rotation angle, so there is no variation in facial appearance due to rotation. Accordingly, features such as HOG, which are used for frontal face detection without rotation but have rotation-sensitive characteristics, can be effectively used in detecting rotated face. Only the training data in the frontal face is needed. The HOG feature obtained from the polar coordinate transformed images is learned using SVM and rotated faces are detected. Experiments on 3600 rotated face images show a rotation angle detection rate of 97.94%. Furthermore, the positions and rotation angles of the rotated faces are accurately detected from images with a background including multiple rotated faces.
KW - Rotated face detection;Polar coordinate transform;Learning;HOG;SVM
DO - 10.9708/jksci.2021.26.11.085
ER -
Kyung-Shik Jang. (2021). Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform. Journal of The Korea Society of Computer and Information, 26(11), 85-92.
Kyung-Shik Jang. 2021, "Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform", Journal of The Korea Society of Computer and Information, vol.26, no.11 pp.85-92. Available from: doi:10.9708/jksci.2021.26.11.085
Kyung-Shik Jang "Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform" Journal of The Korea Society of Computer and Information 26.11 pp.85-92 (2021) : 85.
Kyung-Shik Jang. Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform. 2021; 26(11), 85-92. Available from: doi:10.9708/jksci.2021.26.11.085
Kyung-Shik Jang. "Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform" Journal of The Korea Society of Computer and Information 26, no.11 (2021) : 85-92.doi: 10.9708/jksci.2021.26.11.085
Kyung-Shik Jang. Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform. Journal of The Korea Society of Computer and Information, 26(11), 85-92. doi: 10.9708/jksci.2021.26.11.085
Kyung-Shik Jang. Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform. Journal of The Korea Society of Computer and Information. 2021; 26(11) 85-92. doi: 10.9708/jksci.2021.26.11.085
Kyung-Shik Jang. Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform. 2021; 26(11), 85-92. Available from: doi:10.9708/jksci.2021.26.11.085
Kyung-Shik Jang. "Rotation Invariant Face Detection Using HOG and Polar Coordinate Transform" Journal of The Korea Society of Computer and Information 26, no.11 (2021) : 85-92.doi: 10.9708/jksci.2021.26.11.085