Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65
-
pISSN : 1598-849X / eISSN : 2383-9945
- https://journal.kci.go.kr/jksci
KJCKorea
Journal Central
Multi-scale face detector using anchor free method
- Journal of The Korea Society of Computer and Information
- Abbr : JKSCI
- 2020, 25(7), pp.47-55
- DOI : 10.9708/jksci.2020.25.07.047
- Publisher : The Korean Society Of Computer And Information
- Research Area : Engineering > Computer Science
- Received : June 11, 2020
- Accepted : July 3, 2020
- Published : July 31, 2020
Dong-Ryeol Lee 1, Kim, yoon 1
1강원대학교
Accredited
ABSTRACT
In this paper, we propose one stage multi-scale face detector based Fully Convolution Network using anchor free method. Recently almost all state-of-the-art face detectors which predict location of faces using anchor-based methods rely on pre-defined anchor boxes. However this face detectors need to hyper-parameters and additional computation in training. The key idea of the proposed method is to eliminate hyper-parameters and additional computation using anchor free method. To do this, we apply two ideas. First, by eliminating the pre-defined set of anchor boxes, we avoid the additional computation and hyper-parameters related to anchor boxes. Second, our detector predicts location of faces using multi-feature maps to reduce foreground/background imbalance issue. Through Quantitative evaluation, the performance of the proposed method is evaluated and analyzed. Experimental results on the FDDB dataset demonstrate the effective of our proposed method.
Statistics
-
309 Viewed
-
112 Downloaded
Tools
Issue List
Citation status
* References for papers published after 2023 are currently being built.
[confproc]
J. Li
/ 2011
/ Face detection using surf cascade
/ Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on
/ IEEE
: 2183~2190
[journal]
K.-K. Sung
/ 1998
/ Example-based learning for viewbased human face detection
/ IEEE Transactions on pattern analysis and machine intelligence
20(1)
: 39~51
[journal]
P. Viola
/ 2004
/ Robust real-time face detection
/ International journal of computer vision
57(2)
: 137~154
[confproc]
X. Zhu
/ 2012
/ Face detection, pose estimation,and landmark localization in the wild
/ Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
/ IEEE
: 2879~2886
[confproc]
Ren, S,
/ 2015
/ Faster r-cnn: Towards real-time object detection with region proposal networks
/ Advances in neural information processing systems
: 91~99
[confproc]
Redmon, J.
/ 2016
/ You only look once : Unified, real-time object detection
/ Proceedings of the IEEE conference on computer vision and pattern recognition
: 779~788
[confproc]
Liu, W.
/ 2016
/ Ssd: Single shot multibox detector
/ European conference on computer vision
/ Springer
: 21~37
[confproc]
Lin, T. Y.
/ 2017
/ Feature pyramid networks for object detection
/ Proceedings of the IEEE conference on computer vision and pattern recognition
: 2117~2125
[confproc]
Tsung-Yi Lin
/ 2017
/ Focal loss for dense object detection
/ Proc. IEEE Conf. Comp. Vis. Patt. Recogn
: 2980~2988
[confproc]
He, K.
/ 2017
/ Mask r-cnn
/ Proceedings of the IEEE international conference on computer vision
: 2961~2969
[confproc]
S. Yang
/ 2016
/ Wider face : A face detection benchmark
/ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
: 5525~5533
[confproc]
H. Jiang
/ 2017
/ Face detection with the faster r-cnn
/ Automatic Face & Gesture Recognition (FG 2017), 2017 12th IEEE International Conference on
/ IEEE
: 650~657
[other]
Wang, H.
/ 2017
/ Face r-cnn
/ arXiv preprint arXiv : 1706. 01061
[confproc]
Yang, W.
/ 2018
/ Real-time face detection based on YOLO
/ 2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)
/ IEEE
: 221~224
[confproc]
Tang, X.
/ 2018
/ Pyramidbox : A context-assisted single shot face detector
/ Proceedings of the European Conference on Computer Vision (ECCV)
: 797~813
[other]
Deng, J.
/ 2019
/ Retinaface: Single-stage dense face localisation in the wild
/ arXiv preprint arXiv:1905.00641
[confproc]
Cakiroglu, O.
/ 2019
/ Design of a Deep Face Detector by Mask R-CNN
/ 2019 27th Signal Processing and Communications Applications Conference (SIU)
/ IEEE
: 1~4
[confproc]
Li, J.
/ 2019
/ DSFD: dual shot face detector
/ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
: 5060~5069
[confproc]
Najibi, M.
/ 2017
/ Ssh : Single stage headless face detector
/ Proceedings of the IEEE International Conference on Computer Vision
: 4875~4884
[confproc]
Zhang, S.
/ 2017
/ S3fd : Single shot scale-invariant face detector
/ Proceedings of the IEEE International Conference on Computer Vision
: 192~201
[confproc]
Tian, Z.
/ 2019
/ Fcos : Fully convolutional one-stage object detection
/ Proceedings of the IEEE International Conference on Computer Vision
: 9627~9636
[confproc]
Wang, C.
/ 2018
/ Anchor Free Network for Multi-Scale Face Detection
/ 2018 24th International Conference on Pattern Recognition (ICPR)
/ IEEE
: 1554~1559
[other]
L. Huang
/ 2015
/ Densebox : Unifying landmark localization with end to end object detection
/ arXiv preprint arXiv : 1509. 04874
[confproc]
J. Yu
/ 2016
/ Unitbox: An advanced object detection network
/ Proc. ACM Multimedia
: 516~520
[other]
Xu, Y.
/ 2019
/ CenterFace:Joint Face Detection and Alignment Using Face as Point
/ arXiv preprint arXiv:1911.03599
[journal]
Yotam Abramson
/ 2007
/ Yet even faster (yef) real-time object detection
/ International Journal of Intelligent Systems Technologies and Applications
2(2-3)
: 102~112
[confproc]
P. Hu
/ 2017
/ Finding tiny faces
/ Proc. CVPR
: 1522~1530
[confproc]
Zhang, Z.
/ 2020
/ Robust face detection via learning small faces on hard images
/ The IEEE Winter Conference on Applications of Computer Vision
: 1361~1370
[confproc]
Yu Chen
/ 2017
/ PoseNet: A structure-aware convolutional network for human pose estimation
/ Proc. IEEE Int. Conf. Comp. Vis
[confproc]
Sun, K.
/ 2019
/ Deep high-resolution representation learning for human pose estimation
/ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
: 5693~5703
[other]
K. Simonyan
/ 2014
/ Very deep convolutional networks for large-scale image recognition
/ arXiv:1409.1556
[confproc]
Lokesh Boominathan
/ 2016
/ Crowdnet: A deep convolutional network for dense crowd counting
/ Proc. ACM Int. Conf. Multimedia
/ ACM
: 640~644
[other]
Sam, D. B.
/ 2019
/ Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
/ arXiv preprint arXiv : 1906. 07538
[confproc]
Sindagi, V. A.
/ 2019
/ Inverse attention guided deep crowd counting network
/ 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
/ IEEE
: 1~8
[confproc]
Jonathan Long
/ 2015
/ Fully convolutional networks for semantic segmentation
/ Proc. IEEE Conf. Comp. Vis. Patt. Recogn
: 3431~3440
[journal]
Zhang, Kaipeng
/ 2016
/ Joint face detection and alignment using multitask cascaded convolutional networks
/ IEEE Signal Processing Letters
23(10)
: 1499~1503
[other]
Huang, Gary B.
/ 2008
/ Labeled faces in the wild: A database forstudying face recognition in unconstrained environments
[report]
Jain, Vidit
/ 2010
/ Fddb: A benchmark for face detection in unconstrained settings
/ UMass Amherst
[confproc]
B. Alexe
/ 2012
/ Measuring the objectness of image windows
/ Proceedings of the TPAMI
[confproc]
J.R. Uijlings
/ 2013
/ Selective search for object recognition
/ Proceedings of the IJCV
[journal]
Liu, Li
/ 2020
/ Deep learning for generic object detection: A survey
/ International journal of computer vision
128(2)
: 261~318
[journal]
Zhang, Shifeng
/ 2020
/ Refineface: Refinement neural network for high performance face detection
/ IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper was written with support from the National Research Foundation of Korea.