논문KCI 등재
앵커 프리 방법을 이용한 다중 크기 얼굴 검출기
Multi-scale face detector using anchor free method
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
주제분류컴퓨터학
초록
본 논문에서는 앵커 프리 방법을 이용한 FCN(Fully Convolutional Network)기반의 1단계 다중 크기 얼굴 검출기를 제안한다. 최근 대부분의 연구들은 사전 정의된 앵커를 사용하여 얼굴이 있을만한 위치를 예측한다. 그러나 사전 정의 앵커를 이용함으로써 학습 시 하이퍼 파라미터의 설정과 추가적인 계산이 필요하다. 제안하는 방법의 핵심 아이디어는 앵커 프리 방법을 사용하여 하이퍼 파라미터를 없애고 여러 개의 특징 맵을 사용함으로써 클래스 내 불균형 문제를 완화하는것이다. 이 방법들은 다음과 같은 효과가 있다. 첫째로 사전정의 앵커를 없앰으로써 앵커와 관련된 하이퍼 파라미터와 추가적인 계산을 피한다. 둘째로 클래스 내 불균형을 완화하기 위해 여러개의 특징 맵으로부터 얼굴을 예측한다. 정량적 평가를 통해 제안하는 방법에 따른 검출 성능을평가 및 분석한다. FDDB(Face Detection Dataset & Benchmark) 데이터 셋의 실험 결과에서 제안하는 방법이 효과가 있음을 증명했다.
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.
참고문헌 (42)
- J. Li, "Face detection using surf cascade", Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, pp.2183~2190 (2011), IEEE
- K.-K. Sung, "Example-based learning for viewbased human face detection", IEEE Transactions on pattern analysis and machine intelligence, 20(1), pp.39~51 (1998)
- P. Viola, "Robust real-time face detection", International journal of computer vision, 57(2), pp.137~154 (2004)
- X. Zhu, "Face detection, pose estimation,and landmark localization in the wild", Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp.2879~2886 (2012), IEEE
- Ren, S,, "Faster r-cnn: Towards real-time object detection with region proposal networks", Advances in neural information processing systems, pp.91~99 (2015)
- Redmon, J., "You only look once : Unified, real-time object detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779~788 (2016)
- Liu, W., "Ssd: Single shot multibox detector", European conference on computer vision, pp.21~37 (2016), Springer
- Lin, T. Y., "Feature pyramid networks for object detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2117~2125 (2017)
- Tsung-Yi Lin, "Focal loss for dense object detection", Proc. IEEE Conf. Comp. Vis. Patt. Recogn, pp.2980~2988 (2017)
- He, K., "Mask r-cnn", Proceedings of the IEEE international conference on computer vision, pp.2961~2969 (2017)
- S. Yang, "Wider face : A face detection benchmark", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5525~5533 (2016)
- H. Jiang, "Face detection with the faster r-cnn", Automatic Face & Gesture Recognition (FG 2017), 2017 12th IEEE International Conference on, pp.650~657 (2017), IEEE
- Wang, H., "Face r-cnn", arXiv preprint arXiv : 1706. 01061, ~ (2017)
- Yang, W., "Real-time face detection based on YOLO", 2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII), pp.221~224 (2018), IEEE
- Tang, X., "Pyramidbox : A context-assisted single shot face detector", Proceedings of the European Conference on Computer Vision (ECCV), pp.797~813 (2018)
- Deng, J., "Retinaface: Single-stage dense face localisation in the wild", arXiv preprint arXiv:1905.00641, ~ (2019)
- Cakiroglu, O., "Design of a Deep Face Detector by Mask R-CNN", 2019 27th Signal Processing and Communications Applications Conference (SIU), pp.1~4 (2019), IEEE
- Li, J., "DSFD: dual shot face detector", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5060~5069 (2019)
- Najibi, M., "Ssh : Single stage headless face detector", Proceedings of the IEEE International Conference on Computer Vision, pp.4875~4884 (2017)
- Zhang, S., "S3fd : Single shot scale-invariant face detector", Proceedings of the IEEE International Conference on Computer Vision, pp.192~201 (2017)
- Tian, Z., "Fcos : Fully convolutional one-stage object detection", Proceedings of the IEEE International Conference on Computer Vision, pp.9627~9636 (2019)
- Wang, C., "Anchor Free Network for Multi-Scale Face Detection", 2018 24th International Conference on Pattern Recognition (ICPR), pp.1554~1559 (2018), IEEE
- L. Huang, "Densebox : Unifying landmark localization with end to end object detection", arXiv preprint arXiv : 1509. 04874, ~ (2015)
- J. Yu, "Unitbox: An advanced object detection network", Proc. ACM Multimedia, pp.516~520 (2016)
- Xu, Y., "CenterFace:Joint Face Detection and Alignment Using Face as Point", arXiv preprint arXiv:1911.03599, ~ (2019)
- Yotam Abramson, "Yet even faster (yef) real-time object detection", International Journal of Intelligent Systems Technologies and Applications, 2(2-3), pp.102~112 (2007)
- P. Hu, "Finding tiny faces", Proc. CVPR, pp.1522~1530 (2017)
- Zhang, Z., "Robust face detection via learning small faces on hard images", The IEEE Winter Conference on Applications of Computer Vision, pp.1361~1370 (2020)
- Yu Chen, "PoseNet: A structure-aware convolutional network for human pose estimation", Proc. IEEE Int. Conf. Comp. Vis (2017)
- Sun, K., "Deep high-resolution representation learning for human pose estimation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5693~5703 (2019)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv:1409.1556, ~ (2014)
- Lokesh Boominathan, "Crowdnet: A deep convolutional network for dense crowd counting", Proc. ACM Int. Conf. Multimedia, pp.640~644 (2016), ACM
- Sam, D. B., "Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection", arXiv preprint arXiv : 1906. 07538, ~ (2019)
- Sindagi, V. A., "Inverse attention guided deep crowd counting network", 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.1~8 (2019), IEEE
- Jonathan Long, "Fully convolutional networks for semantic segmentation", Proc. IEEE Conf. Comp. Vis. Patt. Recogn, pp.3431~3440 (2015)
- Zhang, Kaipeng, "Joint face detection and alignment using multitask cascaded convolutional networks", IEEE Signal Processing Letters, 23(10), pp.1499~1503 (2016)
- Huang, Gary B., "Labeled faces in the wild: A database forstudying face recognition in unconstrained environments", ~ (2008)
- Fddb: A benchmark for face detection in unconstrained settings, "Jain, Vidit", UMass Amherst, ~ (2010)
- B. Alexe, "Measuring the objectness of image windows", Proceedings of the TPAMI (2012)
- J.R. Uijlings, "Selective search for object recognition", Proceedings of the IJCV (2013)
- Liu, Li, "Deep learning for generic object detection: A survey", International journal of computer vision, 128(2), pp.261~318 (2020)
- Zhang, Shifeng, "Refineface: Refinement neural network for high performance face detection", IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)
관련 논문AI추천
다중크기와 다중객체의 실시간 얼굴 검출과 머리 자세 추정을 위한 심층 신경망권인소, 안병태, 최동걸한국로봇학회 · 로봇학회 논문지2017 · 제12권 제3호학습기반 효율적인 얼굴 검출 시스템 설계김완태, 김현식, 박병준(사)디지털산업정보학회 · (사)디지털산업정보학회 논문지2023 · 제19권 제3호경량 및 효율적인 네트워크를 활용한 향상된 얼굴 랜드마크 검출 연구홍성혁중소기업융합학회 · 산업과 과학2025 · 제4권 제1호얼굴 인식률 향상을 위한 멀티 블록 방식의딥러닝 구조에 관한 연구김홍직, 라승탁, 이승호한국전기전자학회 · 전기전자학회논문지2018 · 제22권 제4호얼굴이미지열 예측 자기주도학습을 통한 자동표정인식 연구김수균, 윤여찬한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2022 · 제27권 제9호눈 주변영역의 명암분포를 이용한 얼굴탐지김계영, 박주철, 황대동한국정보처리학회 · 정보처리학회 논문지2009 · 제16권 제6호