Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Face Detection Method based Fusion RetinaNet using RGB-D Image

RGB-D 영상을 이용한 Fusion RetinaNet 기반 얼굴 검출 방법

  • Nam, Eun-Jeong (Department of Computer Engineering, Korea University of Technology and Education) ;
  • Nam, Chung-Hyeon (Department of Computer Engineering, Korea University of Technology and Education) ;
  • Jang, Kyung-Sik (Department of Computer Engineering, Korea University of Technology and Education)
  • Received : 2021.11.28
  • Accepted : 2022.03.11
  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The face detection task of detecting a person's face in an image is used as a preprocess or core process in various image processing-based applications. The neural network models, which have recently been performing well with the development of deep learning, are dependent on 2D images, so if noise occurs in the image, such as poor camera quality or pool focus of the face, the face may not be detected properly. In this paper, we propose a face detection method that uses depth information together to reduce the dependence of 2D images. The proposed model was trained after generating and preprocessing depth information in advance using face detection dataset, and as a result, it was confirmed that the FRN model was 89.16%, which was about 1.2% better than the RetinaNet model, which showed 87.95%.

영상 내 사람의 얼굴을 검출하는 얼굴 검출 작업은 다양한 영상 처리 어플리케이션 내 전처리 또는 핵심 과정으로 사용되고 있다. 최근 딥러닝 기술의 발달로 높은 성능을 내고 있는 신경망 모델은 2차원 영상에 의존적이며, 카메라 품질이 떨어지거나, 얼굴의 초점을 제대로 잡지 못하는 등의 영상 내 노이즈가 발생할 경우, 제대로 얼굴을 검출하지 못할 수 있다. 본 논문에서는 2차원 영상의 의존성을 낮추기 위해 깊이 정보를 함께 사용하는 얼굴 검출 방법에 대해 제안한다. 제안하는 모델은 기존 공개된 얼굴 검출 데이터 셋을 이용하여 깊이 정보를 사전에 생성 및 전처리 과정을 거친 후 학습하였으며, 그 결과, 평균 정밀도 기준 FRN 모델은 89.16%로 87.95%의 성능을 보인 RetinaNet 모델보다 약 1.2% 정도의 성능이 향상되었음을 확인하였다.

Keywords

Acknowledgement

This results was supported by "Regional Innovation Strategy(RIS)" through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(MOE)(2021RIS-004)

References

  1. C. H. Nam, E. J. Nam and K. S. Jang, "Mask Wearning Detection System using Deep Learning," Journal of the Korea Institute of Information and Communication Engineering, vol. 25, no. 1, pp. 44-49, Jan. 2021. https://doi.org/10.6109/JKIICE.2021.25.1.44
  2. T. Y. Lin, P. Goyal, R. Girshick, K. He and P. Dollar, "Focal Loss for Dense Object Detection," in Proceeding of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, pp. 936-944, 2017.
  3. Y. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once," in Proceeding of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 779-788, 2016.
  4. T. Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan and Serge Belongie, "Feature Pyramid Networks for Object Detection," in Proceeding of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, pp. 936-944, 2017.
  5. R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceeding of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Ohio, pp. 580-587, 2014.
  6. Y. Redmon, S. Divvala, R. Girshick and A. Farhadi, "Fast R-CNN," in Proceeding of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Las Condes, pp. 1440-1448, 2015.
  7. S. Ren, H. He, R. Girshick, J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in Proceeding of the 28th International Conference on Neural Information Processing Systems, Montreal, pp. 91-99, 2015.
  8. R. Ranftl, K. Lasinger, D. Hafner, K. Schindler and V. Koltun, "Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer," arXiv 2019, arXiv:1907.01341[Online].
  9. S. Yang, P. Luo, C. C. Loy and Xiaoou Tang, "WIDER FACE: A Face Detection Benchmark," in Proceeding of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 5525-5533, 2016.