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

Improved Face Detection Algorithm Using Face Verification

얼굴 검증을 이용한 개선된 얼굴 검출

  • Oh, Jeong-su (Department of Display Engineering, Pukyong National University)
  • Received : 2018.06.29
  • Accepted : 2018.08.13
  • Published : 2018.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Viola & Jones's face detection algorithm is a typical face detection algorithm and shows excellent face detection performance. However, the Viola & Jones's algorithm in images including many faces generates undetected faces and wrong detected faces, such as false faces and duplicate detected faces, due to face diversity. This paper proposes an improved face detection algorithm using a face verification algorithm that eliminates the false detected faces generated from the Viola & Jones's algorithm. The proposed face verification algorithm verifies whether the detected face is valid by evaluating its size, its skin color in the designated area, its edges generated from eyes and mouth, and its duplicate detection. In the face verification experiment of 658 face images detected by the Viola & Jones's algorithm, the proposed face verification algorithm shows that all the face images created in the real person are verified.

Viola & Jones의 얼굴 검출 알고리즘은 대표적인 얼굴 검출 알고리즘으로 매우 우수한 얼굴 검출 성능을 보인다. 그러나 많은 얼굴을 포함하는 영상들을 대상으로 한 Viola & Jones 알고리즘은 얼굴의 다양성으로 미검출 얼굴들, 가짜 얼굴들과 중복 검출된 얼굴들 같은 잘못 검출된 얼굴들을 발생시킨다. 본 논문은 Viola & Jones 알고리즘에서 생성된 잘못 검출된 얼굴들을 제거하는 얼굴 검증 알고리즘을 이용한 개선된 얼굴 검출 알고리즘을 제안한다. 제안된 얼굴 검증 알고리즘은 검출된 얼굴들에 대한 크기, 지정된 영역의 피부색, 눈과 입에서 발생된 에지, 중복 검출을 평가하여 얼굴이 유효한지를 확인한다. Viola & Jones 알고리즘에 의해 검출된 658개의 얼굴 영상들을 대상으로 한 얼굴 검증 실험에서 제안된 얼굴 검증 알고리즘은 실제 사람들에 의해 생성된 모든 얼굴 영상들을 검증하는 것을 보여준다.

Keywords

References

  1. D. Chai, and K. N. Ngan, "Face segmentation using skin-color map in videophone applications," IEEE Trans. on Circuits and Systems for Video Technology, vol. 9, no. 4, pp. 551-564, Jun. 1999. https://doi.org/10.1109/76.767122
  2. H. Li, Z. Lin, X. Shen, J. Brandt, and G. Hua, "A convolutional neural network cascade for face detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 5325-5334, 2015.
  3. P. Viola, and M. J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Kauai, pp. 511-518, 2001.
  4. J. S. Oh, and H. Hoon, "Performance Analysis of Viola & Jones Face Detection Algorithm," Proceedings of Conference on Korea Information and Communication Engineering, vol. 19, no. 9, pp. 238-241, 2018.
  5. R. Lienhart, and J. Maydt, "An extended set of haar-like features for rapid object detection," Proceedings of International Conference on Image Processing, Rochester, pp. 900-903, 2002.
  6. H. Y. Han, Introduction to Pattern Recognition, Hanbit Academy, Inc., Seoul, 2015.
  7. MathWorks, vision.CascadeObjectDetector System object : Properties [Internet]. Available https://kr.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-system-object.html.
  8. W. Y. Kim, Y. H. Seo and D. W. Kim, "A Fast and Accurate Face Detection and Tracking Method by using Depth Information and color information," Journal of The Korea Institute of Information and Communication Engineering, vol. 16, no. 9, pp.1825-1838, Sep. 2012. https://doi.org/10.6109/jkiice.2012.16.9.1825

Cited by

  1. 얼굴 검출을 위한 피부색 추출 과정에서 피부색 손실 영역 개선에 관한 연구 vol.10, pp.5, 2018, https://doi.org/10.15207/jkcs.2019.10.5.001
  2. 가변 변수와 검증을 이용한 개선된 얼굴 요소 검출 vol.24, pp.3, 2020, https://doi.org/10.6109/jkiice.2020.24.3.378