Monday , 16 September 2019
roen

Art. 03 – Vol.23 – No. 2 – 2013

Automatic Human Faces Detection. The Viola-Jones Method

Mihnea Horia Vrejoiu

mihnea@dossv1.ici.ro

National Institute for Research and Development in Informatics – ICI Bucharest

 Anca Mihaela Hotăran

ahotaran@ici.ro

National Institute for Research and Development in Informatics – ICI Bucharest

Abstract: Far from representing an exotic techology, drawn from sci-fi stories or movies, the automatic face detection imperceptibly became already part of our everyday life. In nowadays, almost any user of an average photo camera could see the automatic drawing of a colored rectangle which is framing the faces of human subjects towards which the respective camera objective is pointed to. Few of them asked themselves however how is this possible, and probably fewer know more or less the answer to this question. The present paper aims to present the problematics of automatic face detection, with a brief overview of the specific difficulties, and of the main types of approaches in solving this problem, while detailing – at a level which aims to be as accessible as possible – of one of the most well known and used method, the Viola-Jones one. This paper don’t intend to be an exhaustive survey or a monography on the domain, but only an introduction to this one, easily understandable by most people, while also trying to highlight the beauty and elegance of the innovation, the efficiency and performances brought by the Viola-Jones method.

View full article

Keywords: Face Detection, Computer Vision, Image Analysis, Machine Learning, Haar-like features, Attentional cascade, AdaBoost, classifier, integral image.

REFERENCES

  1. Yang, M.-H.; Kriegman, D. J.; Ahuja, N.: Detecting Faces in Images: A Survey, in IEEE Trans. on PAMI, 24(1), pag. 34-58, 2002
  2. Bucknall, J. M.: How to Find a Face, in PC Plus, Issue 296, July 18th 2010.
  3. Gupta, R.; Saxena, A. K.: Survey of Advanced Face Detection Techniques, in Image Processing, International Journal of Computer Science and Management Research, Vol. 1, Issue 2, ISSN 2278-733X, September 2012, pp. 156-164.
  4. Viola, P.; Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features, in the Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2001.
  5. Viola, P.; Jones, M. J.: Robust Real-Time Face Detection, in the International Journal of Computer Vision (IJCV) 57(2), pag. 137-154, Kluwer Academic Publishers, 2004.
  6. Jones, M.; Viola, P.: Fast multi-view face detection, in Technical report, Mitsubishi Electric Research Laboratories, TR2003-96, 2003.
  7. Lienhart, R.; Maydt, J.: An extended set of Haar-like features for rapid object detection, in Proc. of ICIP, 2002.
  8. Hewitt, R.: Seeing With OpenCV, Part 2: Finding Faces in Images, in SERVO Magazine, T & L Publications Inc., February 2007.
  9. Freund, Y.; Schapire, R. E.: A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting, in Proceedings of EuroCOLT, 1995, pp. 23-37.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.