Advertisement

Evolving Systems

, Volume 10, Issue 2, pp 79–95 | Cite as

New face features to detect multiple faces in complex background

  • Chemesse ennehar BencherietEmail author
Original Paper

Abstract

We propose in this paper a novel method for fast detecting faces even in the presence of constraints such as variation in illumination, human skin tone and facial expression, pose, and background (indoor or outdoor). Our system processes color images in a manner that would decrease the area of a face that must be scanned and for this, a parametric model based on Gaussian mixture models (GMM) applied to segmented regions of skin color. To select, relevant and minimum features from the faces candidates firstly, the variance based Haar-like features are extracted than merged with local binary patterns (LBP) features previously extracted. The resulting fused vectors construct Support Vector Machine database training to achieve a high detection rate. To verify the effectiveness of the proposed method, we carried out a serial of detailed experiments on three difficult face detection datasets (Caltech, BAO and UCD) which contain images featuring both single and multiple faces, presented in a variety of positions and featuring complex backgrounds, both indoor and outdoor. Experimental results have shown that our approach gives better results (91.04%) than those obtained by systems based on primitive Haar-like features and AdaBoost, providing a higher detection rate of 16.51%. Furthermore, the shorter detection time of our method is guaranteed by reducing the dimension of feature vectors and by limited search of faces on only the skin-detected regions and not on the entire image.

Keywords

Face detection Skin color Variance of Haar-like feature Gaussian mixture model (GMM) LBP features SVM 

References

  1. Bai H, Wu J, Liu C (2006) Motion and Haar-like features based vehicles detection. In: 12th International multi-medias modeling conference proceedingsGoogle Scholar
  2. Bencheriet Ch, Oudjani B, Tebikh H (2010) An appropriate color space to improve human skin detection. INFOCOMP J 9(4):1–10Google Scholar
  3. Castrillon M, Hernandez D, Lorenzo J (2011) A study on ear detection and its applications to face detection. In: Conferencia de la Asociacion Espanola para la Inteligencia ArtificialGoogle Scholar
  4. Chai Q, Cheng C, Liu C, Chen H (2013) Vehicle queue length measurement based on a modified local variance and LBP. In: Emerging intelligent computing technology and applications. Springer, Berlin‏, pp 123–128CrossRefGoogle Scholar
  5. Cristianini N, Ricci E (2008) Support vector machines. In: Encyclopedia of algorithms. Springer, Berlin, pp 928–932CrossRefGoogle Scholar
  6. Cuong NK, Park JH, Jung H-Y (2009) Face detection using variance based Haar-like feature and SVM. J World Acad Sci Eng Technol 60:165–168Google Scholar
  7. Fernandes B, Fernández J (2010) Using Haar-like feature classifiers for hand tracking in table top augmented reality. In: XII symposium on virtual and augmented reality, NatalGoogle Scholar
  8. Frischholz R (2012) BAO and CALTECH face database at the face detection homepage. http://www.facedetection.com
  9. Gan G, Cheng J (2011) Pedestrian detection based on HOG-LBP feature. In: Computational intelligence and security (CIS), 2011 seventh international conference, IEEE, pp 1184–1187Google Scholar
  10. Georganas CQ. Petriu ND (2008) Hand gesture recognition using Haar-like features and a stochastic context-free grammar. Instrum Meas IEEE Trans 57:1562–1571CrossRefGoogle Scholar
  11. Guo Z, Zhang L, Zhang D (2010) A completed modeling of local binary pattern operator for texture classification. Image Process IEEE Trans 19(6):1657–1663‏MathSciNetCrossRefzbMATHGoogle Scholar
  12. Hadid A, Ahonen T, Pietikainen M (2004) A discriminative feature space for detecting and recognizing faces. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition (CVPR’04)Google Scholar
  13. Hassanpour R, Shahbahrami A, Wong S (2008) Adaptive Gaussian mixture model for skin color segmentation. World Acad Sci Eng Technol 2(5)Google Scholar
  14. Jagadesh BN, Rao KS, Satyanarayana Ch (2012) A robust skin colour segmentation using bivariate pearson type IIαα (bivariate beta) mixture model. Int J Image Graph Signal Process IJIGSP 4(11)Google Scholar
  15. Jain AK (2010) Data clustering: 50 years beyond K-means. Pattern Recognit Lett 31(8):651–666CrossRefGoogle Scholar
  16. Khammari M, Bencheriet Ch, Tlili Y (2013) Face detection in complex background of color images using mixture Gaussian model and neural network. In: ICSIP’13: international conference on systems and information processing, AlgeriaGoogle Scholar
  17. Khan R, Hanbury A, Stöttinger J, Bais A (2012) Color based skin classification. Pattern Recognit Lett 33(2):157–163CrossRefGoogle Scholar
  18. Kovac J, Peer P, Solin F (2003) A 2D versus 3D color space face detection. In: 4th EURASIP conference on video/image processing and multimedia communication, Croatia, pp 449–454Google Scholar
  19. Lee SK, Kim DG (2005) The feature vector selection for robust multiple face detection. Springer, Berlin, pp 757–764 (LNCS 3746) Google Scholar
  20. Lin L, Li X, Zhou W (2012) Face detection algorithm based on haar and local binary pattern features. J Converg Inf Technol 7:19Google Scholar
  21. Mehieddine S, Chader A (2012) Détection de visages par combinaison de la variance basée sur les caractéristiques de Haar-like et Réseau de neurones PMC, Computer Master’s Thesis, Université 8 Mai 1945, Guelma, AlgeriaGoogle Scholar
  22. Meyer D, Wien FHT (2014) Support vector machines. Theinterface to lib svm in package e1071Google Scholar
  23. Modesto CS, Daniel HS, Javier LN (2012) Combining face and facial feature detectors for face detection performance improvement. Springer, Berlin, pp 82–89 (LNCS 7441) Google Scholar
  24. Monteiro G, Peixoto P, Nunes U (2006) Vision-based pedestrian detection using haar-like features. In: Proc. 6th national festival of robotics, scientific meeting (ROBOTICA), GuimaraesGoogle Scholar
  25. Ojala T, Pietikainen M, Harwood D (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recognit 29(1):51–59CrossRefGoogle Scholar
  26. Paisitkriangkrai S, Shen C, Zhang J (2008) Fast pedestrian detection using a cascade of boosted covariance features. Circuits Syst Video Technol IEEE Trans 18:1140–1151CrossRefGoogle Scholar
  27. Poudel RPK, Zhang JJ, Liu D, Nait-Charif H (2013) Skin color detection using region-based approach. Int J Image Process IJIP 7(4)Google Scholar
  28. Sharma P, Reilly RB (2003) A color face image database for benchmarking of automatic face detection algorithms. In: Region 8 international symposium on video/image processing and multimedia communications—EURASIPGoogle Scholar
  29. Shawe-Taylor J, Cristianini N (2000) Support vector machines. An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge, pp 93–112zbMATHGoogle Scholar
  30. Stanciulescu B, Breheret A, Moutarde F (2007) Introducing new AdaBoost features for real-time vehicle detection. In: Proceedings of COGIS’07 conference on cognitive systems with interactive sensors. Stanford University of California, CaliforniaGoogle Scholar
  31. Steinwart I, Christmann A (2008) Support vector machines. Springer, BerlinzbMATHGoogle Scholar
  32. Taffar M, Benmohammed M (2011) Generic face invariant model for face detection. Image Process Commun Chall 3, Springer, Berlin, AISC 102, pp 43–51CrossRefGoogle Scholar
  33. The Caltech Frontal Face Dataset (1999) Collectedby Markus Weber, California Institute of Technology, USA. http://www.vision.caltech.edu/html-files/archive.html (site official of Caltech dataset)
  34. Vezhnevets V, Sazonov V, Andreeva A (2003) A survey on pixel-based skin color detection techniques. In: Proceedings of the GraphiCon, pp 85–92Google Scholar
  35. Viola P, Jones M (2001a) Robust real-time face detection. Int J Comput Vis 2:747–747Google Scholar
  36. Viola P, Jones M (2001b) Rapid object detection using a boosted cascade of simple features, vol 1. In: Proceedings of the IEEE computer society conference, pp 511–518Google Scholar
  37. Viola P, Jones M (2003) Fast multi-view face detection. Shown as a demo. In: IEEE conference on computer vision and pattern recognition CVPRGoogle Scholar
  38. Wei RT, Chan CS, Yogarajah P, Condell J (2012) A fusion approach for efficient human skin detection. IEEE Trans Ind Inf 8(1):138–147CrossRefGoogle Scholar
  39. Zhang G, Huang X, Li SZ, Wang Y, Wu X (2004) Boosting local binary pattern (LBP)-based face recognition, SINOBIOMETRICS 2004, vol 3338. Springer, Heidelberg, pp 180–187 (LNCS) Google Scholar
  40. Zhang J, Huang K, Yu Y, Tan T (2011) Boosted local structured HOG-LBP for object localization. In: Proceedings of conference on computer vision and pattern recognition, pp 1393–1400Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Department of Computer Science, LAIG LaboratoryUniversité 8 Mai 1945 - GuelmaGuelmaAlgeria

Personalised recommendations