Enhanced Face Detection Based on Haar-Like and MB-LBP Features

  • Tarek Dandashy
  • Moustapha El Hassan
  • Amine Bitar
Keywords: Face Detection, Machine Learning, Boosting, Real-Time Systems


The effective real-time face detection framework proposed by Viola and Jones gained much popularity due its computational efficiency and its simplicity. A notable variant replaces the original Haar-like features with MB-LBP (Multi-Block Local Binary Pattern) which are defined by the local binary pattern operator, both detector types are integrated into the OpenCV library. However, each descriptor and its evaluation method has its own set of strengths and setbacks. In this paper, an enhanced two-layer face detector composed of both Haar-like and MB-LBP features is presented. Haar-like features are employed as a coarse filter but with a new evaluation involving dual threshold. The already established MB-LBPs are arranged as the fine filter of the detector. The Gentle AdaBoost learning algorithm is deployed for the training of the proposed detector to reach the classification and performance potential. Experiments show that in the early stages of classification, Haar features with dual threshold are more discriminative than MB-LBP and original Haar-like features with respect to number of features required and computation. Benchmarking the proposed detector demonstrate overall 12% higher detection rate at 17% false alarm over using MB-LBP features singly while performing with ×3 speedup.


[1] Viola, P. & Jones, M. J. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2), 137-154.
[2] Zhang, L., Chu, R., & Xiang, S., et al. (2007). Face detection based on multi-block lbp representation. In Proc. International Conference on Biometrics, pp. 11-18.
[3] Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119-139.
[4] Amjad, A., Griffiths, A., & Patwary, M. N. (2012). Multiple face detection algorithm using colour skin modeling. IET Image Processing, 6(8), 1093-1101.
[5] Ban, Y., Kim, S. K., & Kim, S., et al. (2014). Face detection based on skin color likelihood. Pattern Recognition, 47(4), 1573-1585.
[6] Dhivakar, B., Sridevi, C., & Selvakumar, S., et al. (2015). Face detection and recognition using skin color. In Proc. Third International Conference on Signal Processing, Communication and Networking (ICSCN), pp. 1-7.
[7] Wu, B., Ai, H., & Huang, C., et al. (2004). Fast rotation invariant multi-view face detection based on real adaboost. In Proc. Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 79-84.
[8] Huang, C., Ai, H., & Li, Y., et al. (2007). High-performance rotation invariant multi view face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(4), 671-686.
[9] Chen, D., Ren, S., & Wei, Y., et al. (2014). Joint cascade face detection and alignment. In Proc. European Conference on Computer Vision, pp. 109-122.
[10] Ren, S., Cao, X., & Wei, Y., et al. (2014). Face alignment at 3000 fps via regressing local binary features. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1685-1692.
[11] Overett, G. & Petersson, L. (2007). Improved response modelling on weak classifiers for boosting. In Proc. IEEE International Conference on Robotics and Automation, pp. 3799-3804.
[12] Li, Z., Wang, W., & Liu,X., et al. (2015). An efficient multi-threshold adaboost approach to detecting faces in images. Multimedia Tools and Applications, 74(3), 885-901.
[13] El Kaddouhi, S., Saaidi A., & Abarkan, M. (2017). Eye detection based on the viola-jones method and corners points. Multimedia Tools and Applications, 76(21), 23077-23097.
[14] Ma, C., Trung,N. T., & Uchiyama, H., et al. (2017). Adapting local features for face detection in thermal image. Sensors, 17(12), 2741.
[15] Tianyu, L., Fei, L., & Rui, W. (2018). Human face gender identification system based on MB-LBP. In Proc. Chinese Control and Decision Conference (CCDC), pp. 1721-1725.
[16] Liao, S., Jain, A. K., & Li, S. Z. (2016). A fast and accurate unconstrained face detector. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 211-223.
[17] Zhang, C. & Zhang, Z. (2014). Improving multiview face detection with multi-task deep convolutional neural networks. In Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1036-1041.
[18] Wu, S., Kan, M., & He, Z. (2017). Funnel-structured cascade for multi-view face detection with alignment-awareness. Neurocomputing, 221, 138-145.
[19] Friedman, J., Hastie, T., & Tibshirani, R. (2000). Additive logistic regression: a statistical view of boosting. The Annals of Statistics, 28(2), 337-407.
How to Cite
Tarek Dandashy, Moustapha El Hassan, & Amine Bitar. (2019). Enhanced Face Detection Based on Haar-Like and MB-LBP Features. International Journal of Engineering and Management Research, 9(4), 117-124. Retrieved from http://www.ijemr.net/ojs/index.php/ojs/article/view/68