Document Type : Original/Review Paper

Authors

1 Department of Computer, Faculty of Engineering, Islamic Azad University, Qom Branch, Qom 3749113191, Iran.

2 Department of Telecommunications, Kashan Branch, Islamic Azad University, Kashan, Iran.

Abstract

Multi-view face detection in open environments is a challenging task, due to the wide variations in illumination, face appearances and occlusion. In this paper, a robust method for multi-view face detection in open environments, using a combination of Gabor features and neural networks, is presented. Firstly, the effect of changing the Gabor filter parameters (orientation, frequency, standard deviation, aspect ratio and phase offset) for an image is analysed, secondly, the range of Gabor filter parameter values is determined and finally, the best values for these parameters are specified. A multilayer feedforward neural network with a back-propagation algorithm is used as a classifier. The input vector is obtained by convolving the input image and a Gabor filter, with both the angle and frequency values equal to π/2. The proposed algorithm is tested on 1,484 image samples with simple and complex backgrounds. The experimental results show that the proposed detector achieves great detection accuracy, by comparing it with several popular face-detection algorithms, such as OpenCV’s Viola-Jones detector.

Keywords

[1] Sarkara, R., Bakshi, S. & Sa, P.K. (2012). A real-time model for multiple human face tracking from low-resolution surveillance videos. Procedia Technology, vol. 6, pp. 1004-1010.
 
[2] Jones, M. J. & Viola, P. (2004). Robust real-time face detection. International Journal of Computer Vision, vol.57, no. 2, pp. 137-154. 
 
[3] Zhang T., et al. (2018). Fast and robust occluded face detection in ATM surveillance. Pattern Recognition Letters, vol. 107, pp. 33-40.
 
[4] Tsai, Y. H., Lee,Y. C., Ding, J.J., Chang. R.Y. & Hsu, M.C. (2018). Robust in-plane and out-of-plane face detection algorithm using frontal face detector and symmetry extension. Image and Vision Computing, vol 78, pp.  26-41.
[5] Ghazali K.H.B., et al. (2012) . An innovative face detection based on YCgCr color space. Physics Procedia, vol. 25, pp.  2116-2124.
 
[6] Sun, X. , Wu, P. & Hoi, S.C.H.  (2017). Face detection using deep learning: An improved faster RCNN approach. Neurocomputing, vol. 299, pp.  42-50. 
 
[7] Zeng, D., Zhao, F., Ge, S. & Shen, W. (2019). Fast cascade face detection with pyramid network. Pattern Recognition Letters, vol 119, pp.  180-186. 
 
[8] Chen, J. et al. (2004). Novel face detection method based on Gabor features. In: Li, S.Z., Lai, J., Tan, T., Feng, G., Wang, Y. (Eds), Advances in Biometric Person Authentication. Springer, Berlin, pp. 90-99.
 
[9] Huang, L. L., Shimizu, A. & Kobatake, H.  (2005). Robust face detection using Gabor filter features. Pattern Recognition Letters, vol. 26, no. 11, pp. 1641-1649.
 
[10] Kwolek, B. (2005). Face detection using convolutional neural networks and Gabor filters. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (Eds), Artificial Neural Networks: Biological Inspirations. Springer, Berlin, pp. 551-556.
 
[11] Sahoolizadeh, H., et al. (2008). Face detection using Gabor wavelets and neural networks. International Journal of Electrical and Computer Engineering, vol. 2, pp. 1862-1864.
 
[12] Xiaohua, L., et al. (2009). Face detection using simplified Gabor features and hierarchical regions in a cascade of classifiers. Pattern Recognition Letters, vol. 30 no. 8 , pp. 717-728.
 
[13] FERET image database (2003), Available: http://www.nist.gov/itl/iad/ig/colorferet.cfm.
 
[14] Markus Weber image database (1999), Available: http://www.vision.caltech.edu/Image_Datasets/faces/faces.tar.
 
[15] OpenCv's Viola-Jones algorithm, Available:https://docs.opencv.org/3.4.1/d7/d8b/tutorial_py_face_detection.html.
 
[16] Oh, J., Choi, S. , Kim, C. , Cho, J.  & Choi, C.  (2013). Selective generation of Gabor features for fast face recognition on mobile devices. Pattern Recognition Letters, vol. 34, no. 13, pp.1540-1547.
 
[17] Xu Y., et al. (2016). Image intelligent detection based on the gabor wavelet and the neural network. Symmetry, vol. 8, pp. 243-253.
[18] Theodoridis, S. & Chellappa, R. (2014). Academic press library in signal processing image and video compression and multimedia. Academic Press,
[19] Jones, J. P. & Palmer, L.A. (1987). An evaluation of the two-dimensional Gabor filter model of simple receptive rields in cat striate cortex. Journal of Neurophysiology, vol. 58  no. 6, pp. 1233-1258.
[20] Kaushal, A. & Raina, J. P. (2010). Face detection using neural network & Gabor wavelet transform. International Journal of Computer Science and Technology, vol. 1, pp. 58-63.
[21] Grigorescu, S. E., Petkov, N. & Kruizinga, P. (2002). Comparison of texture features based on Gabor filters. IEEE Transactions on Image Processing, vol. 11 no. 10, pp. 1160-1167.
[22] Roger, J. & Easton, L.(2010). Fourier methods in imaging. Rochester, John Wiley and Sons.
[23] Amayeh, G., Tavakkoli, A. & Bebis, G. (2009). Accurate and efficient computation of Gabor features in real-time applications, in: Bebis, G. (Eds.) Advances in Visual Computing, Springer Heidelberg, Berlin, pp. 243-252.
[24] Gu, W. , et al. (2012). Facial expression recognition using radial encoding of local Gaborfeatures and classifier synthesis. Pattern Recognition , vol. 45, no. 1, pp. 80-91.
[25] Boulgouris, N. V., Plataniotis, K.N. & Tzanakou E.M. (2009).  Biometric: theory method and applications. John Wiley & Sons.
[26] Serrano, A., de Diego, I.M., Conde, C. & Cabello, E. (2011). Analysis of variance of Gabor filter banks parameters for optimal face recognition. Pattern Recognition Letters, vol. 32, no. 15, pp. 1998-2008.
[27] Mavaddati, S. (2019). A novel face detection method based on over-complete incoherent dictionary learning. Journal of AI and Data Mining, vol. 7, no.2, pp.263-278.
[28] Meshgini S. et al. (2013). Face recognition using Gabor-based direct linear discriminant analysis and support vector machine. Computers and Electrical Engineering, vol. 39, no. 3, pp. 727-745.