A New Approach to Face Detection Based on Binary Texture Extraction Algorithm

In1 this paper we proposed a new face detection process and a new texture-based detection algorithm----binary texture extraction algorithm for image preprocessing. This algorithm is applicable to different lighting, different skin colors and complex background. Furthermore, we invented a rough face inspection method called "reduction" according to the principles of the image morphology. Finally, by integrating the algorithm with the mainstream face detection methods, such as BP (Back Propagation) neural network, Gabor and Adaboost, we demonstrated the applicability and robustness of the binary texture extraction algorithm through a set of Matlab experiments containing a variety of lighting environments and different skin colors test library.

[1]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[2]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 2004, International Journal of Computer Vision.

[3]  Stan Z. Li,et al.  Real-time multi-view face detection , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[4]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Xiao Lin,et al.  A Novel BP Neural Network Based System for Face Detection , 2018 .

[6]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  H.M. Wechsler,et al.  Digital image processing, 2nd ed. , 1981, Proceedings of the IEEE.

[8]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..