Abstract
Estimation of face orientation has been a topic of intense research in the recent past. Most of the prior face orientation methods use symbolic methods or handcrafted internal representations which are not sufficiently brain based. An emergent developmental network (DN) is presented to recognize the face orientation, from sensory and motor experience. This work is different in the sense that we focused on mechanisms that enable a system to develop its emergent representations from its operational experience. In this work, internal unsupervised neurons of the DN are used to represent the face orientation, and the competitions among the internal neurons enable them to represent different face orientations. To illustrate the recognition effect, we study and compare the recognition effects among the BP, LVQ, PNN, and DN. Experiment results demonstrate efficiently how such internal neurons represent the face orientation while they are not directly supervised by the external environment. The presented network is developmental which means that the internal representations are directly learned from the signals of the input and motor ports, not designed internally for particular task; hence, the same learning principles are potentially suitable for other sensory modalities. As far as we know, it is the first trial to use the DN to recognize the face orientation.
Similar content being viewed by others
References
Li, D., Pedrycz, W.: A central profile-based 3D face pose estimation. Pattern Recogn. 47(2), 525–534 (2014)
Peng, X., Huang, J., Hu, Q., Zhang, S., Elgammal, A.: From circle to 3-sphere: head pose estimation by instance parameterization. Comput. Vis. Image Underst. 136, 92–102 (2015)
Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Trans. Pattern Anal. Mach. Intell. 20(1), 22–38 (1998)
Gao, L. Xu, Y.: Face orientation recognition based on multiple facial feature triangles. In: Proceedings of the 2012 International Conference on Control Engineering and Communication Technology, Shenyang, Liaoning, China, December 07–09, pp. 928–932 (2015)
Wang, D., Chen, J., Liu, L.: How internal neurons represent the short context: an emergent perspective. Prog. Artif. Intell. 6(1), 67–77 (2017)
Demirkus, M., Precup, D., Clark, J.J., Arbel, T.: Hierarchical temporal graphical model for head pose estimation and subsequent attribute classification in real-world videos. Comput. Vis. Image Underst. 136, 128–145 (2015)
Dornaika, F., Chahla, C., Khattar, F., Abdallah, F., Snoussi, H.: Discriminant sparse label-sensitive embedding: application to image-based face pose estimation. Eng. Appl. Artif. Intell. 50, 168–176 (2016)
Peng, X., Bemamoun, M., Mian, A.S.: A training-free nose tip detection method from face range images. Pattern Recogn. 44(3), 544–558 (2011)
Baluja,S. Sahami,M., Rowley,H.: Efficient face orientation discrimination. In: Proceedings of the 2004 International Conference on Image Processing, Singapore, October 24–27, pp. 589-592 (2004)
Jones, M., Viola, P.: Fast multi-view face detection. Proc. Comput. Vis. Pattern Recogn. 11(1), 276–286 (2003)
Hu, Z., Uchida, N., Wang, Y., Dong, Y.: Face orientation estimation for driver monitoring with a single depth camera. In: Proceedings of the 2015 IEEE Intelligent Vehicles Symposium, Seoul, Korea, June 28–July, pp. 958–963 (2015)
Kim, S.J. , Choi, H., Kwon, J., Kim, T.: Recognition of face orientation by divided hausdorff distance. In: Proceedings of the 2015 38th International Conference on Telecommunications and Signal Processing (TSP 2015), Prague, Czech Republic, July 9–11, pp. 564–567 (2015 )
Ishi, J.C. Even, T., Hagita, N.: Speech activity detection and face orientation estimation using multiple microphone arrays and human position information. In: Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, Sept 28–Oct 2, pp. 5574–5579 (2015)
Zhang, M., Li, L., Guo, L., Zhao, Y.: Study on vision monitoring techniques of driver’s face orientation. In: Proceedings of the 2010 International Conference on Intelligent Control and Information Processing, Dalian, China, August 13–15, pp. 297–301 (2010)
Han, S., Pan, G. , Wu, Z. : Human face orientation detection using power spectrum based measurements. In: Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR04), Seoul, South Korea, May 17–19, pp. 791–796 (2004)
Wu, Y., Chen, C., Kang, W.: Face orientation recognition base on BP network. Imaging Technol. 1, 29–34 (2012)
Feng, J., Lu, H., Chen, S.: Research of face orientation recognition base on LVQ network. Math. Technol. Appl. 5, 95–97 (2016)
Zhu, Y., Gu, J., Liu, C.: Face orientation recognition base on probabilistic neural network. Technol. Wind 63(7), 80–82 (2014)
Guo, Q., Wu, X. , Weng, J.: WWN-9: cross-domain synapse maintenance and its application to object groups recognition. In: Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, China, July 6–11, pp. 716–723 (2014)
Yin, F.: Eyes location in complex background. Comput. Simul. 26(10), 225–228 (2009)
Liu, H., Fang, W.: New ideas of face orientation discrimination based on BP neural network. Comput. Sci. 39(11A), 366–369 (2012)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, D., Shan, H., Tian, Y. et al. Emergent face orientation recognition with internal neurons of the developmental network. Prog Artif Intell 7, 359–367 (2018). https://doi.org/10.1007/s13748-018-0150-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13748-018-0150-z