Journal of Applied Science and Engineering

Published by Tamkang University Press


Impact Factor



Lei Zhao This email address is being protected from spambots. You need JavaScript enabled to view it.1, Guoxin Zhang2

1School of Mechanical and Electronic Engineering, Shandong Jianzhu University, No.1000 of Fengming Road, Jinan, China
2Department of Mechanical Engineering, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong


Received: August 7, 2019
Accepted: March 26, 2020
Publication Date: September 1, 2020
Download Citation: ||  


A novel approach for the detecting dynamic facial fatigue behavior of drivers is proposed in this work. First, the eye and mouth regions are extracted from a frame in a video to classify the static facial fatigue state by using a local ensemble convolutional neural network (LECNN) model. A transfer learning strategy is used to pretrain the LECNN model for improved recognition accuracy. Second, the classification results for the frames in the video are encoded and connected to construct an encoding vector that represents the facial state in the video. Finally, k-nearest neighbors classifier is adopted to classify the constructed vector and obtain the recognition result of facial fatigue. The proposed system is tested on a human fatigue dataset of images that are captured in different environments. Results demonstrate the stable and robust performance of the proposed method with approximately 96.76% accuracy.

Keywords: Driver fatigue recognition, Local ensemble convolutional neural networks, Transfer learning.


  1. [1] Jo J., Lee SJ., Park KR., Kim I-J., Kim J., “Detecting driver drowsiness using feature-level fusion and user-specific classification,” Expert Systems with Applications, 41, No. 4, pp. 1139-1152 (2014). doi:10.1016/j.eswa.2013.07. 108

  2. [2] Cyganek B., Gruszczyński S., “Hybrid computer vision system for drivers' eye recognition and fatigue monitoring,” Neurocomputing, 126, pp. 78-94 (2014). doi: 10.1016/j.neucom.2013.01.048

  3. [3] Dasgupta A., George A., Happy S., Routray A., “A vision-based system for monitoring the loss of attention in automotive drivers,” IEEE Transactions on Intelligent Transportation Systems, 14, No. 4, pp. 1825-1838 (2013). doi: 10.1109/ TITS.2013.2271052

  4. [4] Zhao C., Lian J., Dang Q., Tong C., “Classification of driver fatigue expressions by combined curvelet features and gabor features, and random subspace ensembles of support vector machines,” Journal of Intelligent & Fuzzy Systems, 26, No. 1, pp. 91-100 (2014). doi: 10.3233/IFS-120717

  5. [5] Zhao C., Zhang Y., Zhang X., He J., “Recognition of driver’s fatigue expression using Local Multiresolution Derivative Pattern,” Journal of Intelligent & Fuzzy Systems, Vol. 30, No. 1, pp. 547-560 (2015). doi:10.3233/ifs-151779

  6. [6] Wang C., Yan T., Jia H., “Spatial-Temporal Feature Representation Learning for Facial Fatigue Detection,” International Journal of Pattern Recognition & Artificial Intelligence, Vol. 32, No. 12, pp. 1856018 (2018). doi: 10.1142/ S0218001418560189

  7. [7] Jabbar R., Al-Khalifa K., Kharbeche M., Alhajyaseen W., Jafari M., Shan J., “Real-time Driver Drowsiness Detection for Android Application Using Deep Neural Networks Techniques,” Procedia Computer Science, Vol. 130, pp. 400-407 (2018). doi: 10.1016/j.procs.2018.04.060

  8. [8] Viola P., Jones MJ. “Robust real-time face detection,” International journal of computer vision, Vol. 57, No. 2 pp. 137-154 (2004). doi: 10.1023/b:visi.000001 3087.49260.fb

  9. [9] Asthana A., Zafeiriou S., Cheng S., Pantic M., “Incremental face alignment in the wild,” of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, U.S.A., June 24-27, pp. 1859-1866 (2014).

  10. [10] LeCun Y., Bottou L., Bengio Y., Haffner P. “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324 (1998). doi: 10.1109/5.726791

  11. [11] Lucey P., Cohn JF., Kanade T., Saragih J., Ambadar Z., Matthews I., “The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression,” of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, U.S.A., June 13-18, pp. 94-101 (2010).

  12. [12] Pantic M., Valstar M., Rademaker R., Maat L., “Web-based database for facial expression analysis,” of 2005 IEEE international conference on multimedia and Expo, Amsterdam, Netherlands, July 06-06, (2005).

  13. [13] Bänziger T., Scherer KR., “Introducing the geneva multimodal emotion portrayal (gemep) corpus,” Blueprint for affective computing: A sourcebook, :Oxford University, Oxford, pp. 271-294 (2010).

  14. [14] Goodfellow IJ., Erhan D., Carrier PL., Courville A., Mirza M., Hamner B., Cukierski W., Tang Y., Thaler D., Lee D-H., “Challenges in representation learning: A report on three machine learning contests,” of 2013 International Conference on Neural Information Processing, Daegu, Korea, May 26-30, pp. 117-124 (2013).

  15. [15] Lyons MJ., Budynek J., Akamatsu S., “Automatic classification of single facial images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 12, pp. 1357-1362 (1999). doi: 10.1109/34.817413
  16. [16] Krizhevsky A. “Learning Multiple Layers of Features from Tiny Images,” Desertation, Univ Toronto, Toronto, ON, Canada, 2009.

  17. [17] Zhao L., Wang Z., Zhang G., “Facial expression recognition from video sequences based on spatial-temporal motion local binary pattern and gabor multiorientation fusion histogram,” Mathematical Problems in Engineering, Vol. 2017, pp. 1-12 (2013). doi: 10.1155/2017/7206041

  18. [18] Zhao L., Wang Z., Wang X., Qi Y., Liu Q., Zhang G., “Human fatigue expression recognition through image-based dynamic multi-information and bimodal deep learning,” Journal of Electronic Imaging, Vol. 25, No. 5, pp. 053024. doi: 1117/1.JEI.25.5.053024