Driver Eye State Detection Based on Minimum Intensity Projection Using Tree Based Classifiers
Eye state identification has wide potential applications in the design of human-computer interface, recognition of facial expression, driver dowsiness detection, and so on. A novel approach to deal with the problem of detecting whether the eyes in a given face image are closed or open is presented in this paper. The projection of row wise minimum intensity and column wise minimum intensity pixel of the histogram equalized eye image is used as a feature in this work. The various tree-based classifiers such as Random Forest, Naive Bayes Tree, Random Tree, and REPTree are exploited to classify the eye as open or closed. The experimental results show that random forest classifier yields the best performance with an overall accuracy rate of 96.3% than the other classifiers.
KeywordsFace and eye localization Row-wise and Column-wise intensity projection Tree based classifiers
Unable to display preview. Download preview PDF.
- 1.Tian, Y.L., Kanade, T., Cohn, J.: Eye-state action unit detection by Gabor wavelets. In: Proceedings of International Conference on Advances in Multi-Modal Interfaces, pp. 143–150 (2000)Google Scholar
- 2.Lu, L., Ning, X., Qian, M., Zhao, Y.: Close eye detected based on synthesized gray projection. Advances in Multimedia, Software Engineering and Computing 2, 345–351 (2012)Google Scholar
- 3.Song, F., et al.: Eyes closeness detection from still images with multi-scale histograms of principal oriented gradients. Pattern Recognition (2014)Google Scholar
- 6.Zhou, L., Wang, H.: Open/closed eye recognition by local binary increasing intensity patterns. In: Proceedings of IEEE Conference on Robotics, Automation and Mechatronics, pp. 7–11 (2011)Google Scholar
- 7.Tian, Z., Qin, H.: Real-time driver’s eye state detection. In: Proceedings of the IEEE International Conference on Vehicular Electronics and Safety, pp 285–289 (2005)Google Scholar
- 8.Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. IEEE Conference on Computer Vision and Pattern Recognition, pp. 511–518 (2001)Google Scholar
- 10.Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: ICCV (2007)Google Scholar
- 12.Nor Haizan, W., Mohamed, W., Salleh, M.N.M., Omar, A.H.: A Comparative Study of Reduced Error Pruning Method in Decision Tree Algorithms. In: IEEE International Conference on Control System, Computing and Engineering, November 23–25 (2012)Google Scholar
- 13.Pumpuang P., Srivihok A., Praneetpolgrang P.: Comparisons of Classifier Algorithms: Bayesian Network, C4.5, Decision Forest and NBTree for Course Registration Planning Model of Undergraduate Students. In: IEEE International Conference, SMC (2008)Google Scholar
- 14.Witten, I.H., Frank, E., Trigg, L., Hall, M., Holmes, G., Cunningham, S.J.: Weka: Practical Machine Leraning Tools and Techniques with Java Implementations, New Zealand (1999)Google Scholar