Mingxin YU, Yingzi LIN, Xiangzhou WANG

An efficient hybrid eye detection method

Eye detection is the most important and critical task of diverse applications such as face detection and recognition. However, most eye detection methods do not fully consider detection robustness to people with glasses, illumination variation, head pose change, and eye occlusions. This paper proposes an efficient hybrid eye detection method based on a gray intensity variance filter (VF) and support vector machines (SVMs). Firstly, the VF is used for eliminating most of noneye region images to keep less candidate eye regions. Then accurate two eye regions are determined easily through the trained SVM classifier. Moreover, this paper provides an assessment of the sensitivity of obtained parameters in the SVM classifier on eye detection accuracy. The proposed method was evaluated on different face databases. The experimental results show that the method can improve the performance of eye detection and achieve a higher detection accuracy compared with state-of-the-art methods.

PDF

___

[1] Hansen DW, Ji Q. In the eye of the beholder: a survey of models for eyes and gaze. IEEE T Pattern Anal 2010; 32: 478-500.
[2] Feng GC, Yuen PC. Multi-cues eye detection on gray intensity image. Pattern Recogn 2001; 34: 1033-1046.
[3] Zhou ZH, Geng X. Projection functions for eye detection. Pattern Recogn 2004; 5: 1049-1056.
[4] Guan Y. Robust eye detection from facial image based on multi-cue facial information. In: IEEE 2007 Control and Automation Conference; 30 May-1 June 2007; Guangzhou, China. New York, NY, USA: IEEE, pp. 1775-1778.
[5] Ando T, Semicond OKI, Moshnyaga VG. A low complexity algorithm for eye detection and tracking in energyconstrained applications. In: IEEE 2013 Communications, Signal Processing, and their Applications Conference; 12-14 February 2013; Sharjah, UAE. New York, NY, USA: IEEE, pp. 1-4.
[6] Ryu YS, Oh SY. Automatic extraction of eye and mouth fields from a face image using eigenfeatures and ensemble networks. Appl Intell 2002; 17: 171-185.
[7] Wang P, Ji Q. Multi-view face and eye detection using discriminant features. Computer and Vision and Image Understanding 2007; 105: 99-111.
[8] Wu J, Trivedi MM. A binary tree for probability learning in eye detection. In: IEEE 2005 Computer Vision and Pattern Recognition Conference; 25-26 June 2005; San Diego, CA, USA. New York, NY, USA: IEEE, pp. 164-171.
[9] Peng K, Chen LM, Ruan S, Kukharev G. A robust algorithm for eye detection on grey intensity face without spectacles. J Comput Sci Tech (JCS&T) 2005; 5: 127-132.
[10] Liu X, Dong YQ, Li S. Rapid human-eye detection based on an integrated method. In: IEEE 2010 Communications and Mobile Computing Conference; 12-14 April 2010; Shenzhen, China. New York, NY, USA: IEEE, pp. 2-8.
[11] Campadelli P, Lanzarotti R. Fiducial point localization in color images of face foregrounds. Image Vis Comput 2004; 22: 863-872.
[12] Hassaballah M, Kanazawa T, Ido S, Ido S. Efficient eye detection method based on grey intensity variance and independent components analysis. IET Comput Vis 2010; 4: 261-271.
[13] Laxmi V, Rao PS. Eye detection using Gabor Filter and SVM. In: IEEE 2012 Intelligent Systems Design and Applications (ISDA) Conference; 27-29 November 2012; Kochi, Japan. New York, NY, USA: IEEE, pp. 880-883.
[14] Kalbkhani H, Shayesteh MG, Moussvi SM. Efficient algorithms for detection of face, eye, and eye state. IET Comput Vis 2013; 7: 184-200.
[15] Phromsuthirak C, Umchid S. Development of a geometrical algorithm for eye detection in color images. In: IEEE 2012 Biomedical Engineering Conference; 5-7 December 2012; Ubon Ratchanthani, Thailand. New York, NY, USA:IEEE, pp. 5-7.
[16] Vapnik VN. The Nature of Statistical Theory. New York, NY, USA: Springer-Verlag, 1995.
[17] Mahesh P, Giles MF. Feature Selection for Classification of Hyperspectral Data by SVM. IEEE T Geosci Remote Sens 2010; 48: 2297-2308.
[18] Boser B, Guyon IM, Vaphik VN. A Training Algorithm for Optimal Margin Classifiers. In: ACM 1992 Computational learning theory annual workshop; 27-29 July 1992; Pittsburgh, PA, USA. New York, NY, USA: ACM. pp. 144-152.
[19] Jian Y, Zhang D, Yang JY. Constructing PCA baseline algorithms to reevaluate ICA-based face-recognition performance. IEEE T Sys Man Cybern B, Cybern. 2007; 37: 1015-1021.
[20] Haupt RL, Haupt SE. Practical Genetic Algorithms. New York, NY, USA: John Wiley and Sons, 1998.
[21] Viola P, Jones MJ. Robust real-time face detection. Int J Comput Vis 2004; 57: 137-154.