Eye Detection Using Composite Cross-Correlation

This study presents a new eye detection method depending on composite template matching for facial images. The objective of this study is to utilize t emplate match method to detect the eyes from given images and to improve this method to obtain higher rate of detection. The idea of our method is to integrate cross correlations of various eye templates. Thus, the co rrect values of single template matching based eye detection dominated the final output. It also contr ibuted to the re-correct the detection in the event of failure of all single templates. The study also presents a method to obtain candidate eye pixels which contrib ute to abbreviate the time required to implement up to 91% . The formula of composite cross correlation has be en generalized taking into account the differences bet ween the sizes, shifts and irregular single templat es. The experiments applied on PICS database reported 98.76% as eye detection rate.

[1]  Thomas Serre,et al.  Component-based face detection , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  B. Heisele.  Face Detection , 2001 .

[3]  Erik Hjelmås,et al.  Face Detection: A Survey , 2001, Comput. Vis. Image Underst..

[4]  Xiaojuan Wu,et al.  Fatigue detection based on the distance of eyelid , 2005, Proceedings of 2005 IEEE International Workshop on VLSI Design and Video Technology, 2005..

[5]  Su Ruan,et al.  A robust agorithm for eye detection on gray intensity face without spectacles , 2005 .

[6]  Thai Hoang Le,et al.  Facial Feature Extraction Using Geometric Feature and Independent Component Analysis , 2009, PKAW.

[7]  Kyoung-Mi Lee.  Component-based face detection and verification , 2008, Pattern Recognit. Lett..

[8]  Tan Ching Seong,et al.  Facial Features for Template Matching Based Face Recognition , 2009 .

[9]  Eric M. Schwartz,et al.  Eye Detection Using Morphological and Color Image Processing , 2009 .

[10]  Caglar Tirkaz,et al.  Face recognition using Active Appearance Model , 2009, 2009 IEEE 17th Signal Processing and Communications Applications Conference.

[11]  Wei Chen,et al.  Face detection based on half face-template , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.

[12]  Joonki Paik,et al.  Comparative Analysis of Wavelet-Based Scale-Invariant Feature Extraction Using Different Wavelet Bases , 2009, FGIT-SIP.

[13]  Nur Izura Udzir,et al.  Extract of Facial Feature Point , 2009 .

[14]  Qiong Liu,et al.  A robust skin color based face detection algorithm , 2010, 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010).

[15]  Nilamani Bhoi,et al.  Template Matching based Eye Detection in Facial Image , 2010 .

[16]  Victor-Emil Neagoe,et al.  Face detection in color images using fusion of the chrominance and luminance channel decisions , 2010, 2010 8th International Conference on Communications.

[17]  Qi Jia,et al.  Face detection with abstract template , 2010, 2010 3rd International Congress on Image and Signal Processing.

[18]  Bogdan Ionescu,et al.  Upper face description by comparative analysis of gray-scale image pairs , 2011, ISSCS 2011 - International Symposium on Signals, Circuits and Systems.

[19]  Satoshi Suzuki,et al.  Pupil detecting algorithm with template matching for analysis of eye movements in training process of a vehicle operation , 2011, SICE Annual Conference 2011.