Pupil extraction system for Nystagmus diagnosis by using K-mean clustering and Mahalanobis distance technique

As vertigo is a type of dizziness, it causes by problem with nystagmus. Doctors can diagnosis this disease from observing the motion of inner eye. For Nystagmus diagnosis system, efficient and precise pupil extraction system is needed. This paper proposed a method of pupil extraction by using K-mean clustering and Mahalanobis distance. Image sequence is captured via infrared camera mounted on the binocular. Eye tracking algorithm is consisted of K-mean clustering and Mahalanobis Distance. Based on the darkness of pupil, K-means clustering algorithm is used to segment black pixels. Extracted region is pupil, however noise is occurred. The noisy data is eliminated by means of Mahalanobis distance technique. Then the pupil is extracted. For experimental result, 1869 frames from 9 image sequences are use to test the performance of the proposed method. Accuracy is 73.68%, precision is 3.18 pixels error.

[1]  Ali Abd Almisreb,et al.  Enhancement pupil isolation method in iris recognition , 2011, 2011 IEEE International Conference on System Engineering and Technology.

[2]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[3]  Hamid Reza Pourreza,et al.  Fast and Accurate Pupil Positioning Algorithm using Circular Hough Transform and Gray Projection , 2011 .

[4]  Hamid R. Tizhoosh,et al.  IRIS Segmentation: Detecting Pupil, Limbus and Eyelids , 2006, 2006 International Conference on Image Processing.

[5]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[6]  Andrew T Duchowski,et al.  A breadth-first survey of eye-tracking applications , 2002, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[7]  Lifeng Gao,et al.  Improvement on Pupil Positioning Algorithm in Eye Tracking Technique , 2009, 2009 International Conference on Information Engineering and Computer Science.

[8]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[9]  Zongcai Ruan,et al.  IR Image Based Eye Gaze Estimation , 2007, Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007).

[10]  Jian-Gang Wang,et al.  Gaze determination via images of irises , 2001, Image Vis. Comput..

[11]  Wei Lu,et al.  Application of hough transform in eye tracking and targeting , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.

[12]  Vidas Raudonis,et al.  Discrete eye tracking for medical applications , 2009, 2009 2nd International Symposium on Applied Sciences in Biomedical and Communication Technologies.

[13]  Shunsuke Tominaga,et al.  3-Dimensional analysis of nystagmus using video and image processing , 2010, Proceedings of SICE Annual Conference 2010.

[14]  Kazuhiko Hamamoto,et al.  DUAL CAMERAS ACQUISITION FOR THREE-DIMENSIONAL EYE-MOTION TRACKING , 2010 .

[15]  Kazuhiko Hamamoto,et al.  Real time eye tracking using initial centroid and gradient analysis technique , 2009, 2009 6th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[16]  Yang Bo,et al.  Using Trust Metric to Detect Malicious Behaviors in WSNs , 2007, Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007).

[17]  Qiang Ji,et al.  In the Eye of the Beholder: A Survey of Models for Eyes and Gaze , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.