使用單一網路攝影機之視線判斷

全文

(1)Gaze Estimation Using Single Webcam. 102 1. 01.

(2) Adaboost. i.

(3) Abstract Eye-tracking systems are wildly used in cognitive psychology research problems, and recently eye-tracking technology has been considered as a potential multimedia interaction way. It can be applied to help people who suffer from disease and lost the ability of controlling their movements, so that they can manipulate computers and communicate with others. In addition, eye-tracking system can also be used to detect drivers’ fatigue. Reducing the number of accidents can not only save lives but also decrease society cost.. However, commercially available eye-tracking systems usually endure with high cost and hard to fetch problems. We propose an eye movement tracking method using personal computer and single webcam. Our method modifies the Adaboost face detection algorithm to make it faster and reduce the false positive rate. We also provide a new method to calculate the center of iris quickly. Finally, we use SVM to help us categories possible gaze region and determine the final gaze region with our gaze tracking mechanism.. Keywords. Face detection, Eye detection, Iris detection, Gaze estimation. ii.

(4) meeting. VIPLab. Albert Yih 334. Fyrisån. 27. Oslo. Kiruna ……. 2013 Feb. 05 iii.

(5) !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!#! $%&'($)'!""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!##! !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!###! !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!#*! !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!*#! !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!*###! !. !""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!+!. !"!. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#!#. !"$#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#$#. !"%#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#%#. !"&#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#%# !. $"!. !""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!,! #"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#&# $""""""""""""""""""""""""""""""""""""""""""""""""$/#. !"#"#$. %&'()*&+,'-&. method. !"#"!$. 0&123'(&$4'(56789$1&(6:.. $"""""""""""""""""""""""""""""""""""""""$;#. !"#"<$. =22&'*'85&+,'-&.$1&(6:.. $"""""""""""""""""""""""""""""""""""""""""$;#. $"$#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#'# $"""""""""""""""""""""""""""""""""""""""""""""""$?#. !"!"#$. S6'2&+>'-&.$'22*:'56. !"!"!$. =22&'*'85&+>'-&.$'22*:'56. !"!"<$. Learning+>'-&.$'22*:'56. $"%. $""""""""""""""""""""""""""""""""""""""""""""""""""""""$A#. 0&123'(&$4'(56789. !"<"!$. %&'()*&+>'-&.$'22*:'56. !"/"# !"/"!$. $"""""""""""""""""""""""""""""""""""""""""""$@#. #"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#(#. !"<"# $"&#. $""""""""""""""""""""""""""""""""""""""$@#. $"""""""""""""""""""""""""""""""""""""""""""""$A#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#)# =22&'*'85&+,'-&. C&)*'3$C&(D:*E. $"""""""""""""""""""""""""""""""""""""""""""""""""""""""$B#. $"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$B#. ! ! ! ! iv.

(6) !""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!+-!. ! %"!#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#!*#. %"$#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#!!#. %"%#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#!$# $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#<#. <"<"#$. F*'G3&H&3$I1'9&. <"<"!$. JE78$K:3:*$L&(&5(7:8. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#<#. <"<"<$. F'11'$5:**&5(7:8. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#/#. <"<"/$. I8(&9*'3$I1'9&. $"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#;#. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#?#. <"<";$ <"<";$. K'-5'.&$:M$K3'--7M7&*. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#@#. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$#A#. <"<"?$ %"&#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#!)#. %"+. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#$*#. <";"#$N0JO. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$!##. <";"!$K'88G. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$!<#. <";"<$. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$!/#. <";"/$. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$<##. <";.5. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$<!# #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#%%#. %"'# <"?"#$. (Support Vector Machine, SVM)$"""""""""""""""""""""""""""""""""""""""""""""""$</#. <"?"!$. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$<;#. !. !"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!./!. &"!#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#%'#. &"$. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#%(#. /"!"#. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$<A#. /"!"!$. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$/!#. /"!"<$. $""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""$//#. !. !""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!,0!. +"!#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#&,#. 5"$#. #""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""#&,# !""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""!,1!. v.

(7) 1. ....................................................................... 5#. 2. .............................................................................................................. 11#. 3. .......................................................................................................... 12#. 4. (a). 5 6. ....................................... 14#. x,y. ................................................................ 15#. R. L4+L1-L2-L3. 7 8. (b). ............................................. 15#. ......................................................................................................... 16# AdaBoost. 9. ................................................... 16# ..................................................................................................... 17#. 10. ........................................................................................................... 19#. 11. ....................................................................................................... 20#. 12. ................................................................................................................... 20#. 13. ............... 24#. 14. !"# ! !"#. A B C. !". ........................................................................................................................................... 24# 15. ................................................................................................... 25#. 16. 5x5. ................................................................................... 26#. 17. ......................................... 27#. 18. ........................................................................................... 28#. 19. ........................................................................................... 29#. 20. ................................................................................... 30#. 22. ................................................................... 30#. 23. ............................................... 31#. 24. ............................................................................................... 32#. 25. ................................................................................... 33#. 26 SVM. (a). (b). ........................................................................................................................................... 34# 27 28. ............................................................................................... 35# Aberdeen. ........................................ 38#. 29. ............................................... 38#. 30. ................................................... 39#. 31. Faces 1999. 32. OpenCV. ............................................................................. 40# ................................................................. 40#. 33 34 CASIA. ........................................................... 41# ........................................................................... 42# vi.

(8) 35. ............... 42#. 36. ........................................... 43#. 37. ........................................... 43#. 38 iMac 39. .................................................................................. 44# ................................................................... 45#. vii.

(9) 1. Aberdeen. 2. Faces 1999. 3. CASIA. OpenCV. AdaBoost. OpenCV Daugman. ......... 39 ................................... 41. ................................................................ 43. 4. ....................................................................... 45. 5. ......................................................... 46. viii.

(10) 1.1. Human Computer Interaction, HCI automatic speech recognition. gesture recognition. movement tracking. eye. multimedia interaction [1, 2]. [3, 4]. Motor Neuron Disease, MND. Amyotrophic Lateral Sclerosis, ALS. [5]. 1.

(11) [6]. 1.2. gaze path. 2.

(12) 1.3. 1.4. 3.

(13) 1. 2. 3. 4. 2.1. 2.1.1. Feature-Based method. [7]. contour. facial feature [8, 9]. 4.

(14) RGB YCbCr[8, 10] HSV[8, 9] YIQ YUV[11] 1. 1. 2.1.2. Template Matching method. [12]. scaling. 2.1.3. rotation angle. skew. Appearance-Based method. [13-15] 5.

(15) 2.2. face recognition detection. 2.2.1. facial expression analysis. red eye. 3D face modeling. Shape-based approach. [16, 17]. 6.

(16) 2.2.2. Appearance-based approach. [18]. 2.2.3. Learning-based approach. [19]. 7.

(17) 2.3. active approach passive approach electrodes. skin. contact lens. Infrared (IR) based. Image-based passive approach. 2.3.1. Template Matching. [20]. 2.3.2. Feature-based approach. [21]. 8.

(18) 2.4. 2.4.1. Appearance-Based. interpolation. [22]. 2.4.2. Neural Network. Multilayer perceptron, MLP. [23]. 9.

(19) 3.1 3.3. 3.2. face detection iris detection. 3.4. 3.6. 3.1. 10. eye detection. 3.5.

(20) 3.2. 2. 11.

(21) 3.3. 3. down sampling Viola. Jones[24]. 12.

(22) 3.3.1. Graylevel Image. Viola. Jones[24]. Adaboost. 8 0. 256. 焍255. RGB. !"#$%&'&% ! !!!!"" ! ! ! !!!"# ! ! ! !!!!" ! ! !"#$%&'&%. 3.3.2. 8-bits. !. !. !. Skin Color Detection. Viola YCbCr. 13. Jones[24]. (1).

(23) YCbCr YCbCr RGB. YCbCr. ! !" !"!!"# !"#!!"" !"!!"" ! !! ! !"# ! !!"!!"! !!"!!!"# ! !!" !! !"# ! !!" !!"!!"# !!"!!"#. YCbCr !! ! !. :. !!!! !!!!. Cs. 3.3.3. (2). !"!!! ! !"#!!"#!!! ! !"#! ! !"!!"#$%!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!. (3). 1. Gamma correction. 4. !! ! ! ! !. (4). G. (a) 4. (b) (a). (b) 14.

(24) 3.3.4. Integral Image. Viola. !!! !!. Jones[24]. 5. !!!! ! ! ! ! !. (5). ! !! ! ! ! !! ! ! ! ! !!!!! !!!. (6). !! !! ! ! !! ! ! !! ! ! !!!!! !!!. (7). !! !! ! !. ! ! !!!!!! ! !!!. !!!! !!. !!!! !!. 5. 6. x,y. R. L4+L1-L2-L3. 15.

(25) 3.3.5. Viola. Jones[24] 7 AdaBoost. 7. 8. AdaBoost. 16.

(26) 3.3.5. Cascade of Classifier. 9. 9. 17.

(27) 3.3.6. !! ! !. !"#$%&!!"!!! !!"#$%!!"!!!!!!"#$%$"&'!!"#$%& ! !"#$%&!!"!!"#$%!!"!!!!!!"#$%$"&'!!"#$%&. (8). !! !. !! !"!! ! !!!"#!!"#! ! !!!!!!!!!!!"!!"#$%!!!!!!!!!!!!!!!!!. (9). !!. Threshold. 0.7. !!. bounding box. 18. 1.

(28) 3.4. 10. 19.

(29) 11. 3.5. 12. 12 20.

(30) 3.5.1 OTSU. Threshold. 0. !. Otsu[25] !!. i. ! ! !! ! !! ! ! ! !! ! !! !. !!!!! !!. C0. !!. ! !!! !!. T. !. C1. 1~T. T+1~L. !! !. !! !. (10). !! ! !!! !. !! !. (11). !! ! ! ! !! ! !!!!!. ! !. !0 ! !!!. !!!!!! ! !!. !. !1 ! !!!!!. (12). !!!!!! !!. (13). ! !. !!!. !! ! !! !!. ! !!!. !! ! !!. (14). 21.

(31) !. !!!. !! ! !! !!. ! !!!!!. !! ! !!. (15). ! ! ! !! !!! ! !! !!! ! T. !!. (16) T 0. !! !! ! !. !! ! !! ! !. !"!! !! ! ! ! !"!!"#$%!!!!!!!!!!!!!!!!!. 22. (17).

(32) 3.5.2 Canny. Canny. Gaussian filter. !. !. ! !! ! !. !. !!! !!. ! ! ! !! ! ! !!!. (18). !. ! !!! ! !! !! ! ! ! !. !. (19). !!. !. !. !! !. !" ! ! ! !! !" !! ! !. ! ! !! !! !! !. (20) !. !! ! ! ! ! !! !!! !. (21). non-maximal suppression !!!! !! candidate. !!!! !! !! ! ! ! !. !. 23. !!! !!.

(33) 3.5.3. Peng Kun. [26]. 13. 13. Jen-Chun Lee. Thales theorem. [27]. 14. 14. A. B. !!"# ! !"#. C 24. !".

(34) 16. 15 25.

(35) YCbCr. Otsu !!!. 0. !!!. 17. !! !. !! ! !. (22). !! !. !! ! !. (23). !!. !!. !!" ! !!! !!. !!. !!. ! ! !! ! !! ! ! ! ! ! !! ! ! ! !! ! !! ! ! ! ! ! !! !. 16. 5x5. 26. (24).

(36) !"#! ! !"#! ! !"#!!"# !!!!!. !"#!. !!!! !! !. (25). !!!!!!!!". !"#! !!. !!! ! !. 18. !!!! !!!. (26). !!! !!!"#! !"#! !!!!!!!. !!! ! !. !!!! !!!. (27). !!!!!!!!"#! !"#! !!!!!!!. !! ! !!"# !! ! !. "#$%&. ! !!"# !! ! !. (28). !. "'$(&. i. 17. 27. (. !!.

(37) !!. !! !!. !!. !!. 18. !!. !!. !"#. 18 !! !!. !!. !!. !!. !!. !!. !! !!. !!. !! !. !! ! !! !. (29). !! !. !! ! !! ! !. (30). !!. 28.

(38) 19. !! 19. !! !!. !!. !! !!. !!. !!. !!. !! !!. !! !. !! ! !! ! !. (31). !! !. !! ! !! ! !. (32). !!. !!. !!. !! !. !! ! !! ! !. !!. !!. 20. (33). 29.

(39) 20. 21. evaluation function. !!. 21. !! ! !!! !! ! ! !! ! !! ! !!! !! ! ! !! ! !!. !. !. ! ! ! !! ! ! ! ! !! !. !. ! !! ! !. ! !! ! ! !!!!!!!!. !. !!!!!!!!. 30. !. !! ! ! !!!. (34). !. !! ! ! !!! !. (35) (36).

(40) !!. !!. 22. e e. 22. 3.5.4. heuristic rules. 23. 1. 23. 2. 23. 3 31.

(41) 4. 5. 3.5.5. !! !! !"#$% !. !!. ). 24. ! ! !!! ! ! !! ! !. (37). slope. w=15. 24. 32.

(42) 3.6. 25. 30. 25. 33.

(43) 3.6.1. (Support Vector Machine, SVM). classification. [28, 29]. hyperplane 26. LibSVM[30]. (a) 26 SVM. (b) (a). (b). 34.

(44) 3.6.2. 27. Initial state. 27. 35.

(45) C++. GUN g++ 4.2.1 2.7 GHz Intel Core i5. 8GB 1333MHz DDR3. Mac OSX 10.6.8 The Psychological Image Collection at Stirling[31] Caltech Faces 1999[32]. CASIA Iris Image Database for Testing Version 1.0[33] iSight. 1280x720. 4.1. 1. Stirling. Caltech. 2. Aberdeen. Faces 1999. CASIA. 3. [32]. [33]. 30~75 11 36. [31].

(46) 1. Run time :. 2. 3. Frame Per Second, FPS :. Recall. !"#$%% ! 4. 5. !"#$%&!!"!!"##$!%!!"#$!!"!!"#"$#"! ! !"#$%&!!"!!"##$!%!!"#$!!"#$!!"#$%&!!"#!!! Recall :. Daugman[34-36]. False Positive Rate, FP. 37.

(47) 4.2. 4.2.1. 1 The Psychological Image Collection at Stirling (PICS) - Aberdeen 457. 336x480 28. 28. Aberdeen. OpenCV 99%. 1. 29. 38. 624x544. [31].

(48) 30. 30. 1. Aberdeen. OpenCV. Method. Run Time (s). FPS. Recall (%). FP (%). Viola&Jones[24] The proposed method. 21.1 9.1. 32.3 181.8. 100.0 99.8. 1.3 0.2. 39.

(49) 2 Caltech. Faces 1999. [32]. 450. 896x592. 27. 31. 31. Faces 1999. AdaBoost 32. Recall. AdaBoost. OpenCV 2. 32. OpenCV. 40.

(50) 33. 33. 2. Faces 1999. OpenCV. Method. Run Time (s). FPS. Recall (%). FP (%). AdaBoost The proposed method. 50.9 19.6. 12.6 112.8. 99.1 80.0. 26.0 0.2. 41.

(51) 4.2.2. CASIA [33]. 756. 108 34. 320x280. 34 CASIA. Daugman[34-36] 2. 95%. 35. 3. !**"**-# )*"**-# (*"**-# ,*"**-# '*"**-# +*"**-# &*"**-# %*"**-# *#. !#. $#. %#. 35. 42. &#. +#. '#. (pixel).

(52) 3. CASIA[33]. Daugman[34-36]. Method. Run Time (s). FPS. Daugman[34-36] The proposed method. 4031.9 12.7. 0.2 60.0. 36 37. 36. 37. 43.

(53) 4.2.3. 30~75 38. 38 iMac. 11. 39. 50 50. 44.

(54) 4. 74%. 83%. 39. 4. (s) 1 2 3 4 5 6 7. 111.9 107.9 109.7 106.6 109.8 106.1 111.5. (%) 74.3 82.7 83.3 85.8 87.0 80.9 79.2. 5. 45.

(55) 5. (%) 1 2 3 4 5 6 7 8 9 10 11. 89.3 90.0 88.6 86.9 85.5 87.7 83.4 70.3 72.8 73.7 68.0. 46.

(56) 5.1. Adaboost False Positive. 90. 5.2. 1. 47.

(57) 2. 48.

(58) [1] A. P. a. L. J.Ball, "Eye tracking in Human-Computer Interaction and Usability Research: Current Status and Future Prospects," in Encyclopedia of Human-Computer Interaction, ed, 2005. [2] K. S. K. R Jacob, "Eye Tracking in Human-Computer Interaction and Usability Research," 2003. [3] E. M, "Eye-tracking for detection of driver fatigue," presented at the IEEE Intelligent Transportation System, 1997. [4] S. Saito, "Does fatigue exist in a quantitative measurement of eye movements?," Ergonomics, vol. 35, 1992. [5] F. Corno, L. Farinetti, and I. Signorile, "A cost-effective solution for eye-gaze assistive technology " presented at the IEEE International Conference on Multimedia and Expo (ICME), 2002. [6] X. a. F.-X. H. Dreze, "Internet Advertising: Is Anybody Watching?," Interactive Marketing, vol. 17, pp. 8-23, 2003. [7] M. C. B. T.K.Leung, P.Perona, "Finding Face in Cluttered Scenes Using Random Labeled Graph Matching," presented at the 15th IEEE Computer Vision, 1995. [8] C. Garcia and G. Tziritas, "Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis," Ieee Transactions on Multimedia, vol. 1, 1999. [9] L. Jordao, M. Perrone, J. P. Costeira, and J. Santos-Victor, "Active Face and Feature Tracking," presented at the 10th International Conference on Image Analysis and Processing (ICIAP'99), Venice, Italy, 1999. [10] R.-L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, "Face Detection in Color Image," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 696-706, 2002. [11] F. Marqués and V. Vilaplana, "A morphological approach for segmentation and tracking of human faces," presented at the 15th International Conference on Pattern Recognition (ICPR'00), Barcelona, Spain, 2000.. 49.

(59) [12] D. T. I. Craw, and A. Bennett, "Finding Face Features," in second European Conference of Computer Vision, 1996, pp. 142-147. [13] M. T. a. A.Pentland, "Eigenface for Recognition," Cognitive Neuroscience, vol. 3, pp. 71-86, 1991. [14] S. B. H. Rowley, and T. Kanade, "Neural Network-Based Face Detection," IEEE Pattern Analysis and Matchine Intelligence, vol. 20, 1998. [15] K. K. A. Rajagopalan, J.Karlekar,R. Manivasakan,M. Patil,U. Desai, P. Poonacha, and S. Chaudhuri, "Finding Faces in Photographs," in 16th IEEE Computer Vision, 1998. [16] J. Ren and X. Jiang, "Fast eye localization based on pixel differences " presented at the 16th IEEE International Conference on Image Processing(ICIP), Cairo, 2009. [17] P. M. D. Sidibe, and S. Janaqi, "A simple and efficient eye detection method in color images," in Image and Vision Computing, New Zealand, Great Barrier Island, 2006. [18] S. C. K. J.B. Kim, and J.Y. Kim, "Fast detection of multi-view face and eye based on cascaded classifier," in IAPR Conference on Machine Vision Applications, 2005. [19] W. Z. H. Lu, and D. Yang, "Eye detection based on rectangle features and pixel-pattern-based texture features," presented at the International Symposium on Intelligent Signal Processing and Communication System, 2007. [20] N. T. Shinjiro Kawato, "Detection and tracking of eyes for gaze-camera control," in 15th International Conference on Vision Interface, 2004, pp. 1031-1038. [21] D. L. W. Shrinivas J. Pundlik, Stanley T. Birchfild, "Non-Ideal Iris Segmentation Using Graph Cuts," presented at the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008. [22] B. L. Nguyen, Y. Chahir, M. Molina, C. Tijus, and F. Jouen, "Eye gaze tracking with free head movements using a single camera," presented at the SoICT '10 Proceedings of the 2010 Symposium on Information and Communication Technology Hanoi, Vietnam, 2010. [23] W. Sewell and O. Komogortsev, "Real-Time Eye Gaze Tracking With an Unmodified Commodity Webcam Employing a Neural Network," presented at 50.

(60) the 28th of the international conference extended abstracts on Human factors in computing systems, Atlanta, Georgia, USA, 2010. [24] P. Viola and M. J. Jones, "Robust Real-Time Face Detection," International Jounrnal of Computer Vision, vol. 57, pp. 137-154, 2004. [25] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man and Cybernetics, vol. 9, pp. 62-66, 1979. [26] K. Peng, L. Chen, S. Ruan, and G. Kukharev, "A Robust Algorithm for Eye Detection on Gray Intensity Face without Spectacles," Journal of Computer Science & Technology, vol. 5, pp. 127-132, 2005. [27] P. S. H. C.-P. C. a. T.-M. T. Jen-Chun Lee, "Novel and Fast Approach for Iris Location," presented at the Intelligent Information Hiding and Multimedia Signal Processing, 2007, 2008. [28] J. Thorsten, "Making Large-scale SVM learning practical," in Advances in Kernel Methods, ed: MIT Press, 1999, pp. 169-184. [29] C. J. C. Burges, "A tutorial on Support Vector Machines for Pattern Recognition," Data Mining and Knowledge Discovery, vol. 2, pp. 121-167, 1998. [30] C.-C. C. a. C.-J. Lin, "LIBSVM: a library for support vector machines.," ed: ACM Transcations on Intelligent Systems and Technology, 2011. [31] U. o. Stirling, "The Psychological Image Collection at Stirling," U. o. Stirling, Ed., ed. pics.stir.ac.uk. [32] C. I. o. Technology, "Faces 1999," C. I. o. Technology, Ed., ed, 1999. [33] P. J. Phillips, K. W. Bowyer, and P. J. Flynn, "CASIA Iris Image Database(ver 1.0)," ed, 2007. [34] J. Daugman, "High Confidence Visual Recognition of Persons by a Test of Statistical Independnce," IEEE Transactions on PAMI, vol. 15, 1993. [35] J. Daugman, "How iris Recognition Works," Proceedings of 2002 International Conference on Image Processing, vol. 1, 2002. [36] J. Daugman, "The Improtance of Being Random: Statical Principles of Iris Recognition," Pattern Recognition, vol. 36, pp. 279-291, 2003.. 51.

(61)