-
摘要: 基于圖像處理的方法，采用了由粗及精的瞳孔定位思想，提出了一種高精度的瞳孔定位算法。該算法首先利用瞳孔區域的直方圖，采用改進的最大類間方差法自適應地分割瞳孔區域，實現粗略定位，然后利用瞳孔灰度的梯度特性來精確定位瞳孔邊緣點，最后在像素級瞳孔邊緣點的基礎上，采用亞像素定位方法，更精確地求得亞像素級瞳孔邊緣點，并通過橢圓擬合的方法來精確確定瞳孔的中心位置。另外，針對瞳孔被遮擋的情況，本文提出了一種等距離補償瞳孔的方法。多次實驗結果證明了該算法對遮擋瞳孔的定位有較強的魯棒性，可以準確地定位瞳孔的位置。Abstract: The gaze tracking technology is widely used in many fields, and it has a broad application prospect in the field of human-computer interaction. The technology is based on the eye characteristic parameters and the gaze parameters, and it estimates the direction of sight and placement of sight based on the eye model. Therefore, accurately locating the pupil position is important in the gaze tracking technology, and it directly affects the accuracy of the gaze tracking result. Presently, there are numerous algorithms used in eye detection; however, most of them are characterized by some problems, such as the low accuracy of locating the pupil position, high detection error, and slow operation speed; thus, they cannot meet the accuracy requirements of locating the pupil position. To solve these problems, in this study, a concept of pupil localization method from rough to precise was adopted, and a high-accuracy pupil localization method based on image processing was proposed. In this method, first, the improved maximal between-cluster variance algorithm used the histogram of the pupil region to adaptively segment region to roughly locate the pupil region. Then the pupil edge points can be accurately located by the gradient of the pupil grayscale. Finally, a sub-pixel localization method was adopted on the basis of the pixel level edge points of the pupil to locate the sub-pixel level edge points of pupil more accurately, and the center position of the pupil was accurately determined by the method of ellipse fitting. In addition, an equidistance pupil compensation method was proposed in this paper for the situation of pupil occlusion. Several experimental results show that the algorithm is robust to locate the position of pupil occlusion and that it can achieve accurate pupil localization.
-
圖 19 圖像處理結果. (a) 人眼圖像; (b) 二值化; (c) 腐蝕膨脹; (d) 瞳孔粗定位; (e) 瞳孔精確分割; (f) 瞳孔擬合
Figure 19. Results of image processing: (a) eye image; (b) binarization; (c) erosion and dilation; (d) pupil coarse localization; (e) accurate pupil segmentation; (f) pupil fitting
表 1 算法檢測誤差比較
Table 1. Comparison of measurement errors between algorithms
下載: 導出CSV
表 2 瞳孔定位算法速度比較
Table 2. Comparison pupil localization speeds between algorithms
下載: 導出CSV
表 3 瞳孔定位算法精度比較
Table 3. Comparison of pupil localization accuracies between algorithms
算法 定位精度/% 一般質量圖片 低質量圖片 文獻[9]方法 92.0 67.5 本文方法 96.0 78.5
下載: 導出CSV
www.77susu.com<span id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> <span id="fpn9h"><noframes id="fpn9h"> <th id="fpn9h"></th> <strike id="fpn9h"><noframes id="fpn9h"><strike id="fpn9h"></strike> <th id="fpn9h"><noframes id="fpn9h"> <span id="fpn9h"><video id="fpn9h"></video></span> <ruby id="fpn9h"></ruby> <strike id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> -
參考文獻
[1] Zhang C, Chi J N, Zhang Z H, et al. Gaze estimation in a gaze tracking system. Scientia Sinica Informationis, 2011, 41(5): 580張闖, 遲健男, 張朝暉, 等. 視線追蹤系統中視線估計方法研究. 中國科學: 信息科學, 2011, 41(5):580 [2] Zhu B, Chi J N, Zhang T X. Gaze point compensation method under head movement in gaze tracking system. J Highway Transportation Res Dev, 2013, 30(10): 105 doi: 10.3969/j.issn.1002-0268.2013.10.019朱博, 遲健男, 張天俠. 視線追蹤系統頭動狀態下的視線落點補償方法. 公路交通科技, 2013, 30(10):105 doi: 10.3969/j.issn.1002-0268.2013.10.019 [3] Chi J N, Zhang C, Qin Y J, et al. Pupil tracking method based on particle filtering in gaze tracking system. Int J Phys Sci, 2011, 6(5): 1233 [4] Jarjes A A, Wang K Q, Mohammed G J. Iris localization: Detecting accurate pupil contour and localizing limbus boundary//2nd International Asia Conference on Informatics in Control, Automation and Robotics. Wuhan, 2010: 349 [5] Tian Z C, Qin H B. Real-time driver's eye state detection//IEEE International Conference on Vehicular Electronics and Safety. Xi'an, 2005: 285 [6] Kallel I K, Masmoudi D S, Derbel N. Fast pupil location for better iris detection//6th International Multi-Conference on Systems, Signals and Devices. Djerba, 2009: 1 [7] Nair P S, Saunders Jr A T. Hough transform based ellipse detection algorithm. Pattern Recognit Lett, 1996, 17(7): 777 doi: 10.1016/0167-8655(96)00014-1 [8] Wang Y H, Zhu Y, Tan T N. Biometrics personal identification based on iris pattern. Acta Autom Sinica, 2002, 28(1): 1王蘊紅, 朱勇, 譚鐵牛. 基于虹膜識別的身份鑒別. 自動化學報, 2002, 28(1):1 [9] Wang J N, Liu T, He D, et al. Pupil center localization algorithm used for the IR head-mounted eye tracker. J Xidian Univ Nat Sci, 2011, 38(3): 7王軍寧, 劉濤, 何迪, 等. 紅外頭盔式眼動儀的瞳孔中心定位算法. 西安電子科技大學學報(自然科學版), 2011, 38(3):7 [10] Liu Y, Gong W G, Li W H. Robust classifier based two-layer Adaboost for precise eye location. J Comput Appl, 2008, 28(3): 801劉藝, 龔衛國, 李偉紅. 雙層結構Adaboost健壯分類器用于人眼精確定位. 計算機應用, 2008, 28(3):801 [11] Xu P, Tong G, Qu J. Face detection in video based on AdaBoost algorithm and eye location. Video Eng, 2011, 35(9): 114 doi: 10.3969/j.issn.1002-8692.2011.09.035徐品, 童癸, 瞿靜. 基于AdaBoost算法和人眼定位的動態人臉檢測. 電視技術, 2011, 35(9):114 doi: 10.3969/j.issn.1002-8692.2011.09.035 [12] Long L M. Research on Face Detection Method and Eye Localization Algorithm Based on Adaboost[Dissertation]. Chengdu: University of Electronic Science and Technology of China, 2008龍伶敏. 基于Adaboost的人臉檢測方法及眼睛定位算法研究[學位論文]. 成都: 電子科技大學, 2008 [13] Lin M Z. Research on Face Recognition Based on Deep Learning[Dissertation]. Dalian: Dalian University of Technology, 2013林妙真. 基于深度學習的人臉識別研究[學位論文]. 大連: 大連理工大學, 2013 [14] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern, 1979, 9(1): 62 doi: 10.1109/TSMC.1979.4310076 [15] Yang X F, Qin Y C, Li T, et al. Eye localization optimization method based on YCb’Cr’ skin color feature and Otsu algorithm. J Nanjing Univ Posts Telecommun Nat Sci, 2014, 34(1): 99楊秀芳, 戚銀城, 李婷, 等. 基于YCb’Cr’膚色特征和Otsu算法的人眼定位優化方法. 南京郵電大學學報(自然科學版), 2014, 34(1):99 [16] Wang J R, Yuan X H, Liu Z L. An extraction method of pupil and corneal reflection centers based on image processing technology. CAAI Trans Intell Syst, 2012, 7(5): 423 doi: 10.3969/j.issn.1673-4785.201112013王錦榕, 袁學海, 劉增良. 基于圖像處理技術的瞳孔和角膜反射中心提取算法. 智能系統學報, 2012, 7(5):423 doi: 10.3969/j.issn.1673-4785.201112013 [17] Liu R A, Jin S J, Li W Q, et al. Subpixel edge detection and center localization of the pupil. Comput Eng Appl, 2007, 43(5): 200 doi: 10.3321/j.issn:1002-8331.2007.05.060劉瑞安, 靳世久, 李文清, 等. 瞳孔亞像素邊緣檢測與中心定位. 計算機工程與應用, 2007, 43(5):200 doi: 10.3321/j.issn:1002-8331.2007.05.060 [18] Yan B, Wang B, Li Y. Optimal ellipse fitting method based on least-square principle. J Beijing Univ Aeron Astron, 2008, 34(3): 295閻蓓, 王斌, 李媛. 基于最小二乘法的橢圓擬合改進算法. 北京航空航天大學學報, 2008, 34(3):295 [19] Pan L, Wei L F, Zheng B K, et al. Improved method for the pupil measurement under occlusion. J Image Graphics, 2012, 17(2): 229 doi: 10.11834/jig.20120211潘林, 魏麗芳, 鄭炳錕, 等. 改進的遮擋條件下瞳孔檢測方法. 中國圖象圖形學報, 2012, 17(2):229 doi: 10.11834/jig.20120211 [20] Yuan W Q, Qiao Y Q. Detection of eyelash occlusions method for the iris recognition. Opto-Electron Eng, 2008, 35(6): 124 doi: 10.3969/j.issn.1003-501X.2008.06.025苑瑋琦, 喬一勤. 一種用于虹膜識別的眼睫毛遮擋檢測算法. 光電工程, 2008, 35(6):124 doi: 10.3969/j.issn.1003-501X.2008.06.025 -
點擊查看大圖
圖(20) / 表(3)
計量
- 文章訪問數: 908
- HTML全文瀏覽量: 769
- PDF下載量: 45
- 被引次數: 0
