一种基于三维眼球模型和Snakuscule的虹膜中心定位算法

doi:10.11896/j.issn.1002-137X.2019.09.043

计算机科学 ›› 2019, Vol. 46 ›› Issue (9): 284-290.doi: 10.11896/j.issn.1002-137X.2019.09.043

所属专题：医学图像

一种基于三维眼球模型和Snakuscule的虹膜中心定位算法

周小龙, 姜嘉祺, 林家宁, 陈胜勇

(浙江工业大学计算机科学与技术学院杭州310023)

收稿日期:2018-08-12 出版日期:2019-09-15 发布日期:2019-09-02
通讯作者: 陈胜勇(1973-),男,博士,教授,博士生导师,CCF会员,主要研究方向为计算机视觉、图像处理,E-mail:sy@ieee.org
作者简介:周小龙(1986-),男,博士,副教授,CCF会员,主要研究方向为目标跟踪、视线跟踪、模式识别,E-mail:zxl@zjut.edu.cn;姜嘉祺(1995-),女,硕士生,主要研究方向为视线跟踪;林家宁(1992-),男,硕士生,主要研究方向为视线跟踪;
基金资助:
国家自然科学基金(61876168,61403342,U1509207,61603341),浙江省自然科学基金(LY18F030020),湖北省水电工程智能视觉监测重点实验室开放基金(2017SDSJ03)

Iris Center Localization Method Based on 3D Eyeball Model and Snakuscule

ZHOU Xiao-long, JIANG Jia-qi, LIN Jia-ning, CHEN Sheng-yong

(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)

Received:2018-08-12 Online:2019-09-15 Published:2019-09-02

摘要/Abstract

摘要： 为提高视线估计中人眼虹膜中心定位的准确性,提出了一种基于三维眼球模型和Snakuscule的新型虹膜中心定位算法。首先,通过人脸对齐方法获取面部特征点,利用特征点初步求得虹膜中心粗定位点;然后,通过判断眼部区域状态降低图像带来的误差;接着,针对Snakuscule能量模型进行改进,通过初始化一个半径固定的Snakuscule模型,对虹膜轮廓进行迭代更新。通过改进的Snakuscule模型结合三维眼球模型获得能量值,其中三维眼球模型反映了虹膜中心、眼球中心和虹膜边界之间组成的几何关系,根据所求能量值不断迭代更新虹膜轮廓,求得最终虹膜中心精确定位点。最后,在BioID 脸部数据库上的实验验证了所提算法的有效性和优越性,该算法的最大标准误差在e≤0.05,e≤0.1和e≤0.25内分别达到了85.0%,97.8%和99.8%。

关键词: Snakuscule, 虹膜中心定位, 能量模型, 三维眼球模型

Abstract: In order to imrove the accuracy of iris center localization of eyes in gaze estimation,this paper proposed a novel iris center localization method based on 3D eyeball model and Snakuscule.Firstly,a facial alignment method is employed to get the facial feature points and the obtained points are used to obtain the initial iris center.Then,the eye status is judged to reduce the error brought by the low-quality image.To further obtain the accurate iris center location,the energy model of Snakuscule is improved and the iris contour is updated iteratively by a fixed size of Snakuscule.The energy value is obtained by combining the Snakuscule model and 3D eye model.The 3D eyeball model reflects the geometric relationship between the iris center,the eyeball center and the iris contours.According to the energy value,the final iris center can be obtained by updating the iris contours iteratively.Finally,experiments conducted on BioID face database validate the effectiveness and superiority of the proposed method.The maximum standard errors of the algorithm reach at 85.0%,97.8% and 99.8% respectively when e≤0.05,e≤0.1,and e≤0.25.

Key words: 3D eyeball model, Energy model, Iris center localization, Snakuscule

中图分类号:

TP391.4

周小龙, 姜嘉祺, 林家宁, 陈胜勇. 一种基于三维眼球模型和Snakuscule的虹膜中心定位算法[J]. 计算机科学, 2019, 46(9): 284-290. https://doi.org/10.11896/j.issn.1002-137X.2019.09.043

ZHOU Xiao-long, JIANG Jia-qi, LIN Jia-ning, CHEN Sheng-yong. Iris Center Localization Method Based on 3D Eyeball Model and Snakuscule[J]. Computer Science, 2019, 46(9): 284-290. https://doi.org/10.11896/j.issn.1002-137X.2019.09.043

参考文献

[1]DAUGMAN J.How iris recognition works[J].IEEE Transaction on Circuits and Systems for Video Technology,2004,14(1):21-30.
[2]WILDES R P.Iris recognition:An emerging bio-metric technology[J].Proceeding of the IEEE,1997,85(9):1348-1363.
[3]WANG Y H,ZHU Y,TAN T N.Identification based on iris recognition[J].Journal of Automatica Sinica,2002,18(1):1-10.(in Chinese)王蕴红,朱勇,谭铁牛.基于虹膜识别的身份鉴别[J].自动化学报,2002,28(1):1-10.
[4]MORIYAMA T,KANADE T,XIAO J,et al.Meticulously detailed eye region model and its application to analysis of facial images[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2006,28(5):738-752.
[5]KIMH I,KIM J B,LEE J E,et al.Gaze estimation using a webcam for region of interest detection[J].Signal Image & Video Processing,2016,10(5):1-8.
[6]LING B,SUO J W,XU J T.An iris localization method combining Snake and GAC model[J].Computer Engineering and Applications,2017,53(1):201-206.(in Chinese)凌滨,索健文,许景涛.一种结合Snake与GAC模型的虹膜定位方法[J].计算机工程与应用,2017,53(1):201-206.
[7]LIU S,LIU Y N,ZHU X D,et al.Iris location algorithm based on partitioning search[J].Computer Engineering and Applications,2018,54(18):212-217.(in Chinese)刘帅,刘元宁,朱晓冬,等.基于分块搜索的虹膜定位算法[J].计算机工程与应用,2018,54(18):212-217.
[8]VALENTI R,GEVERS T.Accurate Eye Center Locationthrough Invariant Isocentric Patterns[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(9):1785-1798.
[9]ZHANG W,ZHANGT N.Eye gaze estimation from the elliptical features of one iris[J].Optical Enginee-ring,2011,50(50):047003-047003-9.
[10]DAS D,RASHED M G,BASHAR M R,et al.Real-Time Iris Center Detection and Tracking From Video Images[C]//International Conference on Machine Learning and Data Enginee-ring.2017:35-41.
[11]XIAO F,HUANG K,QIU Y,et al.Accurate iris center localization method using facial landmark,snakuscule,circle fitting and binary connected component[J].Multimedia Tools & Applications,2018,77(19):25333-25353.
[12]BAEK S J,CHOI K A,MA C,et al.Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems[J].IEEE Transactions on Consumer Electronics,2013,59(2):415-421.
[13]XIONG X,TORRE F D L.Supervised Descent Method and Its Applications to Face Alignment[C]//Computer Vision and Pattern Recognition.IEEE,2013:532-539.
[14]GARG S,TRIPATHI A,CUTRELL E.Accurate eye center localization using Snakuscule[C]//IEEE Winter Conference on Applications of Computer Vision.IEEE,2016:1-8.
[15]CAI H,LIU B,ZHANG J,et al.Visual Focus of Attention Estimation Using Eye Center Localization[J].IEEE Systems Journal,2015,PP(99):1-6.
[16]NIU Z,SHAN S,YAN S,et al.2D Cascaded AdaBoost for Eye Localization[C]//International Conference on Pattern Recognition.IEEE,2006:1216-1219.
[17]ASTERIADIS S,NIKOLAIDIS N,HAJDU A,et al.An Eye Detection Algorithm Using Pixel to Edge Information[C]//International Symposium on Control,Communicationsand Signal Processing.EUSIPCO,2006.
[18]CAMPADELLI P,LANZAROTTIR,LIPORI G.Precise EyeLocalization through a General-to-Specific Model Definition[C]//British Machine Vision Conference.Britain:BMVC,2006:187-196.
[19]LADDI A,PRAKASH N R.An augmented image gradientsbased supervised regression technique for iris center localization[J].Multimedia Tools & Applications,2016,76(5):1-11.
[20]ZHANG W,SMITH M L,SMITH L N,et al.Eye center localization and gaze gesture recognition for human-computer interaction[J].Journal of the Optical Society of America A,2016,33(3):314-325.
[21]KROON B,HANJALIC A,MAAS S M.Eye localization for face matching:is it always useful and under what conditions[C]//International Conference on Content-based Image and Video Retrieval.CIVR,2008:379-388.
[22]LEO M,CAZZATO D,DE M T,et al.Unsupervised eye pupil localization through differential geometry and local self-similarity matching[J].PLoSONE,2014,9(8):e102829.
[23]TIMM F,BARTH E.Accurate Eye Centre Localisation byMeans of Gradients[C]//Proceeding of the Sixth International Conference on Computer Vision Theory and Applications.Vi-lamoura,Algarve,Portugal:VISAPP,2011:125-130.
[24]GARG S,TRIPATHI A,CUTRELL E.Accurate eye center lo-calization using Snakuscule[C]//IEEE Winter Conference on Applications of Computer Vision.IEEE,2016:1-8.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

一种基于三维眼球模型和Snakuscule的虹膜中心定位算法

Iris Center Localization Method Based on 3D Eyeball Model and Snakuscule

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	李章维, 肖璐倩, 郝小虎, 周晓根, 张贵军. 蛋白质构象空间的多模态优化算法 Multimodal Optimization Algorithm for Protein Conformation Space 计算机科学, 2020, 47(7): 161-165. https://doi.org/10.11896/jsjkx.190600100
[2]	董辉,郝小虎,张贵军. 蛋白质构象空间局部增强差分进化搜索方法 Local Enhancement Differential Evolution Searching Method for Protein Conformational Space 计算机科学, 2015, 42(Z11): 22-26.
[3]	郝小虎,张贵军,周晓根,程正华,张启鹏. 一种基于片段组装的蛋白质构象空间优化算法 Protein Conformational Space Optimization Algorithm Based on Fragment-assembly 计算机科学, 2015, 42(3): 237-240. https://doi.org/10.11896/j.issn.1002-137X.2015.03.049
[4]	肖德琴,王景利,罗锡文. 大规模农田传感器网络通信能耗模型 Communication Energy Model for Large Scale Fields Sensor Networks 计算机科学, 2009, 36(8): 75-78.
[5]	赵刚杨宗凯何建华. 基于感知运动能量模型的MPEG-21数字项适配计算机科学, 2005, 32(7): 131-134.