Eye location based on adaptive image segmentation and curve blending

YANG Fan1; ZHANG Hua1; 2; PAN Guo-feng1; WANG Zhi-tao1

doi:10.3788/OPE.20132112.3255

您当前的位置：

首页 >

文章列表页 >

Eye location based on adaptive image segmentation and curve blending

更新时间：2020-08-12

- Eye location based on adaptive image segmentation and curve blending
- Optics and Precision Engineering Vol. 21, Issue 12, Pages: 3255-3262(2013)
- 作者机构：
  
  1. 中国人民解放军93716部队，天津 301716
  2. 河北工业大学信息工程学院天津,300401
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132112.3255
  CLC： TP394.1
- Received：23 April 2013，
  
  Revised：21 June 2013，
  
  Published Online：25 December 2013，
  
  Published：25 December 2013
- 稿件说明：
移动端阅览
杨帆张华潘国峰王志陶. 应用自适应图像分割与曲线融合的人眼定位[J]. 光学精密工程, 2013,21(12): 3255-3262

YANG Fan ZHANG Hua PAN Guo-feng WANG Zhi-tao. Eye location based on adaptive image segmentation and curve blending[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3255-3262
杨帆张华潘国峰王志陶. 应用自适应图像分割与曲线融合的人眼定位[J]. 光学精密工程, 2013,21(12): 3255-3262 DOI： 10.3788/OPE.20132112.3255.

YANG Fan ZHANG Hua PAN Guo-feng WANG Zhi-tao. Eye location based on adaptive image segmentation and curve blending[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3255-3262 DOI： 10.3788/OPE.20132112.3255.

摘要

人眼定位采用的传统投影算法对人脸边缘、表情及光照适应性差，易受眉毛、刘海及皱纹的干扰，故本文提出了一种应用自适应图像分割与曲线融合(AISCB)的人眼定位算法。首先

分析了眼睛灰度分布的特殊性，利用特定梯度算子及形态学膨胀元素的方向选择性定义了一种自适应图像分割方法，用于克服边缘及光照干扰；其次，借鉴混合积分投影思想，利用人眼灰度变化和灰度均值双重特点，给出了自适应权值投影曲线融合方法来增强算法的鲁棒性；最后，通过分析融合后曲线特点，分别实现了人眼区域的划分及眼睛精确定位。基于YaleB和JAFFE人脸库的实验表明，评价标准为derr<0.25时，该算法的平均定位正确率达到98.92%。表明AISCB算法对复杂光照及人脸边缘等适应性强，对眉毛、刘海及睫毛等头部部位不敏感，鲁棒性强。

Abstract

Traditional projection algorithms for eye location have a bad adaptation to face edge

expression and illumination

and they are affected by eyebrows

bangs and eye wrinkles easily. Aiming at the above problems

an algorithm of eye location based on Adaptive Image Segmentation and Curve Blending (AISCB) was proposed. Firstly

the specialty of eye gray distribution was analyzed

and an adaptive image segmentation method was defined by using the direction selectivity of gradient operators and certain expansion elements to overcome the influence of edge and illumination. Then

according to the concept of hybrid integral projection and the characteristics of both eye gray changes and gray mean value

the adaptive weight projection curve blending method was used to enhance algorithm's robustness. Finally

the division of face region and the accurate location of eyes were realized through analyzing the characteristics of fused curves. The experiments on YaleB and JAFFE face data libraries show that AISCB algorithm has a good adaptation to complex illumination and face edges

and it is not sensitive to eyebrows

bangs and other head sections. The correct rate of mean location can reach 98.92% when the evaluation criterion is less than 0.25.

关键词

Keywords

references

［1］李粉兰,徐可欣. 一种应用于人脸正面图像的眼睛自动定位算法［J］.光学精密工程，2006，14 (2): 320-326. LI F L, XU K X. An algorithm applied in frontal-view face images for automatically localizing eyes ［J］. Opt. Precision Eng., 2006, 14 (2): 320-326. (in Chinese)［2］周志宇,杨卫成,汪亚明,等. 应用梯度矢量流Snake和灰预测的人脸轮廓跟踪［J］. 光学精密工程，2011，19(11): 2744-2752.ZHOU ZH Y, YANG W CH, WANG Y M, et al.. Realization of face contour tracking by GVF Snake and grey prediction ［J］. Opt. Precision Eng., 2011, 19(11): 2744-2752. (in Chinese)［3］HANSEN D W, JI Q. In the eye of the beholder: a survey of models for eyes and gaze ［J］. IEEE Trans. Pattern Analysis and Machine Intelligence, 2010, 32(3): 478-500.［4］黄彬彬,唐琎. 一种新的人脸图像中眼睛定位方法［J］.液晶与显示，2009，24(2): 278-282.HUANG B B, TANG J. Novel method of eye detection in facial images ［J］. Chinese Journal of Liquid Crystals and Displays, 2009, 24(2):278-282. (in Chinese)［5］KIM H, KIM W. Eye detection in facial images using zernike moments with SVM ［J］. ETRI Journal, 2008, 30(2): 335-337. ［6］辜小花,龚卫国,杨利平. 有监督图优化保局投影［J］.光学精密工程，2011，19(3): 672-680. GU X H, GONG W G, YANG L P. Supervised graph-optimized locality preserving projections ［J］. Opt. Precision Eng., 2011, 19(3):672-680. (in Chinese)［7］王力,唐琎,许海柱. 一种基于Harris角点检测的快速瞳孔定位方法［J］.液晶与显示，2008，23(1): 87-90.WANG L, TANG J, XU H ZH. Fast pupils localization method based on Harris corner detection ［J］. Chinese Journal of Liquid Crystals and Displays, 2008, 23(1): 87-90. (in Chinese)［8］耿新,周志华,陈世福. 基于混合投影函数的眼睛定位［J］.软件学报，2003，14(8):1395-1399.GENG X, ZHOU ZH H, CHEN SH F. Eye location based on hybrid projection function ［J］. Journal of Software, 2003, 14(8):1395-1399. (in Chinese)［9］王文成,常发亮. 一种基于区域投影的人眼精确定位方法［J］.光电子激光，2011，22(4): 618-622.WANG W CH, CHANG F L. A precise eye localization method based on region projection ［J］. Journal of Optoelectronics Laser, 2011, 22(4):618-622. (in Chinese)［10］孟春宁,白晋军,张太宁,等. 基于梯度积分投影和最大期望算法的人眼定位［J］.光电子激光，2012，23(10): 1971-1976.MENG CH N, BAI J J, ZHANG T N, et al.. Eye localization based on gradient integral projection and expectation-maximization algorithm ［J］. Journal of Optoelectronics Laser, 2012,23(10):1971-1976. (in Chinese)［11］李光鑫,徐抒岩,吴伟平,等. Piella像素级多分辨率图像融合框架的扩展及其算法［J］.光学精密工程，2012，20(12): 2773-2780.LI G X, XU SH Y, WU W P，et al.. Extension of Piella pixel-level multiresolution image fusion framework and its algorithm ［J］. Opt. Precision Eng., 2012, 20(12): 2773-2780. (in Chinese)［12］JESORSKY O, KIRCHBERG K J, FRISHHOLZ R W. Robust face detection using the Hausdorff distance ［C］. Third International Conference on Audio and Video based Biometric Person Authentication, Halmstad, Sweden, 2001: 90-95.［13］LEE K C, HO J, KRIEGMAN D. Acquiring linear subspaces for face recognition under variable lighting ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 684-698.

Views

685

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Machine vision-based method for measuring micro-volume liquid in transparent tubes

Computed tomography image segmentation of cell pole piece via strip attention mechanism

Sand microscopic image segmentation with enhanced tuna swarm optimization exponential entropy

Five-axis CNC machining method for eyeglass lens edge profile

Brain tumor image segmentation based on Semantic Flow Guided Sampling and Attention Mechanism

Related Author

WANG Hao

LI Xinghui

XIAO Wei

QIANG Xiang

WANG Xiaohao

LIU Zefang

LONG Chao

LIU Xueshuan

Related Institution

Tsinghua Shenzhen International Graduate School， Tsinghua University

ICT Research Center， Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education， Chongqing University

College of Optoelectronic Engineering， Chongqing University

Project Management Center， Equipment Department of Rocket Force

College of Information， Chang'an University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰