基于方向梯度极值的手形轮廓跟踪算法

苑玮琦; 董 茜; 桑海峰

doi:10.3788/OPE.20101807.1675

您当前的位置：

首页 >

文章列表页 >

基于方向梯度极值的手形轮廓跟踪算法

信息科学 | 更新时间：2020-08-12

- 基于方向梯度极值的手形轮廓跟踪算法
- Hand shape contour tracking method based on directional gradient extremum
- 光学精密工程 2010年18卷第7期页码：1675-1683
- 作者机构：
  
  沈阳工业大学视觉检测技术研究所,辽宁沈阳,110178
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.60672078();No.60972123)();辽宁省教育厅2009年度高等学校科研基金资助项目(No.2009A561)()
- DOI：10.3788/OPE.20101807.1675
  中图分类号：
- 收稿日期：2009-09-07，
  
  修回日期：2009-11-10，
  
  网络出版日期：2010-07-30，
  
  纸质出版日期：2010-07-20
- 稿件说明：
移动端阅览
苑玮琦, 董茜, 桑海峰. 基于方向梯度极值的手形轮廓跟踪算法[J]. 光学精密工程, 2010,18(7): 1675-1683

YUAN Wei-qi, DONG Qian, SANG Hai-feng. Hand shape contour tracking method based on directional gradient extremum[J]. 光学精密工程, 2010,18(7): 1675-1683
苑玮琦, 董茜, 桑海峰. 基于方向梯度极值的手形轮廓跟踪算法[J]. 光学精密工程, 2010,18(7): 1675-1683 DOI： 10.3788/OPE.20101807.1675.

YUAN Wei-qi, DONG Qian, SANG Hai-feng. Hand shape contour tracking method based on directional gradient extremum[J]. 光学精密工程, 2010,18(7): 1675-1683 DOI： 10.3788/OPE.20101807.1675.

摘要

针对受自然光照影响的手形图像难以准确提取手形轮廓的问题

本文基于手形边界像素在垂直于边界方向上存在灰度突变的特性

提出了一种基于方向梯度极值的手形轮廓跟踪算法。该算法首先找到手形轮廓的起始点

然后按照一定的搜索方向和规则

在局部区域内计算候选点集中梯度极大值所在的点

并逐点跟踪极大值点

得到手形轮廓。将该方法在实验室自采图库及香港科技大学(HKUST)的手形图像库两个数据库中进行轮廓跟踪实验

结果显示

自采图库的跟踪准确率为100%

香港科技大学手形图像库的跟踪准确率为85.8%

该库中符合本文算法限制条件的图像的跟踪准确率为99.4%。实验结果表明

该方法能在灰度图像上直接跟踪出准确、连续、完整的手形轮廓

尤其适合于受光照不均影响的手形图像的边缘提取。

Abstract

Hand contours are hard to be extracted correctly when hand images are illuminated by a unsymmetrical light.Therefore

this paper proposes a contour tracking algorithm based on the directional maximal gradient value according to the characteristic that values of edge pixels turn sharply in the vertical direction of an edge. The algorithm firstly finds the starting point of hand contour

then depending on some searching rules

it calculates the gradient values of candidate points in a local region

chooses the point whose gradient value is maximal in the candidate set of local region and tracks it point by point to get the final contour. Tracking experiments are carried out on both the hand image database formed by ourselves and the HandImage database from Hong Kong University of Science and Technology(HKUST) .Experimental results indicate that the accuracy of contour tracking is 100% in ourselves database

and 85.8% in the database from HKUST.Moreover

the accuracy of contour tracking in the images eligible to our refined condition from HKUST database is 99.4%. These data show that the algorithm can directly track out the accurate

consecutive and integral hand contour in gray-level picture and it is suitable especially for the contour extraction of hand images affected by the unsymmetrical illumination.

关键词

Keywords

references

SANCHEZ R R , SANCHEZ A C , GONZALEZ M A . Biometric identification through hand geometry measurements [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(10):1168-1171.

SANCHEZ R R. Hand geometry pattern recognition through Gaussian mixture modeling . Proceedings of 15th International Conference on Pattern Recognition, Washington, USA:IEEE Computer Society Press, 2000:2937-2940.

JAIN A, NANDAKUMAR K, ROSS A. Score normalization in multimodal biometric systems[J]. Pattern Recognition, 2005,38:2270-2285.

ANDREAS U, PETER W. Personal recognition using single-sensor multimodal hand biometrics . Proceedings of the 3rd international conference on Image and Signal Processing, France, 2008:396-404.

TADEJ S, NIKOLA P. Personal recognition based on an image of the palmar surface of the hand [J]. Pattern Recognition, 2007,40:3152-3163.

RIBARIC S, RIBARIC D, PAVESIC N. Multimodal biometric user-identification system for network-based applications . IEE Proceedings-Vision Image and Signal Processing,2003,409-416.

JAIN A K, DUTA N. Deformable matching of hand shapes for verification . IEEE International Conference on Image Processing, Kobe, Japan, 1999:857-861.

OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979,9(1):62-66.

聂祥飞,郭军. 利用Gabor小波变换解决人脸识别中的小样本问题[J]. 光学精密工程,2007,15(6):973-977. NIE X F, GUO J. Solution of small sample size problem in face recognition using Gabor wavelet transform[J].Opt. Precision Eng.,2007,15(6):973-977.(in Chinese)

付鹏,裘正定. 一种新颖的手形特征提取算法[J]. 信号处理,2003,19(z1):324-327. FU P, QIU ZH D. A novel feature extraction algorithm[J]. Signal Processing, 2003,19(z1):324-327.(in Chinese)

顾理,庄镇泉. 一种基于模板匹配的手形认证算法[J]. 计算机工程与应用,2005,41(6):85-88. GU L,ZHUANG ZH Q. A method of hand shape verification based on template matching rules[J]. Computer Engineering and Applications,2005,41(6):85-88.(in Chinese)

孙冬梅,裘正定,何冰. 一种基于手形特征点匹配的身份认证方法[J]. 电子与信息学报,2003,2(3):412-418. SUN D M,QIU ZH D,HE B. Automated identity verification based on feature points matching of hand shape[J]. Journal of Electronics and information technology,2003,2(3):412-418.(in Chinese)

付树军,阮秋琦,穆成坡,等. 基于非线性扩散滤波的边缘检测和图像测量[J]. 光学精密工程,2007,15(2):289-293. FU SH J, RUAN Q Q, MU CH P, et al.. Edge detection for image measurement based on nonlinear diffusion filtering[J].Opt. Precision Eng.,2007,15(2):289-293.(in Chinese)

顾理,庄镇泉,万淑超,等. 手形识别中的手形提取方法[J]. 计算机仿真,2005,22(7):128-132. GU L, ZHUANG ZH Q, WAN SH CH, et al.. Method of hand shape extracting in hand shape recognition[J]. Computer Simulation, 2005,22(7):128-132.(in Chinese)

聂祥飞,谭泽富,郭军. 应用小波变换的人脸光照补偿[J]. 光学精密工程,2008,16(1):150-155. NIE X F, TAN Z F, GUO J. Face illumination compensation based on wavelet transform[J]. Opt. Precision Eng., 2008,16(1):150-155.(in Chinese)

HKUST Hand Image database . http://visgraph.cs.ust.hk/biometrics/Visgraph_web/index.html.

浏览量

336

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

小模数直齿轮免参数并行快速测量

面向小目标测量的通道注意力网络与系统设计

强噪声下自适应Canny算子边缘检测

基于导向滤波Retinex和自适应Canny的图像边缘检测

Canny算子在PCBA目标边缘提取中的优化应用