吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (03): 711-717.doi: 10.7964/jdxbgxb201303026

• 论文 • 上一篇    下一篇

旋转不变性图像模板匹配快速算法

谢志江1,2, 吕波1, 刘琴1, 陈平1   

  1. 1. 重庆大学 机械传动国家重点实验室,重庆 400044;
    2. 重庆大学 机械工程学院,重庆 400044
  • 收稿日期:2012-03-27 出版日期:2013-05-01 发布日期:2013-05-01
  • 作者简介:谢志江(1963-),男,教授,博士生导师.研究方向:机器视觉,模式识别,设备状态监测与故障诊断. E-mail:xzj99@vip.sina.com
  • 基金资助:

    国家自然科学基金项目(10976034).

Rotation-invariant and fast image template matching algorithm

XIE Zhi-jiang1,2, LYU Bo1, LIU Qin1, CHEN Ping1   

  1. 1. State Key Lab of Mechanical Transmissions, Chongqing University, Chongqing 400044, China;
    2. College of Mechanical Engineering, Chongqing University, Chongqing 400044, China
  • Received:2012-03-27 Online:2013-05-01 Published:2013-05-01

摘要: 综合利用图像梯度幅值统计的旋转不变性,梯度角度统计的旋转迁移性以及图像梯度角度统计的旋转自相关系数分布对称性,基于图像的3种不同特征,分两步精确快速地完成了统计匹配运算.仿真试验结果显示:本文算法在模板图像发生任意角度旋转的情况下匹配性能好.该算法时间复杂度小,并且在模板图像灰度发生一定程度的非线性变换、缩放、遮挡等情况时仍具有良好的鲁棒性能.

关键词: 计算机应用, 模板匹配, 图像梯度, 旋转不变性, 图像梯度角度统计, 图像梯度幅值统计

Abstract: A rotation-invariant algorithm use for image template matching is proposed. This algorithm utilizes the rotation invariance of the image gradient amplitude, the rotation migration of the image gradient angle, and the distribution symmetry of the autocorrelation coefficient of the image gradient angle. The algorithm is divided into two steps to complete precisely and rapidly statistical and matching calculation based on three types of different characteristics of the images. Simulation results show that the algorithm can precisely locate the template image, which is with arbitrary angle. The algorithm has good real-time matching performance and less time-complexity. Even in the case of nonlinear transformation with image grayscale, image scaling and image occlusion, the template matching operation using this algorithm has strong robustness.

Key words: computer application, template matching, image gradient, rotation-invariant, statistics of image gradient angle, statistics of image gradient amplitude

中图分类号: 

  • TP391.4
[1] Huttenlocher D P, Klanderman G A, Kl G A, et al. Comparing images using the hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9):850-863.

[2] Huttenlocher D P, Lilien R H, Olson C F. View-based recognition using an eigenspace approximation to the hausdorff measure[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(9): 951-955.

[3] Wei S D, Lai S H. Fast template matching based on normalized cross correlation with adaptive multilevel winner update[J]. IEEE Transaction on Image Processing, 2008, 17(11):2227-2235.

[4] 沙莎,刘锦峰.基于差分有序数组的图像匹配快速算法[J].微计算机信息,2007,23(8):296-298. Sha Sha, Liu Jin-feng. Fast image matching algorithm based on differential ordinal array[J]. Microcomputer Information, 2007, 23(8):296-298.

[5] Baek G, Kim S. Two step template matching method with correlation coefficient and genetic algorithm//Proceeding ICIC'09 Proceedings of the Intelligent Computing 5th International Conference on Emerging Intelligent Computing Technology and Applications, Berlin, Heidelberg,2009:85-90.

[6] 李强,张钹. 一种基于图像灰度的快速匹配算法[J].软件学报, 2006, 17(2):216-222. Li Qiang,Zhang Bo. A fast matching algorithm based on image gray value[J]. Journal of Software, 2006,17(2):216-222.

[7] Hu M K. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory, 1962, 8(2):179-187.

[8] Choi M S, Kim W Y. A novel two stage template matching method for rotation and illumination invariance[J]. Pattern Recognition, 2002, 35(1):119-129.

[9] 傅卫平,秦川,刘佳,等. 基于SIFT算法的图像目标匹配与定位[J]. 仪器仪表学报, 2011, 32(1):163-169. Fu Wei-ping, Qin Chuang, Liu Jia, et al. Matching and location of image object based on SIFT algorithm[J]. Chinese Journal of Scientific Instrument, 2011, 32(1):163-169.

[10] 郑永斌,黄新生, 丰松江,等. SIFT和旋转不变LBP 相结合的图像匹配算法[J]. 计算机辅助设计及图形学报, 2010, 22(2):286-291. Zheng Yong-bin, Huang Xin-sheng, Feng Song-jiang,et al. An image matching algorithm based on combination of SIFT and the rotation invariant LBP[J] .Journal of Computer-Aided Design & Computer Graphics, 2010, 22(2):286-291.

[11] Kim H Y. Rotation-discriminating template matching based on Fourier coefficients of radial projections with robustness to scaling and partial occlusion[J]. Pattern Recognition, 2010, 43(3):859-872.

[12] Yang T, Lai S H, Chang L W. Hybrid image matching combining Hausdorff distance with normalized gradient matching[J]. Pattern Recognition, 2007, 40(4):1173-1181.

[13] Satoh S. Simple low-dimensional features approximating NCC-based image matching[J]. Pattern Recognition Letters, 2011, 32(14):1902-1911.
[1] 刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2] 王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3] 金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4] 赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5] 刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6] 欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[7] 刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[8] 桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[9] 刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[10] 车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11] 赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12] 黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13] 傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14] 曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15] 侯永宏, 王利伟, 邢家明. 基于HTTP的动态自适应流媒体传输算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!