基于局部二进制模式和图变换的快速匹配算法

doi:10.3969/j.issn.0372-2112.2017.09.015

电子学报 ›› 2017, Vol. 45 ›› Issue (9): 2156-2161.DOI: 10.3969/j.issn.0372-2112.2017.09.015

基于局部二进制模式和图变换的快速匹配算法

赵小强, 岳宗达

兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050

收稿日期:2016-01-06 修回日期:2016-03-23 出版日期:2017-09-25
- 作者简介:
- 赵小强,男,1969年生于陕西岐山.博士.现为兰州理工大学教授、博士生导师.主要研究方向为图像处理、数据挖掘、生产调度.E-mail:xqzhao@lut.cn;岳宗达,男,1990年生于山东阳谷.现为兰州理工大学电气工程与信息工程学院硕士研究生.主要研究方向为图像处理.E-mail:18793139585@163.com
- 基金资助:
- 国家自然科学基金 (No.51265032，No.61263003）

A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation

ZHAO Xiao-qiang, YUE Zong-da

College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou, Gansu 730050, China

Received:2016-01-06 Revised:2016-03-23 Online:2017-09-25 Published:2017-09-25
- Supported by:
- National Natural Science Foundation of China (No.51265032, No.61263003)

摘要/Abstract

摘要： 针对图像匹配在图像拼接、目标识别等领域的应用中尺度不变特征变换（Scale Invariant Feature Transform，SIFT）算法计算复杂度高、实时性较差的问题，提出了一种基于局部二进制模式（Local Binary Patterns，LBP）和图变换（Graph Transformation Matching，GTM）的匹配算法.首先采用SIFT特征检测提取特征点并以特征点为中心取13×13的图像块作为特征区域；然后用本文提出的局部旋转不变二进制模式（Local Rotation Invariant Binary Patterns，LRIBP）描述子对特征区域进行描述产生29维的特征描述向量，降低了描述子的复杂度，并以欧氏距离为度量准则进行初始匹配；最后采用图变换匹配算法剔除误匹配点，从而提高算法的运算速率和匹配精度.仿真结果表明，本文所提算法不仅具有较高的精度和较强的鲁棒性，并且减少了算法的运算量，提高了算法的实时性.

关键词: 图像匹配, 尺度不变特征变换, 局部二进制模式, 图变换匹配

Abstract: Aiming at problems of large computation and poor real-time of scale invariant feature transform (SIFT) algorithm for image matching application in image matching,object recognition and other fields,a matching algorithm based on local binary patterns (LBP) and graph transformation matching (GTM) is proposed.Firstly,SIFT is used to extract initial feature points.13×13 pixel blocks around the feature points are used as the feature regions.Secondly,in order to reduce complexity of descriptors,the local rotation invariant binary patterns (LRIBP) descriptor is used to produce feature vectors of 29 dimensions for a feature region.Euclidean distance is adopted as measure criterion of the descriptors to fulfil initial match.Finally,GTM is adopted to eliminate mismatching points.Simulation results show that the proposed algorithm not only improves accuracy and robustness and real-time,but also reduces the amount of calculation.

Key words: image matching, scale invariant feature transform, local binary patterns, graph transformation matching

中图分类号:

TG156

赵小强, 岳宗达. 基于局部二进制模式和图变换的快速匹配算法[J]. 电子学报, 2017, 45(9): 2156-2161.

ZHAO Xiao-qiang, YUE Zong-da . A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation[J]. Acta Electronica Sinica, 2017, 45(9): 2156-2161.

参考文献

[1] 沈同圣,张健,娄树理.面向目标检测的空间观测图像精确配准[J].光学精密工程,2014,22(8):2205-2213. Shen Tong-sheng,Zhang Jian,Lou Shu-li.Precise registration of space observation images for target detection[J].Optics and Precision Engineering,2014,22(8):2205-2213.(in Chinese)
[2] 常琳,金光,杨秀彬.航天TDI CCD相机成像拼接快速配准算法设计与分析[J].光学学报,2014,34(5):0511001-1-0511001-9. Chang Lin,Jin Guang,Yang Xiu-bin.Fast registration algorithm design and analysis of TDI CCD camera assembly imaging[J].Acta Optica Sinica,2014,34(5):051101-1-051101-9.(in Chinese)
[3] Furukawa Y,Ponce J.Accurate,dense and robust multiview stereopsis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(8):1362-1376.
[4] 王建,潘静薇,杨新.心肌灌注核磁共振图像的非刚性配准[J].中国图像图形学报,2013,18(6):661-668. Wang Jian,Pan Jing-wei,Yang Xin.Non-rigid registration for myocardial perfusion MR image[J].Journal of Image and Graphics,2013,18(6):661-668.(in Chinese)
[5] 陈文达,白瑞林,吉峰,等.基于机器视觉的轴承防尘盖表面缺陷检测[J].计算机工程与应用,2014,50(6):250-254. Chen Wen-da,Bai Rui-lin,Ji Feng,et al.Bearing shield surface defect detection based on machine vision[J].Computer Engineering and Applications,2014,50(6):250-254.(in Chinese)
[6] Lowe D G.Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110.
[7] Ojala T,Pietikainen M,Maenpaa T.Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[8] Heikkila M,Pietikainen M,Schmid C.Description of interest regions with local binary patterns[J].Pattern Recognition,2009,42(3):425-436.
[9] 郑永斌,黄新生,丰松江.SIFT和旋转不变LBP相结合的图像匹配算法[J].计算机辅助设计与图形学学报,2010,22(2):286-292. Zheng Yong-bin,Huang Xin-sheng,Feng Song-jiang.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):286-292.(in Chinese)
[10] 邱春玲,陶强,范润龙,等.基于局部二进制描述SIFT特征的锆石图像配准方法[J].吉林大学学报,2014,44(6):1793-1798. Qiu Chun-ling,Tao Qiang,Fan Run-long,et al.Zircon image marching method based on description of SIFT feature by LBP[J].Journal of Jilin University (Engineering and Technology Edition),2014,44(6):1793-1798.(in Chinese)
[11] 颜普,朱明,唐俊,梁栋.基于DCT和修正CSLBP的局部特征描述子[J].华中科技大学学报,2014,42(9):38-43. Yan Pu,Zhu Ming,Tang Jun,Liang Dong.Local feature descriptor based on DCT and modified CSLBP[J].J Huazhong Univ of Sci & Tech(Natural Science Edition),2014,42(9):38-43.(in Chinese)
[12] Aguilar W,Frauel Y,Escolano F,et al.A robust graph transformation matching for non-rigid registration[J].Image and Vision Computing,2009,27(7):897-910.
[13] Mikolajczyk K,Schmid C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.

基于局部二进制模式和图变换的快速匹配算法

A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

[1]	张峰, 钟宝江. 基于兴趣目标的图像检索[J]. 电子学报, 2018, 46(8): 1915-1923.
[2]	余旺盛, 李卫华, 侯志强. 分层结构直方图及其应用[J]. 电子学报, 2017, 45(11): 2617-2624.
[3]	王峰, 尤红建, 傅兴玉, 许宁. 应用于多源SAR图像匹配的级联SIFT算法[J]. 电子学报, 2016, 44(3): 548-554.
[4]	袁红星, 吴少群, 朱仁祥, 安鹏. 加权SIFT流深度迁移的单幅图像2D转3D[J]. 电子学报, 2015, 43(2): 242-247.
[5]	孙冬梅;裘正定. 利用薄板样条函数实现非刚性图像匹配算法[J]. 电子学报, 2002, 30(8): 1104-1107.