结合颜色不变量的SIFT和形状上下文图像匹配算法

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z11): 144-146.

结合颜色不变量的SIFT和形状上下文图像匹配算法

徐衍鲁,马燕,李顺宝,张相芬

上海师范大学信息与机电工程学院上海200234;上海师范大学信息与机电工程学院上海200234;上海师范大学数理学院上海200234;上海师范大学信息与机电工程学院上海200234

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金项目(61373004)资助

Algorithm of Image Matching Based on Color SIFT and Shape Context

XU Yan-lu,MA Yan,LI Shun-bao and ZHANG Xiang-fen

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对传统图像匹配算法sift和shape-context存在的不足,把这两种算法分别作了改进,并提出一种二者相结合的混合匹配算法。首先在传统sift算法的基础上融入图像的颜色信息,即加入颜色不变量,构建彩色描述子；在shape-context算法中改用基于重心点的形状上下文直方图,代替传统的基于各个轮廓点的形状上下文直方图,生成形状上下文描述子。然后把这两种描述子级联成新的联合描述子,依据设定的新的联合距离对特征点进行匹配,得到初始匹配对。最后利用偏最小二乘法消除误匹配,得到精确匹配点对。实验结果表明,提出的算法能够有效提高图像匹配准确率。

关键词: SIFT,颜色不变量,形状上下文,描述子,图像匹配,偏最小二乘法,误匹配

Abstract: This paper presented a new image matching algorithm based on improved sift and shape-context,and aimed to solve the disadvantages of conventional sift and shape-context algorithm.We took color invariant into consideration and constructed color sift descriptors.In shape context algorithm,shape context histogram based on central points is used instead of the traditional shape context histogram based on contour points.Then the new joint descriptors combining with sift and shape context are applied to lead the feature points matching according to the new given joint distance and achieve the initial matching pairs.Finally,the partial least squares method is used to eliminate mismatching points.The experimental results show that the proposed algorithm can improve image matching accuracy effectively.

Key words: SIFT,Color invariance,Shape context,Descriptor,Image matching,PLS,Mismatching

徐衍鲁,马燕,李顺宝,张相芬. 结合颜色不变量的SIFT和形状上下文图像匹配算法[J]. 计算机科学, 2014, 41(Z11): 144-146. https://doi.org/

XU Yan-lu,MA Yan,LI Shun-bao and ZHANG Xiang-fen. Algorithm of Image Matching Based on Color SIFT and Shape Context[J]. Computer Science, 2014, 41(Z11): 144-146. https://doi.org/

参考文献

[1] Azad P,Asfour T,Dillmann R.Combining Harris InterestPoints and the SIFT Descriptor for Fast Scale-Invariant Object Recognition[C]∥Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems.2009:4275-4280
[2] Rassem T H,Khoo B E.Object Class Recognition using Combination of Color SIFT Descriptors[C]∥Proceedings of IEEE Ima-ging Systems and Techniques (IST).2011:290-295
[3] Geng Cong,Jiang Xu-dong.SIFT Features for Face Recognition[C]∥Proceedings of IEEE International Conference on Computer Science and Information Technology (ICCSIT).2009:598-602
[4] Bastanlar Y,Temizel A,Yardimci Y.Improved SIFT matching for image pairs with scale difference [J].Electronics Letters,2010,46(5):1-2
[5] Huang Lei,Li Zhen.Feature-based image registration using the shape context [J].Remote Sensing,2010,31(8):2169-2177
[6] 杨恒,王庆.一种新的局部不变特征检测和描述算法[J].计算机学报,2010,33(5):935-944
[7] Geusebroek J-M,van den Boomgaard R,Smeulders A W M.ColorInvariance[C]∥Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence.2001:1338-1350
[8] 肖潇,王宪保,王守觉.一种边缘点特征图像配准算法[J].小型微型计算机系统,2012,33(11):622-627
[9] Wold H.Path models with latent variables:The NIPALS approach [C]∥Proceedings of Quantitative Sociology:International Perspectives on Mathematical and Statistical Model Buil-ding.1975:307-357
[10] Salve S G,Jondhale K C.Shape Matching and Object Recognition Using Shape Contexts[C]∥Proceedings of IEEE Computer Science and Information Technology (ICCSIT).2010:471-474
[11] 延伟东,田铮,温金环,等.基于偏最小二乘的SIFT误匹配校正方法[J].计算机应用,2012,32(5):1255-1257,1268
[12] 刘岩,吕肖庆,秦叶阳,等.尺度与颜色不变性图像特征描述[J].小型微型计算机系统,2012,33(10):2297-2302
[13] Salve S G,Jondhale K C.Shape Matching and Object Recognition Using Shape Contexts[C]∥Proceedings of IEEE International Conference on Computer Science and Information Technology (ICCSIT).2010:471-474
[14] Abdel-Hakim A E,Farag A A.CSIFT:A SIFT Descriptor with Color Invariant Characteristics[C]∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition(CVPR).2006:1-6

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed