结合轮廓与形状特征的仿射形状匹配

谷睿宇; 曾接贤; 符祥; 冷璐

doi:10.11834/jig.180039

图像理解和计算机视觉 | 浏览量 : 0 下载量: 110 CSCD: 0

PDF
导出
分享
收藏
专辑

结合轮廓与形状特征的仿射形状匹配
Affine shape matching by using feature combined with contour and shape
2018年23卷第10期页码：1530-1539
收稿：2018-02-08，

修回：2018-4-18，

纸质出版：2018-10-16
DOI： 10.11834/jig.180039
稿件说明：

移动端阅览

谷睿宇, 曾接贤, 符祥, 冷璐. 结合轮廓与形状特征的仿射形状匹配[J]. 中国图象图形学报, 2018,23(10):1530-1539. DOI： 10.11834/jig.180039.

Ruiyu Gu, Jiexian Zeng, Xiang Fu, Lu Leng. Affine shape matching by using feature combined with contour and shape[J]. Journal of Image and Graphics, 2018, 23(10): 1530-1539. DOI： 10.11834/jig.180039.

摘要

目的

针对仿射变换下形状匹配中存在的描述子对形状的描述能力不足，以及描述子计算耗时大的问题，改进基于所有图像点投影的方法，提出一种利用轮廓计算投影面积的仿射形状匹配算法。

方法

该算法分为粗匹配和精匹配两个阶段。粗匹配阶段以CSS角点作为备选特征点，首先统计轮廓投影面积分布作为特征点描述子；然后利用动态规划蚁群算法匹配两幅图片公共特征点序列，并将匹配好的特征点序列记为对应的新特征点；最后采用该新特征点划分目标曲线，得到对应的轮廓曲线；这一阶段的目的是对形状的筛选以及寻找一致的轮廓特征点，同时完成轮廓曲线的划分。精匹配阶段，采用小波仿射不变描述子，对粗匹配阶段匹配代价最小的5%的目标进行对应曲线匹配，得到精匹配阶段的匹配代价，从而实现对仿射目标的识别；精匹配弥补了描述子对轮廓细节描述不足的问题。

结果

算法的平均检索速度比传统基于形状投影分布描述子提高44.3%，在MPEG-7图像库上的检索效果为98.65%，在MPEG-7仿射图像库上的查准率与查全率综合评价指标比传统的基于形状投影分布描述子高3.1%，比形状上下文高25%。

结论

本文算法匹配效果好，效率高，抗噪性强，解决了仿射描述子计算速度慢、描述能力不足的问题，能有效地应用于仿射形状匹配与检索领域。

Abstract

Objective

An affine shape matching method using a projection area calculated with a contour is proposed to improve the computation speed and the discrimination ability of a descriptor during shape matching.

Method

The algorithm can be divided into the coarse and fine matching stages.The coarse matching stage aims to select the shape and find consistent feature points.Area is an important affine invariant.In the coarse matching stage

we use CSS corner points as alternative feature points

and the statistics of the contour projection area as the feature point descriptor.Then

the ant colony algorithm is employed in matching the public feature point sequence in the two pictures.Finally

the target curve is divided by the public feature point sequence to obtain the corresponding contour curve.We use low-dimensional descriptors in the rough matching phase to increase the matching speed.Then

in the precise matching stage

Affine invariant descriptors constructed by wavelet coefficients are used to describe the target curve segment

match the 5% target with the minimum cost of the first step

obtain the matching cost of the second phase

and achieve the recognition of the affine target.

Result

The average retrieval rate of this algorithm is higher than that of the traditional shape projection distribution descriptor by 44.3%

The retrieval result in the MPEG-7 image library is 98.65%.The comprehensive evaluation index of precision and recall ratio on the MPEG-7 affine image library is higher than those of the traditional shape projection distribution descriptor and the shape context by 3.1% and 25%

respectively.

Conclusion

The main contribution of the algorithm lies in the shape projection distribution descriptor that is calculated quickly by using the contour and the wavelet affine invariant that matches the target contour sub-curve and compensates the shortcoming of the description based on the projection area distribution.Moreover

this study addresses the problems of slow calculation speed and insufficient description ability of affine descriptors

and the proposed method has a certain anti-noise ability

which can be used effectively in the field of affine shape matching and retrieval.The strict affine invariance of the QSPD descriptor ensures the applicability of this method to affine transformation shapes.However

the algorithm is not applicable for targets with large shape changes because the calculation of the QSPD is based on global shape information.

关键词

Keywords

references

Zhou Y, Liu J T, Bai X.Research and perspective on shape matching[J].Acta Automatica Sinica, 2012, 38(6):889-910.

周瑜, 刘俊涛, 白翔.形状匹配方法研究与展望[J].自动化学报, 2012, 38(6):889-910. [DOI:10.3724/sp.j.1004.2014.00889]

Mokhtarian F, Abbasi S.Shape similarity retrieval under affine transforms[J].Pattern Recognition, 2002, 35(1):31-41.[DOI:10.1016/S0031-3203(01)00040-1]

Cui M, Femiani J, Hu J, et al.Curve matching for open 2D curves[J].Pattern Recognition Letters, 2009, 30(1):1-10.[DOI:10.1016/j.patrec.2008.08.013]

Mokhtarian F, Bober M.Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization[C]//Mathematical Morphology and ITS Applications To Signal Processing.2003: 13-14.

Fu H J, Tian Z, Ran M, et al.Novel affine-invariant curve descriptor for curve matching and occluded object recognition[J].IET Computer Vision, 2013, 7(4):279-292.[DOI:10.1049/iet-cvi.2012.0123]

Fan B, Wu F C, Hu Z Y.Robust line matching through line-point invariants[J].Pattern Recognition, 2012, 45(2):794-805.[DOI:10.1016/j.patcog.2011.08.004]

Prasad D K.Geometric primitive feature extraction-concepts, algorithms, and applications[D].Singapore: Nanyang Technological University, 2012.

Zhang G M, Sun X X, Zhang Y.New partial shape match method based on wavelet transform[J].Computer Engineering and Applications, 2017, 53(2):188-194.

张桂梅, 孙晓旭, 章毅.基于小波变换的局部形状匹配[J].计算机工程与应用, 2017, 53(2):188-194. [DOI:10.3778/j.issn.1002-8331.1504-0202]

Zhang G M, Jiang S B, Chu J.Affine registration based on chord height point and genetic algorithm[J].Acta Automatica Sinica, 2013, 39(9):1447-1457.

张桂梅, 江少波, 储珺.基于弦高点和遗传算法的仿射配准[J].自动化学报, 2013, 39(9):1447-1457. [DOI:10.3724/SP.J.1004.2013.01447]

Cai H, Zhu F.Shape matching method based on convex hull and multiscale integral features under affine transformation[J].Journal of Computer-Aided Design&Computer Graphics, 2017, 29(2):269-278.

蔡慧英, 朱枫.仿射变换下基于凸包和多尺度积分特征的形状匹配方法[J].计算机辅助设计与图形学学报, 2017, 29(2):269-278. [DOI:10.3969/j.issn.1003-9775.2017.02.008]

Flusser J, Suk T.Pattern recognition by affine moment invariants[J].Pattern Recognition, 1993, 26(1):167-174.[DOI:10.1016/0031-3203(93)90098-H]

Li Y C, Chen H X, Gao L.Object recognition for ANN based on affine invariant moments[J].Computer Engineering, 2004, 30(2):31-32, 143.

李迎春, 陈贺新, 高磊.基于仿射不变矩的神经网络目标识别[J].计算机工程, 2004, 30(2):31-32, 143. [DOI:10.3969/j.issn.1000-3428.2004.02.012]

Mei Y, Androutsos D.Robust affine invariant shape image retrieval using the ICA Zernike moment shape descriptor[C]//16th IEEE International Conference on Image processing.Cairo, Egypt: IEEE, 2009: 1065-1068.[ DOI: 10.1109/ICIP.2009.5413537 http://dx.doi.org/10.1109/ICIP.2009.5413537 ]

Wang Z Z, Liang M.Locally affine invariant descriptors for shape matching and retrieval[J].IEEE Signal Processing Letters, 2010, 17(9):803-806.[DOI:10.1109/LSP.2010.2057506]

Wang W, Xiong B L, Yan X W, et al.Affine invariant shape projection distribution for shape matching using relaxation labelling[J].IET Computer Vision, 2016, 10(2):124-133.[DOI:10.1049/iet-cvi.2014.0034]

Wang W.Image affine invariant feature extraction and matching[D].Changsha: National University of Defense Technology, 2013.

王玮.图像仿射不变特征提取及匹配技术研究[D].长沙: 国防科学技术大学, 2013.

Wang H B, Wang D B, Zhu J Q.Development on ant colony algorithm theory and its application[J].Control and Decision, 2004(12):1321-1326.

段海滨, 王道波, 朱家强.蚁群算法理论及应用研究的进展[J].控制与决策, 2004(12):1321-1326. [DOI:10.13195/j.cd.2004.12.1.duanhb.001]

Wang W.Research on image matching and retrieval algorithms based on shape feature[D].Nanchang: Nanchang Hangkong University, 2016.

王为.基于形状特征的图像匹配与检索算法研究[D].南昌: 南昌航空大学, 2016.

Belongie S, Malik J, Puzicha J.Shape Matching and Object Recognition Using Shape Contexts[M].IEEE Computer Society, 2002.[ DOI: 10.1109/34.993558 http://dx.doi.org/10.1109/34.993558 ]