范文写作网 > 理工毕业论文 > > 基于典型相关分析方法的尺度不变特征变换误匹配剔除(3)
理工毕业论文

基于典型相关分析方法的尺度不变特征变换误匹配剔除(3)

摘要:四、结语 本文针对SIFT描述子对具有相似灰度分布区域的图像易产生误匹配的缺点,提出了一种基于典型相关分析的误匹配剔除方法。该方法首先通过典型相关分析对SIFT匹配后的特征点对的位置关系进行重新描述,利用典型
关键词:基于,典型,相关,分析,方法,尺度,不变,特征,变换,匹配,

不知火舞18p,千载醉翁亭,冯矿伟新浪博客首页

  四、结语

  本文针对SIFT描述子对具有相似灰度分布区域的图像易产生误匹配的缺点,提出了一种基于典型相关分析的误匹配剔除方法。该方法首先通过典型相关分析对SIFT匹配后的特征点对的位置关系进行重新描述,利用典型相关成分拟合直线剔除大部分误匹配; 然后通过分析每对匹配对典型相关成分共线率的影响迭代剔除误匹配,克服了过度剔除正确匹配的缺点; 最后,模拟和真实实验的结果验证了方法的有效性和可行性。阈值T2与匹配精度之间的定量关系有待进一步研究。

  参考文献

  [1] LIU Z, QIAO H, YANG X, et al.Graph matching by simplified convexconcave relaxation procedure[J]. International Journal of Computer Vision, 2014, 109(3): 1-18.

  [2] FENG W, LIU Z, WAN L, et al.A spectralmultiplicitytolerant approach to robust graph matching[J]. Pattern Recognition, 2013, 46(10): 2819-2829.

  [3] KANG U, HEBERT M, PARK S. Fast and scalable approximate spectral graph matching for correspondence problems[J]. Information Sciences, 2013, 220(20): 306-318.

  [4] WANG H, HANCOCK E R. A kernel view of spectral point pattern matching[J]. Structural, Syntactic, and Statistical Pattern Recognition, 2004, 3138: 361-369.

  [5] LOWE D G. Distinctive image features from scaleinvariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

  [6] BAY H, ESS A, TUYTELAARS T, et al.SpeededUp Robust Features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

  [7] TEKE M, VURAL M F, TEMIZEL A, et al.Highresolution multispectral satellite image matching using scale invariant feature transform and speeded up robust features[J]. Journal of Applied Remote Sensing, 2011, 5(1): 53553.

  [8] YANG L, TIAN Z, ZHAO W. A new affine invariant feature extraction method for SAR image registration[J]. International Journal of Remote Sensing, 2014, 35(20): 7219-7229.

  [9] FISCHLER M A, BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.

  [10] KIM T, IM Y. Automatic satellite image registration by combination of matching and random sample consensus[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(5): 1111-1117.

  [11] KUPFER B, NETANYAHU N S, SHIMSHONI I. An efficient SIFTbased modeseeking algorithm for subpixel registration of remotely sensed images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(2): 379-383.

  [12] MOISAN L, MOULON P, MONASSE P. Automatic homographic registration of a pair of images, with a contrario elimination of outliers[J]. Image Processing On Line, 2012, 2: 56-73.

  [13] AGUILAR W, FRAUEL Y, ESCOLANO F, et al.A robust graph transformation matching for nonrigid registration[J]. Image and Vision Computing, 2009, 27(7): 897-910.

  [14] YAN W, TIAN Z, WEN J, et al.SIFT mismatching correction based on partial least squares[J]. Journal of Computer Applications, 2012, 32(5): 1255-1268.(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): 1255-1268.)

上一篇:粗决策树动态规则提取算法研究及应用 下一篇:没有了