Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
SpringerLink
Log in

Ultrarobust support vector registration

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

An iterativeframework based on finding point correspondences and estimating the transformation function is widely adopted for nonrigid point set registration. However, correspondences established based on feature descriptors are likely to be inaccurate. In this paper, we propose a novel transformation model that can learn from such correspondences. The model is built by means of weighted support vector (SV) regression with a quadratic ε-insensitive loss and manifold regularization. The loss is insensitive to noise, and the regularization forces the transformation function to preserve the intrinsic geometry of the input data. To assess the confidences of correspondences, we introduce a probabilistic model that is solved using the expectation maximization (EM) algorithm. Then, we input the confidences into the transformation model as instance weights to guide model training. We use the coordinate descent method to solve the transformation model in a reproducing kernel Hilbert space and accelerate its speed by means of sparse approximation. Extensive experiments show that our approach is efficient and outperforms other state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data Availability

The literature or website sources of the experimental data have been provided in the form of references or footnotes. In addition, we also list the website links for the data in the literature:

Synthetic data

https://www.cise.ufl.edu/~anand/students/chui/

https://github.com/yinlei19/Synthetic_data

IMM face database

http://www.imm.dtu.dk/~aam/

3d point sets

http://tosca.cs.technion.ac.il/book/resources_data.html

Notes

  1. http://cmp.felk.cvut.cz/data/geometry2view/index.xhtml

  2. https://www.cs.ubc.ca/~lowe/keypoints/

References

  1. Aronszajn N (1950) Theory of reproducing kernels. Trans Am Math Soc 68(3):337–404

    Article  MathSciNet  Google Scholar 

  2. Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434

    MathSciNet  MATH  Google Scholar 

  3. Belongie SJ, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522

    Article  Google Scholar 

  4. Belongie SJ, Mori G, Malik J (2006) Matching with shape contexts. In: Statistics and analysis of shapes. Birkhäuser, Boston, pp 81–105

  5. Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239–256

    Article  Google Scholar 

  6. Bronstein AM, Bronstein MM, Kimmel R (2006) Efficient computation of isometry-invariant distances between surfaces. SIAM J Sci Comput 28(5):1812–1836

    Article  MathSciNet  Google Scholar 

  7. Campbell D, Petersson L (2015) An adaptive data representation for robust point-set registration and merging. In: IEEE International conference on computer vision, pp 4292–4300

  8. Carmeli C, Vito ED, Toigo A (2006) Vector valued reproducing kernel hilbert spaces of integrable functions and mercer theorem. Anal Appl 4(4):377–408

    Article  MathSciNet  Google Scholar 

  9. Cherkassky VS, Ma Y (2004) Practical selection of svm parameters and noise estimation for svm regression. Neural Netw 17(1):113–126

    Article  Google Scholar 

  10. Cherkassky VS, Mulier F (1998) Learning from data: concepts, theory, and methods. Wiley, New York

    MATH  Google Scholar 

  11. Chui H, Rangarajan A (2003) A new point matching algorithm for non-rigid registration. Comput Vis Image Underst 89(2):114–141

    Article  Google Scholar 

  12. Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395

    Article  MathSciNet  Google Scholar 

  13. Frome A, Huber D, Kolluri R, Bülow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: European conference on computer vision, pp 224–237

  14. Gold S, Rangarajan A, Lu CP, Pappu S, Mjolsness E (1998) New algorithms for 2d and 3d point matching: pose estimation and correspondence. Pattern Recogn 31(8):1019–1031

    Article  Google Scholar 

  15. Jian B, Vemuri BC (2011) Robust point set registration using gaussian mixture models. IEEE Trans Pattern Anal Mach Intell 33(8):1633–1645

    Article  Google Scholar 

  16. Li W, Zhao X, Peng J, Luo Z, Shen L, Han H, Zhang P, Yang L (2020) A new geolocation error estimation method in mwri data aboard fy3 series satellites. IEEE Geosci Remote Sens Lett 17 (2):197–201

    Article  Google Scholar 

  17. Ling H, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29(2):286– 299

    Article  Google Scholar 

  18. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60 (2):91–110

    Article  Google Scholar 

  19. Ma J, Qiu W, Zhao J, Ma Y, Yuille AL, Tu Z (2015) Robust l2e estimation of transformation for non-rigid registration. IEEE Trans Signal Process 63(5):1115–1129

    Article  MathSciNet  Google Scholar 

  20. Ma J, Wu J, Zhao J, Jiang J, Zhou H, Sheng QZ (2019) Nonrigid point set registration with robust transformation learning under manifold regularization. IEEE Trans Neural Netw Learn Syst 30 (12):3584–3597

    Article  MathSciNet  Google Scholar 

  21. Ma J, Zhao J, Jiang J, Zhou H, Guo X (2019) Locality preserving matching. Int J Comput Vis 127(5):512–531

    Article  MathSciNet  Google Scholar 

  22. Ma J, Zhao J, Tian J, Bai X, Tu Z (2013) Regularized vector field learning with sparse approximation for mismatch removal. Pattern Recogn 46(12):3519–3532

    Article  Google Scholar 

  23. Ma J, Zhao J, Tian J, Yuille AL, Tu Z (2014) Robust point matching via vector field consensus. IEEE Trans Image Process 23(4):1706–1721

    Article  MathSciNet  Google Scholar 

  24. Ma J, Zhao J, Yuille AL (2016) Non-rigid point set registration by preserving global and local structures. IEEE Trans Image Process 25(1):53–64

    Article  MathSciNet  Google Scholar 

  25. Myronenko A, Song XB (2010) Point set registration: coherent point drift. IEEE Trans Pattern Anal Mach Intell 32(12):2262–2275

    Article  Google Scholar 

  26. Papadimitriou CH, Steiglitz K (1998) Combinatorial optimization: algorithms and complexity. Courier Corporation

  27. Rangarajan A, Chui H, Mjolsness E, Pappu S, Davachi L, Goldman-Rakic PS, Duncan JS (1997) A robust point-matching algorithm for autoradiograph alignment. Med Image Anal 1(4):379–398

    Article  Google Scholar 

  28. Rifkin R, Yeo G, Poggio T (2003) Regularized least-squares classification. Nato Science Series Sub Series III Computer and Systems Sciences 190:131–154

    Google Scholar 

  29. Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (fpfh) for 3d registration. In: IEEE International conference on robotics and automation, pp 1848–1853

  30. Rusu RB, Marton ZC, Blodow N, Dolha M, Beetz M (2008) Towards 3d point cloud based object maps for household environments. Robot Auton Syst 56(11):927–941

    Article  Google Scholar 

  31. Stegmann M, Ersboll B, Larsen R (2003) Fame-a flexible appearance modeling environment. IEEE Trans Med Imaging 22(10):1319–1331

    Article  Google Scholar 

  32. Timofte R, Kwon J, Gool LV (2016) Picaso: pixel correspondences and soft match selection for real-time tracking. Comput Vis Image Underst 153:151–162

    Article  Google Scholar 

  33. Vedaldi A, Fulkerson B (2010) Vlfeat: an open and portable library of computer vision algorithms. In: Proceedings of the 18th ACM international conference on multimedia, pp 1469–1472

  34. Wang G, Chen Y, Zheng X (2018) Gaussian field consensus: a robust nonparametric matching method for outlier rejection. Pattern Recogn 74:305–316

    Article  Google Scholar 

  35. Wang G, Wang Z, Chen Y, Zhao W (2015) A robust non-rigid point set registration method based on asymmetric gaussian representation. Comput Vis Image Underst 141:67–80

    Article  Google Scholar 

  36. Wang G, Zhou Q, Chen Y (2017) Robust non-rigid point set registration using spatially constrained gaussian fields. IEEE Trans Image Process 26(4):1759–1769

    Article  MathSciNet  Google Scholar 

  37. Wang L, Gao C, Zhao N, Chen X (2019) A projection wavelet weighted twin support vector regression and its primal solution. Appl Intell 49(8):3061–3081

    Article  Google Scholar 

  38. Wells WM (1997) Statistical approaches to feature-based object recognition. Int J Comput Vis 21(1):63–98

    Article  Google Scholar 

  39. Weng R, Lu J, Hu J, Yang G, Tan YP (2013) Robust feature set matching for partial face recognition. In: IEEE International conference on computer vision, pp 601–608

  40. Yang L, Dong H (2019) Robust support vector machine with generalized quantile loss for classification and regression. Appl Soft Comput 81:105483

    Article  Google Scholar 

  41. Yang Y, Ong SH, Foong KWC (2015) A robust global and local mixture distance based non-rigid point set registration. Pattern Recogn 48(1):156–173

    Article  Google Scholar 

  42. Zhao J, Ma J, Tian J, Ma J, Zhang D (2011) A robust method for vector field learning with application to mismatch removing. In: IEEE Conference on computer vision and pattern recognition, pp 2977–2984

  43. Zhao J, Xu Y, Fujita H (2019) An improved non-parallel universum support vector machine and its safe sample screening rule. Knowledge Based Systems 170:79–88

    Article  Google Scholar 

  44. Zheng Y, Doermann DS (2006) Robust point matching for nonrigid shapes by preserving local neighborhood structures. IEEE Trans Pattern Anal Mach Intell 28(4):643–649

    Article  Google Scholar 

Download references

Funding

This work is supported in part by NSFC grants 61772011, 61977021, 61871177, and Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province (No. CICIP2018002).

Author information

Authors and Affiliations

  1. Hubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, 430062, China

    Lei Yin & Bin Zou

  2. Mornengchen Intelligent Technology Co. Ltd., Shanghai, 200090, China

    Chong Yu

  3. Department Electrical Engineering, ETH Zurich, Zurich, 358092, Switzerland

    Yuyi Wang

  4. Theory Lab, Huawei 2012 Lab, Shanghai, 201206, China

    Yuyi Wang

  5. Faculty of Science and Technology, University of Macau, Macau, 999078, China

    Yuan Yan Tang

Authors
  1. Lei Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chong Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuyi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bin Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuan Yan Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bin Zou.

Additional information

Code Availability

The pseudocode of the algorithm is shown in Algorithm 1. The proposed algorithm can be easily implemented according to the pseudocode.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yin, L., Yu, C., Wang, Y. et al. Ultrarobust support vector registration. Appl Intell 51, 3664–3683 (2021). https://doi.org/10.1007/s10489-020-01967-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-020-01967-y

Keywords

Search

Navigation