Abstract
Hypergraphs are tools for matching of point-features incorporating spatial relationships in the form of hyperedges exhibiting topological and geometric features between the points of images to be matched. Considering all possible hyperedges is computationally expensive and are randomly chosen in the state of the art techniques. A Helly Hypergraph based Matching Framework (HHMF) is proposed for the matching of images using point-features with effective hyperedges. The framework includes proposed algorithms such as Construction of Hyperedges using Point-features by Random (CHPR), Combinatorial (CHPC), and Exhaustive (CHPE) sampling techniques with and without Helly selection. The resultant hyperedges are treated with Adaptive Block Co-ordinate Ascent Graph Matching with Integer Projected Fixed Point algorithm. The performance of the proposed framework is evaluated in terms of Accuracy, Matching score, Execution time and Tensor Size for synthetic point sets and Willow wine image dataset. Based on the experimental studies carried out against existing framework, CHPC, and CHPE with Helly selection, exhibited better performance with 73.88% & 81% accuracy for 53.64 & 14.8% reduced tensor size respectively, in deformation noise tests, and 98% & 96% accuracy for 97% & 70% reduced tensor size in outlier tests. In the implicit experimental comparisons within sampling techniques, CHPR, and CHPE provided better performance with 81.37%, and 76% accuracy. In general, HHMF framework has reduced the tensor size and execution time for deterministic sampling cases during point sets matching. The framework can be extended in the near future by incorporating learning schemes for automated hypergraph based point sets matching.
Similar content being viewed by others
References
Ali-Sisto D, Packalen P (2017) Forest Change Detection by Using Point Clouds from Dense Image Matching Together with a LiDAR-Derived Terrain Model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10(3):1197–1206. https://doi.org/10.1109/JSTARS.2016.2615099
Awrangjeb M, Lu G (2008) An improved curvature scale-space corner detector and a robust corner matching approach for transformed image identification. IEEE Trans Image Process 17(12):2425–2441. https://doi.org/10.1109/TIP.2008.2006441
Bretto A, Azema J, Cherifi H, Laget B (1997) Combinatorics and Image Processing. Graphical Models and Image Processing 59(5):265–277. https://doi.org/10.1006/gmip.1997.0437
Bretto A, Cherifi H, Ubéda S (2001) An efficient algorithm for Helly property recognition in a linear hypergraph. In Electronic Notes in Theoretical Computer Science (Vol. 46, pp. 181–191). https://doi.org/10.1016/S1571-0661(04)80985-X
Bretto A, Ubéda S, Eerovnik J (2002) A polynomial algorithm for the strong Helly property. Inf Process Lett. https://doi.org/10.1016/S0020-0190(01)00186-7
Chui H, Rangarajan A (2003) A new point matching algorithm for non-rigid registration. Comput Vis Image Underst 89(2–3):114–141. https://doi.org/10.1016/S1077-3142(03)00009-2
Dharmarajan R (2016) Studies in Hypergraphs with a few applications in Image Processing (Doctoral dissertation). SASTRA Deemed to be University, Thanjavur
Dongxiang Z, Yun-Hui L, Xuanping C (2004) An efficient and robust corner detection algorithm. In Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on (Vol. 5, p. 4020–4024). https://doi.org/10.1109/WCICA.2004.1342254
Dourado MC, Lin MC, Protti F, Szwarcfiter JL (2008) Improved algorithms for recognizing p-Helly and hereditary p-Helly hypergraphs. Inf Process Lett 108(4):247–250. https://doi.org/10.1016/j.ipl.2008.05.013
Dourado MC, Protti F, Szwarcfiter JL (2006) Computational aspects of the Helly property: a survey. J Braz Comput Soc 12(1):7–33. https://doi.org/10.1007/BF03192385
Duchenne O, Bach F, Kweon IS, Ponce J (2011) A tensor-based algorithm for high-order graph matching. IEEE Trans Pattern Anal Mach Intell 33(12):2383–2395. https://doi.org/10.1109/TPAMI.2011.110
Gong M, Zhao S, Jiao L, Tian D, Wang S (2014) A novel coarse-to-fine scheme for automatic image registration based on SIFT and mutual information. IEEE Trans Geosci Remote Sens 52(7):4328–4338. https://doi.org/10.1109/TGRS.2013.2281391
Hartley R, Zisserman A (2004) Multiple view geometry in computer vision. Cambridge University Press, New York, p 673
Kahaki SMM, Jan Nordin M, Ashtari AH, Zahra SJ (2016) Deformation invariant image matching based on dissimilarity of spatial features. Neurocomputing 175:1009–1018. https://doi.org/10.1016/j.neucom.2015.09.106
Kannan K, Kanna BR, Aravindan C (2010) Root mean square filter for noisy images based on hyper graph model. Image Vis Comput 28(9):1329–1338. https://doi.org/10.1016/j.imavis.2010.01.013
Lee J, Cho M, Lee KM (2011) Hyper-graph matching via reweighted random walks. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1633–1640). https://doi.org/10.1109/CVPR.2011.5995387
Leordeanu, M., & Hebert, M. (2005). A spectral technique for correspondence problems using pairwise constraints. In Proceedings of the IEEE International Conference on Computer Vision (Vol. II, pp. 1482–1489). https://doi.org/10.1109/ICCV.2005.20
Lin MC, Szwarcfiter JL (2007) Faster recognition of clique-Helly and hereditary clique-Helly graphs. Inf Process Lett 103(1):40–43. https://doi.org/10.1016/j.ipl.2007.02.017
Liu, Y., Nie, L., Han, L., Zhang, L., & Rosenblum, D. S. (2015). Action2Activity: Recognizing complex activities from sensor data. IJCAI International Joint Conference on Artificial Intelligence, 1617–1623
Liu Y, Nie L, Liu L, Rosenblum DS (2016) From action to activity: Sensor-based activity recognition. Neurocomputing 181:108–115. https://doi.org/10.1016/j.neucom.2015.08.096
Liu Y, Zhang L, Nie L, Yan Y, Rosenblum DS (2016) Fortune teller: predicting your career path. Proceedings of the 30th Conference on Artificial Intelligence (AAAI 2016), (1), 201–207
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27(10):1615–1630. https://doi.org/10.1109/TPAMI.2005.188
Ng ES, Kingsbury NG (2012) Robust pairwise matching of interest points with complex wavelets. IEEE Trans Image Process 21(8):3429–3442. https://doi.org/10.1109/TIP.2012.2195012
Nguyen Q, Tudisco F, Gautier A, Hein M (2017) An Efficient Multilinear Optimization Framework for Hypergraph Matching. IEEE Trans Pattern Anal Mach Intell 39(6):1054–1075. https://doi.org/10.1109/TPAMI.2016.2574706
Rajesh Khanna B (2012) Development of hypergraph based techniques for selected image engineering applications. Dissertation, SASTRA Deemed to be University, Thanjavur
Somu N, Kirthivasan K, Shankar SS (2017) A computational model for ranking cloud service providers using hypergraph based techniques. Futur Gener Comput Syst 68:14–30. https://doi.org/10.1016/j.future.2016.08.014
Yan J, Li C, Li Y, Cao G (2018) Adaptive Discrete Hypergraph Matching. IEEE Transactions on Cybernetics 48(2):765–779. https://doi.org/10.1109/TCYB.2017.2655538
Yan J, Zhang C, Zha H, Liu W, Yang X, Chu SM (2015) Discrete hyper-graph matching. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition:1520–1528. https://doi.org/10.1109/CVPR.2015.7298759
Zass R, Shashua A (2008) Probabilistic graph and hypergraph matching. In 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. https://doi.org/10.1109/CVPR.2008.4587500
Zhang H, Ren P (2017) Game theoretic hypergraph matching for multi-source image correspondences. Pattern Recogn Lett 87:87–95. https://doi.org/10.1016/j.patrec.2016.07.011
Acknowledgements
This work was supported by the Council of Scientific and Industrial Research, the premier research and development organization in India, under the Senior Research Fellowship Scheme. (grant number 09/1095/(0009)/2015-EMR-I).The second author wishes to thank Department of Science & Technology –Science and Engineering Research Board for the financial support through FIST No.: SR/FST/MSI-107/2015 and TATA Realty IT city-SASTRA Srinivasan Ramanujan Research Cell.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Rights and permissions
About this article
Cite this article
Divya Lakshmi K., Rajappa, M., Krithivasan, K. et al. Helly hypergraph based matching framework using deterministic sampling techniques for spatially improved point feature based image matching. Multimed Tools Appl 78, 14657–14681 (2019). https://doi.org/10.1007/s11042-018-6852-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6852-1