Abstract
In the field of industrial inspection, it is an urgent need to recognize and locate objects with similar transformation in real time. Current traditional methods cannot keep high robustness in illumination change, clutter, occlusion and other environments, and cannot match objects correctly when there is a rotation angle between the scene object and the given template. In order to solve the above problems, a fast and robust rotated template matching method is proposed in this paper. First, the algorithm uses the gradient of object edge points as the basic data of similarity measure function which has high robustness; Second, image pyramid technology is selected to reduce algorithm complexity; For edges, the maximum pyramid is designed to preserve the shape information to the greatest extent, and for gradients, the mean pyramid is designed to fully consider the neighborhood information. Third, down-sampling of feature points is adopted in accelerating the algorithm and combining rotated feature with image pyramid is adopted in solving rotated matching problem. Last, the least square adjustment is applied to improve the pose accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brown, L.G.: A survery of image registration techniques. ACM Comput. Surv. 24(4), 325–376 (1992)
Barnea, D.I., Silverman, H.F.: A class of algorithms for fast digital image registration. IEEE Trans. Comput. C-21(2), 179–186 (1972)
Vanne, J., Aho, E., Hamalainen, T.D., et al.: A high-performance sum of absolute difference implementation for motion estimation. IEEE Trans. Circ. Syst. Video Technol. 16(7), 876–883 (2006)
Stefano, L.D., Mattoccia, S., Mola, M.: An efficient algorithm for exhaustive template matching based on normalized cross correlation. IEEE Computer Society (2003)
Brogefors, G.: Hierarchical chamfer matching: a parametric edge matching algorithm. IEEE Trans. Pattern Anal. Mach. Intell. 10(6), 849–865 (2002)
Li, S., Hu, P., Yang, C.: Algorithm and application of Voronoi graph generation for graphic components. Comput. Eng. 31(10), 42–44 (2005)
Bai, C., Qi, C., Yang, Y., et al.: Hausdorff matching for fast detection of PCB benchmark markers. Optoelectron. Laser 17(4), 498–501 (2006)
Klauck, C., Muller, H., Chew, L.P., et al:. Geometric pattern matching under euclidean motion. Comput. Geom. 7(1) (1997)
Ullah, F., Kaneko, S.I.: Using orientation codes for rotation-invariant template matching. Pattern Recogn. 37(2), 201–209 (2004)
Tsai, D.M., Chiang, C.H.: Rotation-invariant pattern matching using wavelet decomposition. Pattern Recogn. Lett. 23(1–3), 191–201 (2002)
Prokop, R.J., Reeves, A.P.: A survey of moment-based techniques for unoccluded object representation and recognition. CVGIP Graph. Models Image Process. 54(5), 438–460 (1992)
Choi, M.S., Kim, W.Y.: A novel two stage template matching method for rotation and illumination invariance. Pattern Recogn. 35(1), 119–129 (2002)
Harris, C.G., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)
Tanaka, K., Sano, M., Ohara, S., et al.: A parametric template method and its application to robust matching. In: Computer Vision and Pattern Recognition, pp. 620–627 (2000)
Ulrich, M., Steger, C., Baumgartner, A., et al.: Real-time object recognition using a modified generalized Hough transform. Pattern Recogn. 36(11), 2557–2570 (2003)
Steger, C.: Similarity measures for occlusion, clutter, and illumination invariant object recognition (2001)
Steger, C.: Occlusion, clutter, and illumination invariant object recognition. In: International Archives of Photogrammetry and Remote Sensing, vol. XXXIV, Part 3A, pp. 345–350 (2002)
Tanimoto, S.L.: Template matching in pyramids. Comput. Graph. Image Process. 16(4), 356–369 (1981)
Ulrich, M., Steger, C.: Empirical performance evaluation of object recognition methods. In: Christensen, H.I., Phillips, P.J. (eds.) Empirical Evaluation Methods in Computer Vision, pp. 62–76. IEEE Computer Society Press, Los Alamitos (2001)
Acknowledgement
This research was partially supported by the key research project of Ministry of science and technology (Grant no. 2018YFB1306802 and no. 2017YFB1301503) and the National Nature Science Foundation of China (Grant no. 51575332).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Si, Y., Wang, W., Zheng, Z., Zhang, X. (2019). A Fast and Robust Template Matching Method with Rotated Gradient Features and Image Pyramid. In: Yu, H., Liu, J., Liu, L., Ju, Z., Liu, Y., Zhou, D. (eds) Intelligent Robotics and Applications. ICIRA 2019. Lecture Notes in Computer Science(), vol 11743. Springer, Cham. https://doi.org/10.1007/978-3-030-27538-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-27538-9_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27537-2
Online ISBN: 978-3-030-27538-9
eBook Packages: Computer ScienceComputer Science (R0)