Abstract
Existing edge detection methods are based on fixed logics, which are not intelligent enough to distinguish useful edges and useless/noise edges. Recent ellipse detection methods developed some excellent algorithms that can still detect ellipses, while a large number of noise edges exist. However, these algorithms are compromised that will lose some precision and recall. This paper proposes a deep learning model that can intelligently distinguish useful edges and useless edges. Therefore, high-quality edge maps with low noise can be obtained. An arc-growing-based ellipse detection method is also proposed to take full advantage of the high-quality edge maps. Experiments are performed to reveal the mechanism of the deep learning model and to verify the performance of the proposed method. The experimental results demonstrate that the proposed method performs far better than the state-of-the-art in terms of precision, recall and the F-measure on industrial images and performs slightly better on natural images.
Similar content being viewed by others
References
Fornaciari, M., Prati, A., Cucchiara, R.: A fast and effective ellipse detector for embedded vision applications. Pattern Recogn. 47(11), 3693–3708 (2014)
Cakir, H.I., Benligiray, B., Topal, C.: Combining feature-based and model-based approaches for robust ellipse detection. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp. 2430–2434. IEEE (2016)
Liang, J., Wang, Y., Zeng, X.: Robust ellipse fitting via half-quadratic and semidefinite relaxation optimization. IEEE Trans. Image Process. 24(11), 4276–4286 (2015)
Hu, Z., Feipeng, D., Qin, L.: Self-calibration using two same circles. Chin. J. Sci. Instrum. 3, 618–624 (2010)
Teutsch, C., Berndt, D., Trostmann, E., Weber, M.: Real-time detection of elliptic shapes for automated object recognition and object tracking. In: Machine Vision Applications in Industrial Inspection XIV, vol. 6070, p. 60700. International Society for Optics and Photonics (2006)
Soetedjo, A., Yamada, K.: Fast and robust traffic sign detection. In: 2005 IEEE International Conference on Systems, Man and Cybernetics, vol. 2, pp. 1341–1346. IEEE (2005)
Ono, K., Ogawa, T., Maeda, Y., Nakatani, S., Nagayasu, G., Shimizu, R., Ouchi, N.: Detection, localization and picking up of coil springs from a pile. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 3477–3482. IEEE (2014)
Chia, A.Y.-S., Rahardja, S., Rajan, D., Leung, M.K.: A split and merge based ellipse detector with self-correcting capability. IEEE Trans. Image Process. 20(7), 1991–2006 (2010)
Prasad, D.K., Leung, M.K., Cho, S.-Y.: Edge curvature and convexity based ellipse detection method. Pattern Recogn. 45(9), 3204–3221 (2012)
Duda, R.O., Hart, P.E.: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11–15 (1972)
Zhang, S.-C., Liu, Z.-Q.: A robust, real-time ellipse detector. Pattern Recogn. 38(2), 273–287 (2005)
Sewisy, A.A., Leberl, F.: Detection ellipses by finding lines of symmetry in the images via an Hough transform applied to straight lines. Image Vis. Comput. 19(12), 857–866 (2001)
Guil, N., Zapata, E.L.: Lower order circle and ellipse Hough transform. Pattern Recogn. 30(10), 1729–1744 (1997)
Xu, L., Oja, E., Kultanen, P.: A new curve detection method: randomized Hough transform (rht). Pattern Recogn. Lett. 11(5), 331–338 (1990)
Kiryati, N., Eldar, Y., Bruckstein, A.M.: A probabilistic Hough transform. Pattern Recogn. 24(4), 303–316 (1991)
Grbić, R., Grahovac, D., Scitovski, R.: A method for solving the multiple ellipses detection problem. Pattern Recogn. 60, 824–834 (2016)
Mai, F., Hung, Y., Zhong, H., Sze, W.: A hierarchical approach for fast and robust ellipse extraction. Pattern Recogn. 41(8), 2512–2524 (2008)
Kim, E., Haseyama, M., Kitajima, H.: Fast and robust ellipse extraction from complicated images. In: Proceedings of IEEE Information Technology and Applications. Citeseer (2002)
Prasad, D.K., Leung, M.K., Quek, C.: Ellifit: an unconstrained, non-iterative, least squares based geometric ellipse fitting method. Pattern Recogn. 46(5), 1449–1465 (2013)
Dong, H., Chen, I.-M., Prasad, D.K.: Robust ellipse detection via arc segmentation and classification. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 66–70. IEEE (2017)
Meng, C., Li, Z., Bai, X., Zhou, F.: Arc adjacency matrix-based fast ellipse detection. IEEE Trans. Image Process. 29, 4406–4420 (2020)
Lu, C., Xia, S., Shao, M., Fu, Y.: Arc-support line segments revisited: an efficient high-quality ellipse detection. IEEE Trans. Image Process. 29, 768–781 (2020)
Yuen, H., Illingworth, J., Kittler, J.: Detecting partially occluded ellipses using the Hough transform. Image Vis. Comput. 7(1), 31–37 (1989)
Chia, A.Y.S., Leung, M.K., Eng, H.-L., Rahardja, S.: Ellipse detection with Hough transform in one dimensional parametric space. In: 2007 IEEE International Conference on Image Processing, vol. 5, p. 333. IEEE (2007)
Xie, Y., Ji, Q.: A new efficient ellipse detection method. In: Object Recognition Supported by User Interaction for Service Robots, vol. 2, pp. 957–960. IEEE (2002)
Lu, T., Hu, W., Liu, C., Yang, D.: Effective ellipse detector with polygonal curve and likelihood ratio test. IET Comput. Vis. 9(6), 914–925 (2015)
Fornaciari, M., Prati, A.: Very fast ellipse detection for embedded vision applications. In: 2012 Sixth International Conference on Distributed Smart Cameras (ICDSC), pp. 1–6. IEEE (2012)
Jia, Q., Fan, X., Luo, Z., Song, L., Qiu, T.: A fast ellipse detector using projective invariant pruning. IEEE Trans. Image Process. 26(8), 3665–3679 (2017)
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986)
Sobel, I., Feldman, G.: A \(3\times 3\) isotropic gradient operator for image processing. A talk at the Stanford Artificial Project in 271–272 (1968)
Pătrăucean, V., Gurdjos, P., Von Gioi, R.G.: A parameterless line segment and elliptical arc detector with enhanced ellipse fitting. In: European Conference on Computer Vision, pp. 572–585. Springer (2012)
Guo, Z., Hall, R.W.: Parallel thinning with two-subiteration algorithms. Commun. ACM 32(3), 359–373 (1989)
Lam, L., Lee, S.-W., Suen, C.Y.: Thinning methodologies-a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 14(9), 869–885 (1992)
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)
Marošević, T., Scitovski, R.: Multiple ellipse fitting by center-based clustering. Croat. Oper. Res. Rev. 6(1), 43–53 (2015)
Morales-Esteban, A., Martínez-Álvarez, F., Scitovski, S., Scitovski, R.: A fast partitioning algorithm using adaptive Mahalanobis clustering with application to seismic zoning. Comput. Geosci. 73, 132–141 (2014)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)
Funding
Funding was provided by National Key Research and Development Program of China (Grant No. 2016YFE0206200) and National Natural Science Foundation of China (Grant Nos. U1613205, 51675291)
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.
Rights and permissions
About this article
Cite this article
Liu, C., Chen, R., Chen, K. et al. Ellipse detection using the edges extracted by deep learning. Machine Vision and Applications 33, 63 (2022). https://doi.org/10.1007/s00138-022-01319-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00138-022-01319-5