Abstract
Thin line defect is a common and critical kind of tire defect, which may result in serious accidents. This paper proposes a novel adaptive threshold based model for thin line defects detection in tire X-ray images. First, a new adaptive binarization algorithm using column based threshold selecting is proposed. The proposed algorithm outperforms previous algorithms in hard examples, without introducing extra spots or distortions to the original defect area. Next, a tire X-ray image segmentation algorithm is developed, which can divide the image into sectors with different texture features. Finally, an adaptive criterion algorithm is introduced for thin line defection, which can deal with images from different angles of shooting. The proposed model is evaluated on a tire X-ray data set composed of tire images of various thin line types. Experimental results demonstrate that the proposed model obtains significant improvement in terms of both recall rate and precision rate compared with conventional models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Technical Research Centre of Finland (VTT) Intelligent tyre systems – state of the art and potential technologies; Deliverable D7 (2001)
Koornstra, M.K.: Transport safety performance in the EU [EB/OL]. European Transport Safety Council, Brussels, 20 November 2012
Zhang, Y., Lefebvre, D., Li, Q.: Automatic detection of defects in tire radiographic images. IEEE Trans. Autom. Sci. Eng. 14(3), 1378–1386 (2017)
Guo, Q., Zhang, C., Liu, H., et al.: Defect detection in tire X-ray images using weighted texture dissimilarity. J. Sens. 1, 1–12 (2016)
Yue, Z., Wenyao, L., Hua, Y., et al.: A defect extraction and segmentation method for radial tire X-ray image. J. Optoelectron. 21(05), 758–761 (2010)
Aradhya, V.N.M.: A comprehensive of transforms, Gabor filter and k-means clustering for text detection in images and video. Appl. Comput. Informatics 12(2), 109–116 (2016)
Ostu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Wang, J., Hong, J.: A new self-adaptive weighted filter for removing noise in infrared images. In: International Conference on Information Engineering and Computer Science (2009)
Michael, H.F.W.: Gaussian-weighted moving-window robust automatic threshold selection. In: International Conference on Computer Analysis of Images and Patterns (2003)
Serra, J.: Image Analysis and Mathematical Morphology. Academic Press, Inc., Orlando (1983)
Couprie, M., Bezerra, N., Bertrand, G.: A parallel thinning algorithm for grayscale images. In: Gonzalez-Diaz, R., Jimenez, M.-J., Medrano, B. (eds.) DGCI 2013. LNCS, vol. 7749, pp. 71–82. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37067-0_7
Saeed, K., Tab, M., Rybnik, M., Adamski, M.: K3M: a universal algorithm for image skeletonization and a review of thinning techniques. Int. J. Appl. Math. Comput. Sci. 20(2), 317–335 (2010)
Yue, Z.: Study on X-ray image inspection technology of engineering radial tire. Tianjin University, Tianjin (2009)
Xiang, Y., Zhang, C., Guo, Q.: A dictionary-based method for tire defect detection. In: Proceeding of the IEEE International Conference on Information and Automation, Hailar, China, July 2014
Mak, K.L., Peng, P., Yiu, K.F.C.: Fabric defect detection using morphological filters. Image Vis. Comput. 27, 1585–1592 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Y., Gu, N., Zhang, X., Lin, C. (2020). Tire X-ray Image Defects Detection Based on Adaptive Thresholding Method. In: Shen, H., Sang, Y. (eds) Parallel Architectures, Algorithms and Programming. PAAP 2019. Communications in Computer and Information Science, vol 1163. Springer, Singapore. https://doi.org/10.1007/978-981-15-2767-8_11
Download citation
DOI: https://doi.org/10.1007/978-981-15-2767-8_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2766-1
Online ISBN: 978-981-15-2767-8
eBook Packages: Computer ScienceComputer Science (R0)