Abstract
We present modifications in a local operator known as stroke width transform (SWT) in order to improve its performance to detect Race Bib Numbers (RBNs) from natural images of running competitions. The original SWT algorithm is a simple and yet one of the top competitive algorithms for text detection. The proposal adds a Hue channel similarity test in the neighborhoods of edge borders candidates, and it limits the length of the stroke according to aimed characters at the images. We tested the proposed, and the original approach, using a publicly available database of 217 images in different conditions. The suggested approach outperformed the original one, both in sizes of width maps, and on RBNs detection. This research is not an end-to-end RBNs recognition system, so we focused on the improvements of the SWT algorithm in order to provide a more efficient method for future use in automated systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1480–1500 (2015)
Ben-Ami, I., Basha, T., Avidan, S.: Racing bib numbers recognition. In: Proceedings of the British Machine Vision Conference, pp. 19.1–19.10. BMVA Press (2012)
Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2963–2970. IEEE (2010)
Jung, K., Kim, K.I., Jain, A.K.: Text information extraction in images and video: a survey. Pattern Recogn. 37, 977–997 (2004)
Mosleh, A., Bouguila, N., Hamza, A.B.: Image text detection using a bandlet-based edge detector and stroke width transform. In: Proceedings of the British Machine Vision Conference, pp. 1–12. BMVA Press (2012)
Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1083–1090. IEEE (2012)
Paul, S., Saha, S., Basu, S., Nasipuri, M.: Text localization in camera captured images using adaptive stroke filter. In: Mandal, J.K., Satapathy, S.C., Sanyal, M.K., Sarkar, P.P., Mukhopadhyay, A. (eds.) Information Systems Design and Intelligent Applications. AISC, vol. 340, pp. 217–225. Springer, New Delhi (2015). https://doi.org/10.1007/978-81-322-2247-7_23
Koschan, A., Abidi, M.: Digital Color Image Processing. Wiley, Hoboken (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
de Jesus, W.M., Borges, D.L. (2018). An Improved Stroke Width Transform to Detect Race Bib Numbers. In: Martínez-Trinidad, J., Carrasco-Ochoa, J., Olvera-López, J., Sarkar, S. (eds) Pattern Recognition. MCPR 2018. Lecture Notes in Computer Science(), vol 10880. Springer, Cham. https://doi.org/10.1007/978-3-319-92198-3_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-92198-3_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92197-6
Online ISBN: 978-3-319-92198-3
eBook Packages: Computer ScienceComputer Science (R0)