Abstract
A method of text detection in natural images, to be turned into an effective embedded software on a mobile device, shall be both efficient and lightweight. We observed that a simple method based on the morphological Laplace operator is very appropriate: we can construct in quasi-linear time a hierarchical image decomposition/simplification based on its 0-crossings, and search for some text in the resulting tree. Yet, for this decomposition to be sound, we need “0-crossings” to be Jordan curves, and to that aim, we rely on some discrete topology tools. Eventually, the hierarchical representation is the morphological tree of shapes of the Laplacian sign (ToSL). Moreover, we provide an algorithm with linear time complexity to compute this representation. We expect that the proposed hierarchical representation can be useful in some applications other than text detection.
Thierry Géraud: This work has been conducted in the context of the mobidem project, part of the “Systematic Paris-Region” and “Images & Network” Clusters (France). This project is partially funded by the French Gov. and its economic development agencies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We will see later that we actually do not interpolate the Laplacian image, but proceed as if there were an interpolation. Practically, it means that we avoid the need of multiplying by 4 the number of pixels in the process.
- 2.
Note that the two identical local configurations enclosed by red rectangles in Fig. 7(a) do not lead to the same interpolation; this is due to the non-local interpolation process that depends on the outer region, which is different in the two cases: respectively negative for the top configuration, and positive for the bottom one.
References
Blayvas, I., Bruckstein, A., Kimmel, R.: Efficient computation of adaptive threshold surfaces for image binarization. Pattern Recogn. 39(1), 89–101 (2006)
Boutry, N., Géraud, T., Najman, L.: How to make nD functions digitally well-composed in a self-dual way. In: Benediktsson, J.A., Chanussot, J., Najman, L., Talbot, H. (eds.) ISMM 2015. LNCS, vol. 9082, pp. 561–572. Springer, Cham (2015). doi:10.1007/978-3-319-18720-4_47
Boutry, N., Géraud, T., Najman, L.: On making nD images well-composed by a self-dual local interpolation. In: Barcucci, E., Frosini, A., Rinaldi, S. (eds.) DGCI 2014. LNCS, vol. 8668, pp. 320–331. Springer, Cham (2014). doi:10.1007/978-3-319-09955-2_27
Carlinet, E., Géraud, T.: A comparative review of component tree computation algorithms. IEEE Trans. Image Process. 23(9), 3885–3895 (2014)
Crozet, S., Géraud, T.: A first parallel algorithm to compute the morphological tree of shapes of \(n\)D images. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp. 2933–2937 (2014)
Géraud, T., Carlinet, E., Crozet, S.: Self-duality and digital topology: links between the morphological tree of shapes and well-composed gray-level images. In: Benediktsson, J.A., Chanussot, J., Najman, L., Talbot, H. (eds.) ISMM 2015. LNCS, vol. 9082, pp. 573–584. Springer, Cham (2015). doi:10.1007/978-3-319-18720-4_48
Géraud, T., Carlinet, E., Crozet, S., Najman, L.: A quasi-linear algorithm to compute the tree of shapes of nD images. In: Hendriks, C.L.L., Borgefors, G., Strand, R. (eds.) ISMM 2013. LNCS, vol. 7883, pp. 98–110. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38294-9_9
Huỳnh, L.D., Xu, Y., Géraud, T.: Morphology-based hierarchical representation with application to text segmentation in natural images. In: Proceedings of the International Conference on Pattern Recognition (ICPR) (2016, to appear). http://www.lrde.epita.fr/theo/papers/huynh.2016.icpr.pdf
Khalimsky, E., Kopperman, R., Meyer, R.: Computer graphics and connected topologies on finite ordered sets. Topol. Appl. 36, 1–17 (1990)
Latecki, L.J.: 3D well-composed pictures. GMIP 59(3), 164–172 (1997)
Latecki, L.J., Eckhardt, U., Rosenfeld, A.: Well-composed sets. Comput. Vis. Image Underst. 61(1), 70–83 (1995)
van Vliet, L., Young, I., Beckers, G.: An edge detection model based on non-linear laplace filtering. In: Proceedings of International Workshop on PRAI, pp. 63–73 (1988)
van Vliet, L., Young, I., Beckers, G.: A non-linear laplace operator as edge detector in noisy images. CVGIP 45(2), 167–195 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Huỳnh, L.D., Xu, Y., Géraud, T. (2017). Morphological Hierarchical Image Decomposition Based on Laplacian 0-Crossings. In: Angulo, J., Velasco-Forero, S., Meyer, F. (eds) Mathematical Morphology and Its Applications to Signal and Image Processing. ISMM 2017. Lecture Notes in Computer Science(), vol 10225. Springer, Cham. https://doi.org/10.1007/978-3-319-57240-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-57240-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57239-0
Online ISBN: 978-3-319-57240-6
eBook Packages: Computer ScienceComputer Science (R0)