A Prototype Model for Semantic Segmentation of Curvilinear Meandering Regions by Deconvolutional Neural Networks

  • 1 Polish Naval Academy, , Gdynia, Poland

Abstract

Deconvolutional neural networks are a very accurate tool for semantic image segmentation. Segmenting curvilinear meandering regions is a typical task in computer vision applied to navigational, civil engineering, and defence problems. In the study, such regions of interest are modelled as meandering transparent stripes whose width is not constant. The stripe on the white background is formed by the upper and lower non-parallel black curves so that the upper and lower image parts are completely separated. An algorithm of generating datasets of such regions is developed. It is revealed that deeper networks segment the regions more accurately. However, the segmentation is harder when the regions become bigger. This is why an alternative method of the region segmentation consisting in segmenting the upper and lower image parts by subsequently unifying the results is not effective. If the region of interest becomes bigger, it must be squeezed in order to avoid segmenting the empty image. Once the squeezed region is segmented, the image is conversely rescaled to the original view. To control the accuracy, the mean BF score having the least value among the other accuracy indicators should be maximised first.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] H.-J. He, C. Zheng, and D.-W. Sun, “Image Segmentation Techniques,” in: Computer Vision Technology for Food Quality Evaluation, 2nd edition, Sun D.-W. (ed.). Academic Press, San Diego, 2016, pp. 45–63. https://doi.org/10.1016/B978-0-12-802232-0.00002-5

  • [2] Ç. Kaymak and A. Uçar, “A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving,” in: Handbook of Deep Learning Applications. Smart Innovation, Systems and Technologies, Balas V., Roy S., Sharma D., Samui P. (eds). Springer, Cham, 2019, pp. 161–198. https://doi.org/10.1007/978-3-030-11479-4_9

  • [3] G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The Mapillary Vistas dataset for semantic understanding of street scenes,” 2017 IEEE International Conference on Computer Vision, Venice, 2017, pp. 5000–5009. https://doi.org/10.1109/ICCV.2017.534

  • [4] J. Rogowska, “Overview and Fundamentals of Medical Image Segmentation,” in: Handbook of Medical Image Processing and Analysis, 2nd edition, Bankman I. N. (ed.). Academic Press, San Diego, 2009, pp. 73–90. https://doi.org/10.1016/B978-012373904-9.50013-1

  • [5] H. Liu, J. Xu, Y. Wu, Q. Guo, B. Ibragimov, and L. Xing, “Learning deconvolutional deep neural network for high resolution medical image reconstruction,” Information Sciences, vol. 468, pp. 142–154, 2018. https://doi.org/10.1016/j.ins.2018.08.022

  • [6] Larsson C. Clustering, in: 5G Networks, Larsson C. (ed.). Academic Press, San Diego, 2018, pp. 123–141. https://doi.org/10.1016/B978-0-12-812707-0.00011-5

  • [7] Shapiro L. G., Stockman G. C. Computer Vision. Prentice-Hall, New Jersey, 2001.

  • [8] Sethian J. A. A fast marching level set method for monotonically advancing fronts. Proceedings of the National Academy of Sciences, 93(4): 1591–1595, 1996. http://dx.doi.org/10.1073/pnas.93.4.1591

  • [9] V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A deep convolutional encoder-decoder architecture for image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, iss. 12, pp. 2481–2495, 2017. https://doi.org/10.1109/TPAMI.2016.2644615

  • [10] V. V. Romanuke, “Generator of a toy dataset of multi-polygon monochrome images for rapidly testing and prototyping semantic image segmentation networks,” Electrical, Control and Communication Engineering, vol. 15, no. 2, pp. 1–8, 2019. https://doi.org/10.2478/ecce-2019-0008

  • [11] V. V. Romanuke, “An infinitely scalable dataset of single-polygon grayscale images as a fast test platform for semantic image segmentation,” KPI Science News, no. 1, pp. 24–34, 2019. https://doi.org/10.20535/kpisn.2019.1.157259

OPEN ACCESS

Journal + Issues

Search