Generator of a Toy Dataset of Multi-Polygon Monochrome Images for Rapidly Testing and Prototyping Semantic Image Segmentation Networks

Vadim Romanuke

doi:10.2478/ecce-2019-0008

Generator of a Toy Dataset of Multi-Polygon Monochrome Images for Rapidly Testing and Prototyping Semantic Image Segmentation Networks

Authors

Vadim Romanuke Polish Naval Academy https://orcid.org/0000-0003-3543-3087

DOI:

https://doi.org/10.2478/ecce-2019-0008

Keywords:

Dataset complexity, Multi-polygon object, Semantic image segmentation, Segmentation network architecture, Toy dataset, Two-class segmentation

Abstract

In the paper, the problem of building semantic image segmentation networks in a more efficient way is considered. Building a network capable of successfully segmenting real-world images does not require a real semantic image segmentation task. At this stage, called prototyping, a toy dataset can be used. Such a dataset can be artificial and thus may not need augmentation for training. Besides, its entries are images of much smaller size, which allows training and testing the network a way faster. Objects to be segmented are one or few convex polygons in one image. Thus, a toy dataset generator is created whose complexity is regulated by the number of edges in a polygon, the maximal number of polygons in one image, the set of scale factors, and the set of probabilities determining how many polygons in a current image are generated. The dataset capacity and image size are concurrently adjustable, although they are much less influential.

References

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

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

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

J.-T. Chien, “Deep Neural Network,” in: Source Separation and Machine Learning, Chien J.-T. (ed.). Academic Press, 2019, pp. 259–320. https://doi.org/10.1016/B978-0-12-804566-4.00019-X

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, no. 12, pp. 2481–2495, 2017. https://doi.org/10.1109/TPAMI.2016.2644615

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

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

J.-J. Lv, X.-H. Shao, J.-S. Huang, X.-D. Zhou, and X. Zhou, “Data augmentation for face recognition,” Neurocomputing, vol. 230, pp. 184–196, 2017. https://doi.org/10.1016/j.neucom.2016.12.025

V. Romanuke, “Optimal training parameters and hidden layer neuron number of two-layer perceptron for generalised scaled object classification problem,” Information Technology and Management Science, vol. 18, no. 1, pp. 42–48, 2015. https://doi.org/10.1515/itms-2015-0007

H. Hofbauer, E. Jalilian, and A. Uhl, “Exploiting superior CNN-based iris segmentation for better recognition accuracy,” Pattern Recognition Letters, vol. 120, pp. 17–23, 2019. https://doi.org/10.1016/j.patrec.2018.12.021

V. V. Romanuke, “Appropriateness of DropOut layers and allocation of their 0.5 rates across convolutional neural networks for CIFAR-10, EEACL26, and NORB datasets,” Applied Computer Systems, vol. 22, no. 1, pp. 54–63, 2017. https://doi.org/10.1515/acss-2017-0018

V. V. Romanuke, “An attempt of finding an appropriate number of convolutional layers in CNNs based on benchmarks of heterogeneous datasets,” Electrical, Control and Communication Engineering, vol. 14, no. 1, pp. 51–57, 2018. https://doi.org/10.2478/ecce-2018-0006

D. Avis, H. ElGindy, and R. Seidel, “Simple On-Line Algorithms for Convex Polygons”, in: Machine Intelligence and Pattern Recognition (vol. 2), Toussaint G. T. (ed.). North-Holland, 1985, pp. 23–42. https://doi.org/10.1016/B978-0-444-87806-9.50007-4

E. Horowitz and M. Papa, “Polygon Clipping: Analysis and Experiences”, in: Theoretical Studies in Computer Science, Ullman J. D. (ed.). Academic Press, 1992, pp. 315–339. https://doi.org/10.1016/B978-0-12-708240-0.50016-2

M. A. Rahman and Y. Wang, “Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation”, in: Advances in Visual Computing (ISVC 2016), Bebis G. et al. (eds). Springer, Cham, 2016, pp. 234–244. https://doi.org/10.1007/978-3-319-50835-1_22

P. M. Radiuk, “Impact of training set batch size on the performance of convolutional neural networks for diverse datasets,” Information Technology and Management Science, vol. 20, no. 1, pp. 20–24, 2017. https://doi.org/10.1515/itms-2017-0003