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

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

[1] 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/B978-012373904-9.50013-110.1016/B978-012373904-9.50013-1
Search in Google Scholar Back to article
[2] 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/B978-0-12-802232-0.00002-510.1016/B978-0-12-802232-0.00002-5
Search in Google Scholar Back to article
[3] 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_910.1007/978-3-030-11479-4_9
Search in Google Scholar Back to article
[4] 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-X10.1016/B978-0-12-804566-4.00019-X
Search in Google Scholar Back to article
[5] 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.2016.264461510.1109/TPAMI.2016.2644615
Search in Google Scholar Back to article
[6] 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.2018.08.02210.1016/j.ins.2018.08.022
Search in Google Scholar Back to article
[7] 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.2017.53410.1109/ICCV.2017.534
Search in Google Scholar Back to article
[8] 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.2016.12.02510.1016/j.neucom.2016.12.025
Search in Google Scholar Back to article
[9] 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-2015-000710.1515/itms-2015-0007
Search in Google Scholar Back to article
[10] 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.2018.12.02110.1016/j.patrec.2018.12.021
Search in Google Scholar Back to article
[11] 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-2017-001810.1515/acss-2017-0018
Search in Google Scholar Back to article
[12] 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-2018-000610.2478/ecce-2018-0006
Search in Google Scholar Back to article
[13] 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/B978-0-444-87806-9.50007-410.1016/B978-0-444-87806-9.50007-4
Search in Google Scholar Back to article
[14] 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/B978-0-12-708240-0.50016-210.1016/B978-0-12-708240-0.50016-2
Search in Google Scholar Back to article
[15] 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_2210.1007/978-3-319-50835-1_22
Search in Google Scholar Back to article
[16] 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-2017-000310.1515/itms-2017-0003
Search in Google Scholar Back to article

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

Abstract

Paradigm

My account