Automation of Sampling of Images of Natural Scenes for Training and Testing Neural Networks
DOI:
https://doi.org/10.52575/2687-0932-2023-50-3-624-632Keywords:
neural networks, dataset, image segmentation, image annotation, training setAbstract
Artificial neural networks are actively used to solve problems of pattern recognition in images. For their training, it is necessary to prepare labeled data sets for the formation of training and validation samples. The formation of such samples "manually" requires highly qualified specialists and large time and, consequently, material costs. This work is devoted to the formation of a set of basic methods and technologies, as well as the creation and testing of the solution architecture for automated segmentation and annotation of images of natural scenes in order to create samples for training and testing neural networks.
Downloads
References
Ахметвалеев Р.Р., Шабанова К.И., Падукова А.А., Лакман И.А. 2021. Методика разметки медицинских изображений с функцией кросс-проверки и интеллектуального сегментирования. Вестник ВШОУЗ, 7, 3: 62-69.
Андриянов Н.А. 2022. Обнаружение объектов на изображении: от критериев Байеса и Неймана–Пирсона к детекторам на базе нейронных сетей EfficientDet. Компьютерная оптика. 46, 1: 139-159. DOI: 10.18287/2412-6179-CO-922.
Брехт Э.А., Коншина В.Н. 2022. Применение нейронной сети YOLO для распознавания дефектов. Intellectual Technologies on Transport, 2: 41-47. DOI: 10.24412/2413-2527-2022-230-41-47.
Вожегова М.А. 2023. Структурно-функциональная модель комплексов неразрушающего контроля с системой обработки данных на основе нейронных сетей. Экономика. Информатика. 50(2): 389–397. DOI: 10.52575/2687-0932-2023-50-2-389-397.
Сирота А.А., Митрофанова Е.Ю., Милованова А.И. 2019. Анализ алгоритмов поиска объектов на изображениях с использованием различных модификаций сверточных нейронных сетей. Вестник ВГУ, серия: системный анализ и информационные технологии, 3: 123-137.
Ханжина Н.Е. 2021. Байесовские функции потерь для моделирования гомоскедастичной алеаторной неопределенности в задаче детекции пыльцы на изображениях. Научно-технический вестник информационных технологий, механики и оптики. 21, 4: 535–544. DOI: 10.17586/2226-1494-2021-21-4-535-544.
Du X, Lin T, Jin P, Ghiasi G, Tan M, Cui Y, Le QV, Song X. 2020. SpineNet: Learning scale-permuted backbone for recognition and localization. Proc IEEE Conf on Computer Vision and Pattern Recognition (CVPR), 1: 11593-11601. DOI: 10.1109/CVPR42600.2020.01161.
Fang H, Sun J, Wang R, Gou M, Li Y, Lu C, Tong SJ. 2019. InstaBoost: Boosting instance segmentation via probability map guided copy-pasting. Proc 2019 IEEE/CVF Int Conf on Computer Vision (ICCV), 1: 682-691. DOI: 10.1109/ICCV.2019.00077.
Gao Z, Wang L, Wu G. 2019. LIP: Local importance-based pooling. Proc 2019 IEEE/CVF Int Conf on Computer Vision (ICCV), 1: 3355-3364. DOI: 10.1109/ICCV.2019.00345.
Hsu G., Chen J., Chung Y. 2013. Application-oriented license plate recognition. IEEE Trans. Veh. Technol. 62(2): 552-561.
Liu Y, Wang S, Liang T, Zhao Q, Tang Z, Ling H. CBNet: A novel composite backbone network architecture for object detection. arXiv Preprint. URL: https://ojs.aaai.org/index.php/
AAAI/article/view/6834.
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C, Berg A. 2016. SSD: Single shot multibox detector. Proc European Conf on Computer Vision (ECCV), 1: 1-17. DOI: 10.1007/978-3-319-46448-0_2.
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Zh, Lin S, Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv Preprint. URL: https://arxiv.org/pdf/2103.14030v1.pdf.
Redmon J, Farhadi A. 2017. YOLO9000: Better, faster, stronger. Proc 2017 IEEE Conf on Computer Vision and Pattern Recognition (CVPR), 1: 7263-7271. DOI: 10.1109/CVPR.2017.690.
Shen Yi. 2005. Loss Functions For Binary Classification and Class Probability Estimation. University of Pennsylvania. URL: http://stat.wharton.upenn.edu/~buja/PAPERS/yi-shen-dissertation.pdf.
Tan M, Pang R, Le QV. EfficientDet: Scalable and efficient object detection. arXiv Preprint. URL: https://arxiv.org/abs/1911.09070.
Vu T, Jang H, Pham T, Yoo C. 2019. Cascade RPN: Delving into high-quality region proposal network with adaptive convolution. Proc 33rd Conf on Neural Information Processing Systems (NeurIPS 2019), 1: 1-11.
Wang C, Bochkovskiy A, Liao H. Scaled-YOLOv4: Scaling cross stage partial network. arXiv Preprint. URL: https://arxiv.org/pdf/2011.08036v2.pdf.
Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X, Liu W, Xiao B. 2020. Deep highresolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell, 1: 1-23. DOI: 10.1109/tpami.2020.2983686.
Zhang R, Du L, Xiao Q, Liu J. 2020. Comparison of Backbones for Semantic Segmentation Network. J. Phys.: Conf. Ser. 1544 012196. DOI: 10.1088/1742-6596/1544/1/012196.
Zhou X, Koltun V, Krahenbuhl P. Probabilistic two-stage detection. arXiv Preprint. URL: https://arxiv.org/pdf/2103.07461v1.pdf.
Abstract views: 45
Share
Published
How to Cite
Issue
Section
Copyright (c) 2023 Economics. Information Technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
