{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:41:35Z","timestamp":1774554095136,"version":"3.50.1"},"reference-count":27,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T00:00:00Z","timestamp":1554422400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005357","name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","doi-asserted-by":"publisher","award":["APVV-15-0602"],"award-info":[{"award-number":["APVV-15-0602"]}],"id":[{"id":"10.13039\/501100005357","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["ITMS 26220220103"],"award-info":[{"award-number":["ITMS 26220220103"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Small series production with a high level of variability is not suitable for full automation. So, a manual assembly process must be used, which can be improved by cooperative robots and assisted by augmented reality devices. The assisted assembly process needs reliable object recognition implementation. Currently used technologies with markers do not work reliably with objects without distinctive texture, for example, screws, nuts, and washers (single colored parts). The methodology presented in the paper introduces a new approach to object detection using deep learning networks trained remotely by 3D virtual models. Remote web application generates training input datasets from virtual 3D models. This new approach was evaluated by two different neural network models (Faster RCNN Inception v2 with SSD, MobileNet V2 with SSD). The main advantage of this approach is the very fast preparation of the 2D sample training dataset from virtual 3D models. The whole process can run in Cloud. The experiments were conducted with standard parts (nuts, screws, washers) and the recognition precision achieved was comparable with training by real samples. The learned models were tested by two different embedded devices with an Android operating system: Virtual Reality (VR) glasses, Cardboard (Samsung S7), and Augmented Reality (AR) smart glasses (Epson Moverio M350). The recognition processing delays of the learned models running in embedded devices based on an ARM processor and standard x86 processing unit were also tested for performance comparison.<\/jats:p>","DOI":"10.3390\/sym11040496","type":"journal-article","created":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T11:36:01Z","timestamp":1554464161000},"page":"496","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["An Automated Training of Deep Learning Networks by 3D Virtual Models for Object Recognition"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-7433","authenticated-orcid":false,"given":"Kamil","family":"\u017didek","sequence":"first","affiliation":[{"name":"Faculty of Manufacturing Technologies with a seat in Presov, Department of Industrial Engineering and Informatics, Technical University of Kosice, Bayerova 1, 08001 Pre\u0161ov, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Lazor\u00edk","sequence":"additional","affiliation":[{"name":"Faculty of Manufacturing Technologies with a seat in Presov, Department of Industrial Engineering and Informatics, Technical University of Kosice, Bayerova 1, 08001 Pre\u0161ov, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1942-0438","authenticated-orcid":false,"given":"J\u00e1n","family":"Pite\u013e","sequence":"additional","affiliation":[{"name":"Faculty of Manufacturing Technologies with a seat in Presov, Department of Industrial Engineering and Informatics, Technical University of Kosice, Bayerova 1, 08001 Pre\u0161ov, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Ho\u0161ovsk\u00fd","sequence":"additional","affiliation":[{"name":"Faculty of Manufacturing Technologies with a seat in Presov, Department of Industrial Engineering and Informatics, Technical University of Kosice, Bayerova 1, 08001 Pre\u0161ov, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,4,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Pavlenko, I., Simonovskiy, V., Ivanov, V., Zajac, J., and Pitel, J. (2019). Application of artificial neural network for identification of bearing stiffness characteristics in rotor dynamics analysis. Advances in Design, Simulation and Manufacturing, Springer. Lecture Notes in Mechanical Engineering.","DOI":"10.1007\/978-3-319-93587-4_34"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zidek, K., Pite\u013e, J., and Ho\u0161ovsk\u00fd, A. (2017, January 20\u201323). Machine learning algorithms implementation into embedded systems with web application user interface. Proceedings of the IEEE 21st International Conference on Intelligent Engineering Systems (INES 2017), Larnaca, Cyprus.","DOI":"10.1109\/INES.2017.8118532"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zidek, K., Maxim, V., Pitel, J., and Hosovsky, A. (2016). Embedded vision equipment of industrial robot for inline detection of product errors by clustering-classification algorithms. Int. J. Adv. Robot. Syst., 13.","DOI":"10.1177\/1729881416664901"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"395101","DOI":"10.1088\/1751-8113\/48\/39\/395101","article-title":"Deffuant model of opinion formation in one-dimensional multiplex networks","volume":"48","author":"Shang","year":"2015","journal-title":"J. Phys. A Math. Theor."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pavlenko, I., Trojanowska, J., Ivanov, V., and Liaposhchenko, O. (2019). Scientific and methodological approach for the identification of mathematical models of mechanical systems by using artificial neural networks. Innovation, Engineering and Entrepreneurship, Springer. Lecture Notes in Electrical Engineering.","DOI":"10.1007\/978-3-319-91334-6_41"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"227","DOI":"10.4028\/www.scientific.net\/AMM.616.227","article-title":"Diagnostics of errors at component surface by vision recognition in production systems","volume":"616","author":"Maxim","year":"2014","journal-title":"Appl. Mech. Mater."},{"key":"ref_7","first-page":"459","article-title":"Diagnostics of surface errors by embedded vision system and its classification by machine learning algorithms","volume":"669","author":"Dubjak","year":"2016","journal-title":"Key Eng. Mater."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"\u017didek, K., Hosovsky, A., Pite\u013e, J., and Bedn\u00e1r, S. (2019). Recognition of assembly parts by convolutional neural networks. Advances in Manufacturing Engineering and Materials, Springer. Lecture Notes in Mechanical Engineering.","DOI":"10.1007\/978-3-319-99353-9_30"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Sarkar, K., Varanasi, K., and Stricker, D. (March, January 27). Trained 3D models for CNN based object recognition. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Visigrapp 2017), Porto, Portugal.","DOI":"10.5220\/0006272901300137"},{"key":"ref_10","unstructured":"Socher, R., Huval, B., Bhat, B., Manning, C.D., and Ng, A.Y. (2012, January 3\u20136). Convolutional-recursive deep learning for 3D object classification. Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS\u201912), Lake Tahoe, NV, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., and Guibas, L.J. (2015, January 7\u201313). Render for CNN: Viewpoint estimation in images using CNNs trained with rendered 3D model views. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV\u201915), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.308"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/JAS.2017.7510841","article-title":"Training and testing object detectors with virtual images","volume":"5","author":"Tian","year":"2018","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s00530-015-0485-2","article-title":"Convolutional deep learning for 3D object retrieval","volume":"23","author":"Nie","year":"2017","journal-title":"Multimed. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Peng, X.C., Sun, B.C., Ali, K., and Saenko, K. (2015, January 7\u201313). Learning deep object detectors from 3D models. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV\u201915), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.151"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"05011","DOI":"10.1051\/matecconf\/201817805011","article-title":"Product engineering design enhancing by parameterizing the 3D solid model","volume":"178","author":"Cucos","year":"2018","journal-title":"MATEC Web Conf."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"011009","DOI":"10.1115\/1.4041777","article-title":"Triangular mesh and boundary representation Combined Approach for 3D CAD Lightweight Representation for Collaborative Product Development","volume":"19","author":"Nguyen","year":"2018","journal-title":"J. Comput. Inf. Sci. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Poll\u00e1k, M., Baron, P., and Zajac, J. (2016). Automatization process of designing the technological documentation by tools of comprehensive CAD-CAM-CAE system. MM Sci. J., 942\u2013946.","DOI":"10.17973\/MMSJ.2016_09_201630"},{"key":"ref_18","first-page":"703","article-title":"Design of the web interface to manage automatically generated production documentation","volume":"7","author":"Baron","year":"2018","journal-title":"Tech. Technol. Educ. Manag. TTEM"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan, K. (2018). Deep Learning in data-driven pavement image analysis and automated distress detection: A review. Data, 3.","DOI":"10.3390\/data3030028"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mao, K., Lu, D., E, D., and Tan, Z. (2018). A case study on attribute recognition of heated metal mark image using deep convolutional neural networks. Sensors, 18.","DOI":"10.3390\/s18061871"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Pham, G., Lee, S.-H., Kwon, O.-H., and Kwon, K.-R. (2018). Anti-3D weapon model detection for safe 3D printing based on convolutional neural networks and D2 shape distribution. Symmetry, 10.","DOI":"10.3390\/sym10040090"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.promfg.2017.07.124","article-title":"An AR-based worker support system for human-robot collaboration","volume":"11","author":"Liu","year":"2017","journal-title":"Procedia Manuf."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gerstweiler, G., Furlan, L., Timofeev, M., and Kaufmann, H. (2018). Extraction of structural and semantic data from 2D floor plans for interactive and immersive VR real estate exploration. Technologies, 6.","DOI":"10.3390\/technologies6040101"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Gao, Q.H., Wan, T.R., Tang, W., Chen, L., and Zhang, K.B. (2017). An improved augmented reality registration method based on Visual SLAM. E-Learning and Games, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-65849-0_2"},{"key":"ref_25","first-page":"13","article-title":"Wireless device based on MEMS sensors and bluetooth low energy (LE\/smart) technology for diagnostics of mechatronic systems","volume":"460","year":"2014","journal-title":"Appl. Mech. Mater."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hrubo\u0161, M., Svetl\u00edk, J., Nikitin, Y., Pirn\u00edk, R., Nemec, D., \u0160im\u00e1k, V., Janota, A., Hrb\u010dek, J., and Gregor, M. (2016). Searching for collisions between mobile robot and environment. Int. J. Adv. Robot. Syst., 13.","DOI":"10.1177\/1729881416667500"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shang, Y. (2017). On the delayed scaled consensus problems. Appl. Sci., 7.","DOI":"10.3390\/app7070713"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/11\/4\/496\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:43:14Z","timestamp":1760186594000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/11\/4\/496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,5]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2019,4]]}},"alternative-id":["sym11040496"],"URL":"https:\/\/doi.org\/10.3390\/sym11040496","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,5]]}}}