{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T17:24:55Z","timestamp":1773681895671,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2018,10,11]],"date-time":"2018-10-11T00:00:00Z","timestamp":1539216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772396"],"award-info":[{"award-number":["61772396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472302"],"award-info":[{"award-number":["61472302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772392"],"award-info":[{"award-number":["61772392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672409"],"award-info":[{"award-number":["61672409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Recent work has shown that recognizing point symbols is an essential task in the field of map digitization. For the identification of symbols, it is generally necessary to compare the symbols with a specific criterion and find the most similar one with each known symbol one by one. Most of the works can only identify a single symbol, a small number of works are to deal with multiple symbols simultaneously with a low recognition accuracy. Given the two deficiencies, this paper proposes a deep transfer learning architecture, where the task is to learn a symbol classifier with AlexNet. For the insufficient dataset, we develop a method for transfer learning that uses a MNIST dataset to pretrain the model, which makes up for the problem of small training dataset and enhances the generalization of the model. Before the recognition process, preprocessing the point symbols in the map to coarse screening out the areas suspected of point symbols. We show a significant improvement over using point symbol images to keep a high performance in being able to deal with many more categories of symbols simultaneously.<\/jats:p>","DOI":"10.3390\/s18103403","type":"journal-article","created":{"date-parts":[[2018,10,12]],"date-time":"2018-10-12T02:58:04Z","timestamp":1539313084000},"page":"3403","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Combinatorial Solution to Point Symbol Recognition"],"prefix":"10.3390","volume":"18","author":[{"given":"Yining","family":"Quan","sequence":"first","affiliation":[{"name":"The School of Computer and Technology, Xidian University, Xi\u2019an 710071, China"},{"name":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Shi","sequence":"additional","affiliation":[{"name":"The School of Computer and Technology, Xidian University, Xi\u2019an 710071, China"},{"name":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[{"name":"The School of Computer and Technology, Xidian University, Xi\u2019an 710071, China"},{"name":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutao","family":"Qi","sequence":"additional","affiliation":[{"name":"The School of Computer and Technology, Xidian University, Xi\u2019an 710071, China"},{"name":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, Xi\u2019an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,10,11]]},"reference":[{"key":"ref_1","first-page":"104","article-title":"Symbol recognition: Current advances and perspectives","volume":"2390","author":"Valveny","year":"2001","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1137\/15M104373X","article-title":"A geodesic landmark shooting algorithm for template matching and its applications","volume":"10","author":"Camassa","year":"2017","journal-title":"SIAM J. Imag. Sci."},{"key":"ref_3","first-page":"1","article-title":"Optimal clustering framework for hyperspectral band selection","volume":"99","author":"Wang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_4","first-page":"1546","article-title":"Linear feature separation from topographic maps using energy density and the shear transform","volume":"22","author":"Miao","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rahman, S.Z.A., Abdullah, S.N.H.S., and Nazri, M.Z.B.A. (2016, January 14\u201316). The analysis for gait energy image based on statistical methods. Proceedings of the International Conference on Advances in Electrical, Electronic and Systems Engineering, Putrajaya, Malaysia.","DOI":"10.1109\/ICAEES.2016.7888022"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"33","DOI":"10.5638\/thagis.3.33","article-title":"A statistical method for determining the size of map labels","volume":"3","author":"Sadahiro","year":"2009","journal-title":"Theor. Appl. Gis"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1021\/acssynbio.5b00179","article-title":"A statistical approach reveals designs for the most robust stochastic gene oscillators","volume":"5","author":"Woods","year":"2016","journal-title":"ACS Synth. Biol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Coles, R. (2006). Race and Family: A Structural Approach, Rowman & Littlefield.","DOI":"10.4135\/9781483329000"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/34.754622","article-title":"Integration of structural and statistical information for unconstrained handwritten numeral recognition","volume":"21","author":"Cai","year":"1999","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","first-page":"1","article-title":"Locality and structure regularized low rank representation for hyperspectral image classification","volume":"99","author":"Wang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","first-page":"1197","article-title":"Synergistic face detection and pose estimation with energy-based models","volume":"8","author":"Osadchy","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ullah, I., and Lee, H.J. (2016, January 15\u201317). An approach of locating korean vehicle license plate based on mathematical morphology and geometrical features. Proceedings of the 2016 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA.","DOI":"10.1109\/CSCI.2016.0162"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6265","DOI":"10.1109\/TGRS.2016.2567481","article-title":"Guided superpixel method for topographic map processing","volume":"54","author":"Miao","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","first-page":"50","article-title":"Recognition based on BP neural network map symbol","volume":"11","author":"Wang","year":"2014","journal-title":"Digit. Technol. Appl."},{"key":"ref_15","first-page":"675113","article-title":"Automatic recognition of point symbols on topographic maps","volume":"6751","author":"Chen","year":"2007","journal-title":"Geoinform"},{"key":"ref_16","first-page":"1","article-title":"GETNET: A general end-to-end 2-D CNN framework for hyperspectral image change detection","volume":"99","author":"Wang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","first-page":"15","article-title":"Automatic recognition of point-shaped symbols in scanned maps","volume":"3","author":"Zhang","year":"2000","journal-title":"Eng. Surv. Mapp."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_19","first-page":"65","article-title":"Intelligent recognition of map point symbols based on cognitive theory","volume":"1","author":"Jisheng","year":"2016","journal-title":"Hydrogr. Surv. Chart."},{"key":"ref_20","unstructured":"Gartner, G., Jobst, M., and Huang, H. (2016). Dynamic Cartography: A Concept for Multidimensional Point Symbols. Progress in Cartography, Springer International Publishing."},{"key":"ref_21","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 12\u201314). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Nakada, M., Wang, H., and Terzopoulos, D. (2017, January 21\u201326). AcFR: Active face recognition using convolutional neural networks. Proceedings of the Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.11"},{"key":"ref_23","first-page":"1","article-title":"Convolutional neural networks-based intelligent recognition of Chinese license plates","volume":"22","author":"Liu","year":"2017","journal-title":"Soft Comput."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rodrigues, J., Cardoso, P., Monteiro, J., and Figueiredo, M. (2016). A Comparative Study of Machine Learning Techniques for Gesture Recognition Using Kinect. Handbook of Research on HumanComputer Interfaces, Developments, and Applications, IGI Global.","DOI":"10.4018\/978-1-5225-0435-1"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2751","DOI":"10.1109\/TIP.2016.2613409","article-title":"The recognition of the point symbols in the scanned topographic maps","volume":"26","author":"Miao","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","unstructured":"Simonyan, K., and Zisserman, A. (arXiv, 2014). Very deep convolutional networks for large-scale image recognition, arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3403\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:24:56Z","timestamp":1760196296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,11]]},"references-count":26,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2018,10]]}},"alternative-id":["s18103403"],"URL":"https:\/\/doi.org\/10.3390\/s18103403","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,11]]}}}