Fully Convolutional Network based Ship Plate Recognition

Ship plate recognition is challenging due to variations of plate locations and text types. This paper proposes an effcient Fully Convolutional Network based Plate Recognition approach FCNPR, which uses a CNN (Convolutional Neural Network) to locate ships, then detects plate text lines with the fully convolutional network (FCN). The recognition accuracy is improved with integrating the AIS (Automatic Identification System) information. The actual FCNPR deployment demonstrates that it can work reliably with a high accuracy for satisfying practical usages.

Zhang Weishan, Sun Haoyun, Zhou Jiehan, Liu Xin, Zhang Zhanmin, Min Guizhi

A4 Article in conference proceedings

IEEE International Conference on Systems Man and Cybernetics Conference Proceedings

W. Zhang, H. Sun, J. Zhou, X. Liu, Z. Zhang and G. Min, "Fully Convolutional Network Based Ship Plate Recognition," 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, 2018, pp. 1803-1808, https://doi.org/10.1109/SMC.2018.00312

https://doi.org/10.1109/SMC.2018.00312 http://urn.fi/urn:nbn:fi-fe2020042822734