Deep learning based container text recognition

Traditional character segmentation has low accuracy for container scene text recognition. Convolutional recurrent neural network (CRNN) and connectionist text proposal network (CTPN) methods cannot extract container text features effectively. This paper proposes a novel Container Text Detection and Recognition Network (CTDRNet) for accurately detecting and recognizing container scene text. The CTDRNet consists of three components: (1) CTDRNet text detection enables to improve detection accuracy for single words; (2) CTDRNet text recognition has faster convergence speed and detection accuracy; (3) CTDRNet post-processing improves detection and recognition accuracy. In the end, the CTDRNet is implemented and evaluated with an accuracy of 96% and processing rate of 2.5 fps.

Zhang Weishan, Zhu Liqian, Xu Liang, Zhou Jiehan, Sun Haoyun, Liu Xin

Publication type:
A4 Article in conference proceedings

Place of publication:
23rd IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2019

container, Deep learning, scene text detection, scene text recognition


Full citation:
W. Zhang, L. Zhu, L. Xu, J. Zhou, H. Sun and X. Liu, “Deep Learning Based Container Text Recognition,” 2019 IEEE 23rd International Conference on Computer Supported Cooperative Work in Design (CSCWD), Porto, Portugal, 2019, pp. 69-74,


Read the publication here: