Key Methods of Recognizing Container Number Automatically Using Video Stream in Intelligent Tally

An automatic identification algorithm of container number based on video stream is proposed in this paper. The algorithm is designed to use Selective Search and frame difference method to locate the front and rear sides of the container and the land and sea side of the container. And then the region of the number is located through noise filtering. Ultimately, the complete container number is identified by the template matching and convolutional neural network (CNN). The algorithm can realize the real-time positioning of the container surface from the four-side video stream of the container docking as well as the identification of the container number.

[1]  Youngwoo Yoon,et al.  Automatic Container Code Recognition from Multiple Views , 2016 .

[2]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[3]  Wen-Chang Cheng,et al.  A cascade classifier using Adaboost algorithm and support vector machine for pedestrian detection , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[4]  Pengfei Shi,et al.  An Algorithm for License Plate Recognition Applied to Intelligent Transportation System , 2011, IEEE Transactions on Intelligent Transportation Systems.

[5]  Xiaohai He,et al.  An automated vision system for container-code recognition , 2012, Expert Syst. Appl..

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Jianming Guo,et al.  MSER and Connected Domain Analysis Based Algorithm for Container Code Locating Process , 2017, 2017 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII).