Title :
A New Method for Container Code Location
Author :
Yin, Jianqin ; Cao, Aizeng ; Li, Jinping
Author_Institution :
Univ. of Jinan, Jinan
Abstract :
An automatic extraction method of container identity codes based on mathematical morphology operation, region analysis and projection transformation is proposed. With different kinds of noises on the image, the container code can hardly be extracted precisely. To decrease the influence the noise and detect the code coarsely the image is filtered by mathematical morphological operators. Then, closed regions are found to filter the isolated strokes. Regions splitting and merging are used to obtain the candidate rectangles. Combination test based on the relationship of the rectangles is used to identify the 6-cases code arrangement rectangles. At last, the change frequency of the gray value of the image is used to identify the last code areas. Experimental results show that the method we proposed can segment the container ID codes with high performance.
Keywords :
containers; feature extraction; logistics; mathematical morphology; optical character recognition; 6-cases code arrangement rectangles; automatic extraction method; container code location; container identity codes; mathematical morphology; projection transformation; region analysis; Automation; Containers; Data mining; Filters; Information analysis; Information science; Intelligent transportation systems; Licenses; Logistics; Morphology; container number location; mathematical morphology; projection transform;
Conference_Titel :
Automation and Logistics, 2007 IEEE International Conference on
Conference_Location :
Jinan
Print_ISBN :
978-1-4244-1531-1
DOI :
10.1109/ICAL.2007.4339065