A Port Container Code Recognition Algorithm under Natural Conditions

Mi, C.; Cao, L.; Zhang, Z.; Feng, Y.; Yao, L., and Wu, Y., 2020. A port container code recognition algorithm under natural conditions. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Researc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of coastal research Ročník 103; číslo sp1; s. 822 - 829
Hlavní autoři: Mi, Chao, Cao, Lingen, Zhang, Zhiwei, Feng, Yufei, Yao, Lei, Wu, Yunbao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Fort Lauderdale Coastal Education and Research Foundation 01.06.2020
Allen Press Publishing
Allen Press Inc
Témata:
Algorithms
Back propagation networks
BP neural network
Coastal engineering
Coastal inlets
Coastal research
Coasts
Container code recognition
Containers
Deflection
differential edge binarization
Edge detection
Illumination
Image processing
Image segmentation
least square method
Localization
Neural networks
Object recognition
Ocean engineering
OCEAN INFORMATION SCIENCE
Offshore engineering
tilt correction
ISSN:0749-0208, 1551-5036
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Mi, C.; Cao, L.; Zhang, Z.; Feng, Y.; Yao, L., and Wu, Y., 2020. A port container code recognition algorithm under natural conditions. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 822–829. Coconut Creek (Florida), ISSN 0749-0208. Automatic container code recognition is very important for modern container intelligent management system. Under natural conditions, aiming at the problems of uneven illumination, tilt and deflection of container number in port container code recognition. A new differential edge detection algorithm is used to realize binary segmentation of uneven illumination container number image, and then the problem of accurate location of container number deflection is solved effectively by the improved least square method, then use gradient descent projection based character correction and segmentation algorithm to correct and segment tilt container number; BP neural network to recognize the segmented characters. Finally, experiments are carried out on the images taken under different conditions. The comprehensive recognition rate is 96.8%, the localization rate is 2.4% higher than the traditional method, and the comprehensive recognition rate is 6.5% higher than yolov3 algorithm, which meets the real-time requirements.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0749-0208
1551-5036
DOI:10.2112/SI103-170.1