An automated vision system for container-code recognition

Wu, Wei; Liu, Zheng; Chen, Mo; Yang, Xia; He, Xiaohai

doi:10.1016/j.eswa.2011.08.143

Cited by 42 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current LPR techniques can function well under specified working conditions [1] such as indoor scenes, fixed backgrounds [2] or illuminations [3], prescribed driveways [4,5], limited vehicle speeds [6] and the fixed distance between a camera and vehicles. For example, a color-based localization method works well under the normal illumination, but the recognition accuracy is unsatisfactory when the illumination becomes too strong or weak.…”

Section: Introductionmentioning

confidence: 99%

A multi-filter based license plate localization and recognition framework

Zhang

Shi

Xia

et al. 2013

2013 Ninth International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

A license plate is regarded as the unique identification of a vehicle, which makes the license plate recognition (LPR) an indispensable operation in intelligent transportation systems (ITS). Since many techniques related to the LPR are restricted to specific working conditions, a multi-filter based LPR framework for the plate localization and the character recognition is proposed to solve the issues. In the localization phase, chromatic and morphologic filters are cooperated with each other under flexible criterions to detect candidate plate regions accurately. Plate characteristics, such as the length-to-width ratio, the size of a character, etc. are utilized in the character segmentation phase. In the recognition phase, a back propagation (BP) neural network is trained for the character recognition. 800 images taken from various scenes under different conditions are used to evaluate the accuracy of the proposed framework. The experimental results show that the missing rate of localization is close to zero, and the accuracy of the plate localization and the recognition is 98.4% and 93.8% respectively. Moreover, the overall accuracy of the multi-filter based framework is 93.1%.

show abstract

Section: Introductionmentioning

confidence: 99%

A multi-filter based license plate localization and recognition framework

Zhang

Shi

Xia

et al. 2013

2013 Ninth International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

show abstract

“…connect region analysis [21]. Then, container code characters were cut by binarization and projection.…”

Section: Advances In Engineering Research (Aer) Volume 132mentioning

confidence: 99%

Container Code Detection by Deep Convolutional Network

Wang¹,

Ma²

2017

Proceedings of the 2017 Global Conference on Mechanics and Civil Engineering (GCMCE 2017)

View full text Add to dashboard Cite

Abstract. Automatic container code recognition plays an important role in customs logistics and tra-nsport management. Due to difficulties such as character color and font size variation, illumination conditions, image degradation, and exist of many other characters, automatic detect and recognition of container code is still a difficult task. This paper proposes a container code detection algorithm based on deep convolutional neural network named holistically-nested edge detection (HED). In the training phase, a bounding box was drawn around container code as virtual edges, and they were feed to the network together with original image to train the HED model. In the test phase, probability map of bounding box was predict by trained model and finally bounding box is obtained by thresholding and connected region analysis. Experimental results on 9953 container images show that the performance of IOU and recall precision on test set can reach 0.646 and 0.934 respectively with the proposed algorithms.

show abstract

“…Among the image of positioning, the character of the interferential parts has been eliminated and the character of the case number is more prominent and obvious, but between the character and character of the case number area exist the gap, when we scan the row of the case number area from left to right, the black and white pixels jump more frequently [9,10].Make it get obvious effect by new model of container image preprocessing, a large number of background is removed so that the container is much easier to locate.As shown in figure 4: …”

Section: Effect Of Container Segmentationmentioning

confidence: 99%

A New Model of Adaptive Container Image Preprocessing

Zhang¹,

Zeng²

2015

Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015

View full text Add to dashboard Cite

Abstract. The preprocessing of container image is the key to the whole container code intelligent identification system, and the result of treatment directly affects the accuracy of the code area positioning, the character segmentation and recognition. Based on some features of container images such as the color, the gradient and the connected domain we proposed a novel and adaptive container image preprocessing model. In traditional methods,there are many parameters should be optimized,and multi-parameter optimization is a difficult point.Yet,our model not only solve the problem skillfully,but also can remove a large number the background color of container image adaptively when the color difference of background and target is small.Therefore,our model can better on container area segmentation,character segmentation and recognition.A lot of experimental results showed that the proposed model can effectively extract the more effect.

show abstract

An automated vision system for container-code recognition

Cited by 42 publications

References 25 publications

A multi-filter based license plate localization and recognition framework

A multi-filter based license plate localization and recognition framework

Container Code Detection by Deep Convolutional Network

A New Model of Adaptive Container Image Preprocessing

Contact Info

Product

Resources

About