A computer vision system for automated container code recognition

Hsin Chen Chen, Chih Kai Chen, Fu Yu Hsu, Yu San Lin, Yu Te Wu, Yung-Nien Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Container code examination is an essential step in the container flow management. To date, this step is mostly achieved by human visual inspections, which are however time-consuming and error-prone. We hence propose a new computer vision system for automated container code recognition. The proposed system consists of model construction and code recognition stages. In the model construction stage, we first incorporate a locally thresholding method with prior knowledge of code character geometry to segment the code characters, including English characters A-Z and numeric characters 0-9, from a training set of container images. With the segmentation results of each character, we subsequently construct its Eigen-feature model using the principal component analysis (PCA). In the recognition stage, the code characters are firstly segmented from the given container image. Each segmented character is then recognized by finding the best matched Eigen-feature model that maintains the minimal PCA reconstruction error of the character appearance. Experiments showed that the proposed method achieved the code recognition with a high recognition rate and little recognition time for each image automatically. Overall, our proposed system has great potential for improving the efficiency of container terminals as well as enhancing the container management.

Original languageEnglish
Title of host publicationIMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011
Pages470-474
Number of pages5
Publication statusPublished - 2011 Jul 26
EventInternational MultiConference of Engineers and Computer Scientists 2011, IMECS 2011 - Kowloon, Hong Kong
Duration: 2011 Mar 162011 Mar 18

Publication series

NameIMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011
Volume1

Other

OtherInternational MultiConference of Engineers and Computer Scientists 2011, IMECS 2011
CountryHong Kong
CityKowloon
Period11-03-1611-03-18

Fingerprint

Computer vision
Containers
Principal component analysis
Inspection
Geometry
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Chen, H. C., Chen, C. K., Hsu, F. Y., Lin, Y. S., Wu, Y. T., & Sun, Y-N. (2011). A computer vision system for automated container code recognition. In IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011 (pp. 470-474). (IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011; Vol. 1).
Chen, Hsin Chen ; Chen, Chih Kai ; Hsu, Fu Yu ; Lin, Yu San ; Wu, Yu Te ; Sun, Yung-Nien. / A computer vision system for automated container code recognition. IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011. 2011. pp. 470-474 (IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011).
@inproceedings{6fa6ab7d94c74aa8a5e9747fbefc4e2a,
title = "A computer vision system for automated container code recognition",
abstract = "Container code examination is an essential step in the container flow management. To date, this step is mostly achieved by human visual inspections, which are however time-consuming and error-prone. We hence propose a new computer vision system for automated container code recognition. The proposed system consists of model construction and code recognition stages. In the model construction stage, we first incorporate a locally thresholding method with prior knowledge of code character geometry to segment the code characters, including English characters A-Z and numeric characters 0-9, from a training set of container images. With the segmentation results of each character, we subsequently construct its Eigen-feature model using the principal component analysis (PCA). In the recognition stage, the code characters are firstly segmented from the given container image. Each segmented character is then recognized by finding the best matched Eigen-feature model that maintains the minimal PCA reconstruction error of the character appearance. Experiments showed that the proposed method achieved the code recognition with a high recognition rate and little recognition time for each image automatically. Overall, our proposed system has great potential for improving the efficiency of container terminals as well as enhancing the container management.",
author = "Chen, {Hsin Chen} and Chen, {Chih Kai} and Hsu, {Fu Yu} and Lin, {Yu San} and Wu, {Yu Te} and Yung-Nien Sun",
year = "2011",
month = "7",
day = "26",
language = "English",
isbn = "9789881821034",
series = "IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011",
pages = "470--474",
booktitle = "IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011",

}

Chen, HC, Chen, CK, Hsu, FY, Lin, YS, Wu, YT & Sun, Y-N 2011, A computer vision system for automated container code recognition. in IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011. IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011, vol. 1, pp. 470-474, International MultiConference of Engineers and Computer Scientists 2011, IMECS 2011, Kowloon, Hong Kong, 11-03-16.

A computer vision system for automated container code recognition. / Chen, Hsin Chen; Chen, Chih Kai; Hsu, Fu Yu; Lin, Yu San; Wu, Yu Te; Sun, Yung-Nien.

IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011. 2011. p. 470-474 (IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A computer vision system for automated container code recognition

AU - Chen, Hsin Chen

AU - Chen, Chih Kai

AU - Hsu, Fu Yu

AU - Lin, Yu San

AU - Wu, Yu Te

AU - Sun, Yung-Nien

PY - 2011/7/26

Y1 - 2011/7/26

N2 - Container code examination is an essential step in the container flow management. To date, this step is mostly achieved by human visual inspections, which are however time-consuming and error-prone. We hence propose a new computer vision system for automated container code recognition. The proposed system consists of model construction and code recognition stages. In the model construction stage, we first incorporate a locally thresholding method with prior knowledge of code character geometry to segment the code characters, including English characters A-Z and numeric characters 0-9, from a training set of container images. With the segmentation results of each character, we subsequently construct its Eigen-feature model using the principal component analysis (PCA). In the recognition stage, the code characters are firstly segmented from the given container image. Each segmented character is then recognized by finding the best matched Eigen-feature model that maintains the minimal PCA reconstruction error of the character appearance. Experiments showed that the proposed method achieved the code recognition with a high recognition rate and little recognition time for each image automatically. Overall, our proposed system has great potential for improving the efficiency of container terminals as well as enhancing the container management.

AB - Container code examination is an essential step in the container flow management. To date, this step is mostly achieved by human visual inspections, which are however time-consuming and error-prone. We hence propose a new computer vision system for automated container code recognition. The proposed system consists of model construction and code recognition stages. In the model construction stage, we first incorporate a locally thresholding method with prior knowledge of code character geometry to segment the code characters, including English characters A-Z and numeric characters 0-9, from a training set of container images. With the segmentation results of each character, we subsequently construct its Eigen-feature model using the principal component analysis (PCA). In the recognition stage, the code characters are firstly segmented from the given container image. Each segmented character is then recognized by finding the best matched Eigen-feature model that maintains the minimal PCA reconstruction error of the character appearance. Experiments showed that the proposed method achieved the code recognition with a high recognition rate and little recognition time for each image automatically. Overall, our proposed system has great potential for improving the efficiency of container terminals as well as enhancing the container management.

UR - http://www.scopus.com/inward/record.url?scp=79960601061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960601061&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789881821034

T3 - IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011

SP - 470

EP - 474

BT - IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011

ER -

Chen HC, Chen CK, Hsu FY, Lin YS, Wu YT, Sun Y-N. A computer vision system for automated container code recognition. In IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011. 2011. p. 470-474. (IMECS 2011 - International MultiConference of Engineers and Computer Scientists 2011).