Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Transformer Network for Container's BIC-code Recognition

컨테이너 BIC-code 인식을 위한 Transformer Network

  • 권희주 (충북대학교 정보통신공학부) ;
  • 강현수 (충북대학교 정보통신공학부)
  • Received : 2021.11.12
  • Accepted : 2022.01.20
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a pre-processing method to facilitate the container's BIC-code recognition. We propose a network that can find ROI(Region Of Interests) containing a BIC-code region and estimate a homography matrix for warping. Taking the structure of STN(Spatial Transformer Networks), the proposed network consists of next 3 steps, ROI detection, homography matrix estimation, and warping using the homography estimated in the previous step. It contributes to improving the accuracy of BIC-code recognition by estimating ROI and matrix using the proposed network and correcting perspective distortion of ROI using the estimated matrix. For performance evaluation, five evaluators evaluated the output image as a perfect score of 5 and received an average of 4.25 points, and when visually checked, 224 out of 312 photos are accurately and perfectly corrected, containing ROI.

본 논문은 컨테이너의 BIC-code를 인식하기 위한 전처리(pre-processing) 방법에 관한 것으로서, BIC-code가 포함된 관심 영역을 찾고 이 관심 영역을 광학 문자 인식에 용이하도록 워핑하기 위한 호모그래피 행렬을 추정할 수 있는 네트워크를 제안한다. 제안하는 네트워크의 구조는 STN(Spatial Transformer Networks)의 구조를 차용하였으며, 관심 영역 검출, 호모그래피 변환을 위한 행렬 추정, 행렬을 이용한 워핑 단계로 구성되어 있다. 제안된 네트워크를 이용하여 관심 영역과 행렬을 동시에 추정하고, 추정된 행렬을 이용하여 관심 영역의 원근 왜곡을 바로 잡음으로써 BIC-code의 인식 정확도 향상에 기여한다. 성능 평가를 위하여 총 5인의 평가원이 출력 영상을 5점 만점으로 평가한 결과 평균 4.25점을 받았으며, 육안으로 확인했을 시 총 312장의 사진 중 224장의 사진이 완벽하게 보정됨과 동시에 관심 영역을 출력하였다.

Keywords

Acknowledgement

This work was conducted as a part of the research project of "Development of IoT Infrastructure Technology for Smart Port" and in part the research project of " Development of automatic screening and hybrid detection system for hazardous material detecting in port container" (20200611) financially supported by the Ministry of Oceans and Fisheries

References

  1. Song, J. W. (2015). Container BIC-code region extraction and recognition method using multiple thresholding, Master Thesis. Graduate School of Chungbuk National University, Cheongju, Korea.
  2. Max J., Karen S., Andrew Z. and koray k. (2015). Spatial Transformer Networks, Neural Information Processing Systems, 28, 2017-2025.
  3. Francois C. (2017). Xception: Deep Learning with Depthwise Separable Convolutions, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1800-1807, https://doi.org/10.1109/CVPR.2017.195.
  4. Christian S., Vincent V., Sergey l., Jon S and Zbigniew W. (2016). Rethinking the Inception Architecture for Computer Vision, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2818-2826, https://doi.org/10.1109/CVPR.2016.308.
  5. Peter J. H. (1964). Robust Estimation of a Location Parameter, The Annals of Mathmatical Statistics, 53 (1), 73-101, https://doi.org/10.1214/aoms/1177703732
  6. Leon A. G., Alexander S. E. and Matthias B. (2016). Image Style Transfer Using Convolutional Neural Networks, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2414-2423, https://doi.org/10.1109/CVPR.2016.265.
  7. Karen S. and Andrew Z. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition, CoRR, abs/1409.1556.