Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Number and Character Area of License Plate Using Deep Learning and Semantic Image Segmentation

딥러닝과 의미론적 영상분할을 이용한 자동차 번호판의 숫자 및 문자영역 검출

  • Received : 2020.11.09
  • Accepted : 2021.01.20
  • Published : 2021.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

License plate recognition plays a key role in intelligent transportation systems. Therefore, it is a very important process to efficiently detect the number and character areas. In this paper, we propose a method to effectively detect license plate number area by applying deep learning and semantic image segmentation algorithm. The proposed method is an algorithm that detects number and text areas directly from the license plate without preprocessing such as pixel projection. The license plate image was acquired from a fixed camera installed on the road, and was used in various real situations taking into account both weather and lighting changes. The input images was normalized to reduce the color change, and the deep learning neural networks used in the experiment were Vgg16, Vgg19, ResNet18, and ResNet50. To examine the performance of the proposed method, we experimented with 500 license plate images. 300 sheets were used for learning and 200 sheets were used for testing. As a result of computer simulation, it was the best when using ResNet50, and 95.77% accuracy was obtained.

자동차 번호판 인식은 지능형 교통시스템에서 핵심적인 역할을 담당한다. 따라서 효율적으로 자동차 번호판의 숫자 및 문자영역을 검출하는 것은 매우 중요한 과정이다. 본 연구에서는 딥러닝과 의미론적 영상분할 알고리즘을 적용하여 효과적으로 자동차 번호판의 번호영역을 검출하는 방법을 제안한다. 제안된 방법은 화소 투영과 같은 전처리과정 없이 번호판 영상에서 바로 숫자 및 문자영역을 검출하는 알고리즘이다. 번호판 영상은 도로 위에 설치된 고정 카메라로 부터 획득한 영상으로 날씨 및 조명변화 등을 모두 포함한 다양한 실제 상황에서 촬영된 것을 사용하였다. 입력 영상은 색상변화를 줄이기 위해 정규화하고 실험에 사용된 딥러닝 신경망 모델은 Vgg16, Vgg19, ResNet18 및 ResNet50이다. 제안방법의 성능을 검토하기 위해 번호판 영상 500장으로 실험하였다. 학습을 위해 300장을 할당하였으며 테스트용으로 200장을 사용하였다. 컴퓨터모의 실험결과 ResNet50을 사용할 때 가장 우수하였으며 95.77% 정확도를 얻었다.

Keywords

References

  1. S. An, B. Lee & D. Shin. (2011).A Survey of Intelligent Transportation Systems. Third International Conference on Computational Intelligence, Communication Systems and Networks, Bali, 332-337. DOI: 10.1109/CICSyN.2011.76
  2. M.A. Lalimia, S. Ghofrania & McLernonb. (2013). A Vehicle License Plate Detection Method Using Region and Edge Based Methods. [Online]. DOI: 10.1016/j.compeleceng.2012.09.015.
  3. M. Ko. (2004). Effective License Plate Character Recognition based on Geometric Invariant Features. Doctoral dissertation, Kyungpook National University, Daegu.
  4. H. Bai & C. Liu. (2004). A Hybrid License Plate Extraction Method Based on Edge Statistics and Morphology. Proceedings of the 17th International Conference on Pattern Recognition, 831-834. DOI: 10.1109/ICPR.2004.1334387
  5. J. Schmidhuber. (2014). Deep Learning in Neural Networks: An Overview. [Online]. arxiv. org/abs/1404.7828. DOI:10.1016/j.neunet.2014.09.003
  6. A. Khan1, A. Sohail1, U. Zahoora1 & A. S. Qureshi1.(2020). A Survey of the Recent Architectures of Deep Convolutional Neural Networks. [Online]. arxiv.org/abs/1901. 06032. DOI: 10.1007/s10462-020-09825-6
  7. Vijay Badrinarayanan, Alex Kendall & Roberto CipollaSegNet. (2017). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481-2495. DOI: 10.1109/TPAMI.2016.2644615
  8. J. Lee. (2018). A Method of Eye and Lip Region Detection using Faster R-CNN in Face Image. Journal of the Korea Convergence Society, 9(8), 1-8. DOI: 10.15207/JKCS.2018.9.8.001
  9. B. Oh & D. Cho. (2011). Number Region Extraction of License Plates Using Colors and Arrangement of Number. Journal of Korea Multimedia Society, 14(9), 1117-1124. https://doi.org/10.9717/kmms.2011.14.9.1117
  10. X. Long & J. Zhou. (2013). An Efficient Method for Dark License Plate Detection. Int. Journal of Digital Content Technology and its Applications, 7(55), 477-485. DOI: 10.4156/JDCTA.VOL7.ISSUE1.55
  11. R. Chen & Y. Luo. (2012). An Improved License Plate Location Method Based on Edge Detection. Proceeding of International Conference on Applied Physics and Industrial Engineering, 1350-1356.
  12. K. Lim, H. Byun & Y. Cho. (2016). Vehicle License Plate Detection in Road Images. Journal of Korean Institute of Information Science and Engineers, 43(2), 186-195.
  13. K. Simonyan & A. Zisserman. (2015). Very Deep Convolutional Networks for Large-scale Image Recognition. [Online]. arXiv:1409.1556. DOI:10.2146/ajhp170251
  14. T. D. Duan, D. A. Duc & T. L. H. Du. (2004). Combining Hough Transform and Contour Algorithm for Detecting Vehiclesi License-Plates. Proceeding of International Symposium on Intelligent Multimedia, Video and Speech Processing, 747-750.
  15. H. Li & C. Shen. (2016). Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs. [Online]. arXiv:1601.05610
  16. Y. Jeong, I. Ansari, J. Shim & J. Lee. (2017). A Car Plate Area Detection System Using Deep Convolution Neural Network. Journal of Korea Multimedia Society. 20(8), 1166-1174. DOI: 10.9717/KMMS.2017.20.8.1166