한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

뉴턴 최적화를 통해 개선된 아다부스트 훈련과 MCT 특징을 이용한 번호판 검출

License Plate Detection with Improved Adaboost Learning based on Newton's Optimization and MCT

  • 이영현 (고려대학교 영상정보처리협동과정) ;
  • 김대훈 (고려대학교 전기전자전파공학부) ;
  • 고한석 (고려대학교 전기전자전파공학부)
  • Lee, Young-Hyun (Dept. of Visual Information Processing, Korea University) ;
  • Kim, Dae-Hun (School of Electrical Engineering, Korea University) ;
  • Ko, Han-Seok (School of Electrical Engineering, Korea University)
  • 투고 : 2012.10.10
  • 심사 : 2012.10.23
  • 발행 : 2012.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 MCT(Modified Census Transform) 특징과 개선된 아다부스트 분류기를 이용한 번호판 검출 알고리즘을 제안한다. MCT 특징은 영상의 국소 지역 패턴을 정수화하여 표현하는 특징으로서 조명 변화에 강인하고 메모리 효율이 높은 장점이 있다. 그러나 패턴을 표현하는 정수형의 MCT 특징값들이 이산적인 특징을 가지기 때문에 아다부스트 훈련 방법을 적용하기 위해서는 룩업테이블 (Lookup Table)을 이용하여 분류기를 설계해야 한다. 그동안의 아다부스트 훈련 방법에 대한 최적화 연구는 지수 기준(exponential criterion)을 최소화 하는 방법에 대한 방향으로 연구가 진행되고 있다. 본 논문에서는 MCT 특징을 이용하고 지수 기준의 뉴턴 최적화를 통해 아다부스트 훈련 방법을 개선하여 번호판 검출성능을향상 시키는 방법을 제안한다. 번호판샘플 영상과 필드 테스트 영상에 대한 실험을 통해 제안한 방법의 성능을 고찰하고, 기존의 일반 아다부스트 훈련을 이용한 검출 방법과의 비교 실험을 통해 그 효용성을 입증한다.

In this paper, we propose a license plate detection method with improved Adaboost learning and MCT (Modified Census Transform). The MCT represents the local structure patterns as integer numbered feature values which has robustness to illumination change and memory efficiency. However, since these integer values are discrete, a lookup table is needed to design a weak classifier for Adaboost learning. Some previous research efforts have focused on minimization of exponential criterion for Adaboost optimization. In this paper, a method that uses MCT and improved Adaboost learning based on Newton's optimization to exponential criterion is proposed for license plate detection. Experimental results on license patch images and field images demonstrate that the proposed method yields higher performance of detection rates with low false positives than the conventional method using the original Adaboost learning.

키워드

참고문헌

  1. Younghyun Lee, Taeyup Song, Hanjun Kim, David K. Han and Hanseok Ko, "Hostile Intent and Behaviour Detection in Elevators", 4th International Conference on Imaging for Crime Detection and Prevention (ICDP-11), London, UK, November, 2011.
  2. Michael A. Goodrich, Alan C. Schultz. "Human-robot interaction: a survey", Journal Foundations and Trends in Human-Computer Interaction, Vol.1, No.3, pp. 203-275, February, 2007. https://doi.org/10.1561/1100000005
  3. Ionescu, D., Ionescu, B., Gadea, C., Islam, S., "A Multimodal Interaction Method that Combines Gestures and Physical Game Controllers", Computer Communications and Networks (ICCCN), 2011 Proceedings of 20th International Conference on , pp.1-6, August, 2011
  4. Jong Sun Kim, Dong Hae Yeom, Young Hoon Joo, "Fast and robust algorithm of tracking multiple moving objects for intelligent video surveillance systems", Consumer Electronics, IEEE Transactions on , vol.57, no.3, pp.1165-1170, August, 2011. https://doi.org/10.1109/TCE.2011.6018870
  5. Kyu-Dae Ban, Jaeyeon Lee, DoHyung Kim, Jaehong Kim, and Yun Koo Chung, "Tiny and Blurred Face Alignment for Long Distance Face Recognition", ETRI Journal, vol.33, no.2, pp.251-258, April, 2011. https://doi.org/10.4218/etrij.11.1510.0022
  6. Hye-Jin Kim, Ho Sub Yoon, Jae Hong Kim, "User recognition based on continuous monitoring and tracking", Human-Robot Interaction (HRI), 2011 6th ACM/IEEE International Conference on, pp.163-164, March, 2011.
  7. Anwar Saeed, Ayoub Al-Hamadi, Michael Heuer, "Speaker Tracking Using Multi-modal Fusion Framework", Image and Signal Processing Lecture Notes in Computer Science, Volume 7340, pp 539-546, June, 2012.
  8. Gang-Zeng Mao, Yi-Leh Wu, Maw-Kae Hor, Cheng-Yuan Tang, "Real-Time Hand Detection and Tracking against Complex Background", Intelligent Information Hiding and Multimedia Signal Processing, 5th International Conference on , pp.905-908, September, 2009.
  9. Feifei Huo, Hendriks, E., Paclik, P., Oomes, A.H.J.,, "Markerless human motion capture and pose recognition", Image Analysis for Multimedia Interactive Services, 10th Workshop on, pp.13-16, May, 2009.
  10. Christos Nikolaos E. Anagnostopoulos, Ioannis E. Anagnostopoulos, Vassili Loumos, Eleftherios Kayafas, "A license plate-recognition algorithm for intelligent transportation system applications", IEEE Transactions on Intelligent Transportation Systems Vol.7 No.3, September, 2006.
  11. S.Z. Wang, H.M. Lee, "Detection and recognition of license plate characters with different appearances", in Proc. Conf. Intell. Transp. Syst., vol. 2, pp. 979-984, October, 2003.
  12. X. Shi, W. Zhao, Y. Shen, "Automatic license plate recognition system based on color image processing", in O. Gervasi et al. (Eds.), Lecture Notes on Computer Science, vol. 3483, Springer, pp. 1159-1168, May, 2005.
  13. T.D. Duan, T.L. Hong Du, T.V. Phuoc, N.V. Hoang, "Building an automatic vehicle license plate recognition system", in Proc. Int. Conf. Comput. Sci. RIVF, pp. 59-63, Febuary, 2005.
  14. H. Zhang, W. Jia, X. He and Q. Wu, "Learning-Based License Plate Detection Using Global and Local Features", IEEE International Conference on Pattern Recognition, 2006.
  15. Gang Li, Ruili Zeng, Ling Lin, "Research on vehicle license plate location based on neural networks", in 1st International Conference on Innovative Computing, Information and Control, September, 2006.
  16. B. Froba, and A. Ernst, "Face Detection with the Modified Census Transform", In Proceeding of the Sixth IEEE Conference on Automatic Face and Gesture Recognition, pp. 91-96, May, 2004.
  17. T. Song, Y. Lee, M. Kim, B. Ku, and H. Ko, "Fusion Methods of License Plate Detection and Super Resolution for Improving License Plate Recognition", Journal of The Korea Society of Computer and Information, Vol. 16, No. 4, pp. 53-60, April, 2011. https://doi.org/10.9708/jksci.2011.16.4.053
  18. Y. Freund and R. E. Schapire, "A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting", Journal of Computer and System Sciences, vol.55, pp.119-139, March, 1997. https://doi.org/10.1006/jcss.1997.1504
  19. R. E. Schapire and Y. Singer, "Improved Boosting Algorithms using Confidence-rated Predictions", Machine Learning, vol.37, pp.297-336, December, 1999. https://doi.org/10.1023/A:1007614523901
  20. J. Friedman, T. Hastie and R. Tibshirani, "Additive Logistic Regression: a Statistical View of Boosting", Annals of statistics, vol.28, no.2, pp.337-407, August, 2000.
  21. P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features", IEEE Conference on Computer Vision and Pattern Recognition, vol.1, pp.511-518, December, 2001.

피인용 문헌

  1. 인공 신경망을 이용한 영상의 유해성 결정 vol.16, pp.10, 2012, https://doi.org/10.5762/kais.2015.16.10.6708