The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Optimal Structures of a Neural Network Based on OpenCV for a Golf Ball Recognition

골프공 인식을 위한 OpenCV 기반 신경망 최적화 구조

  • 김강철 (전남대학교 전기전자통신컴퓨터공학부)
  • Received : 2014.12.03
  • Accepted : 2015.02.09
  • Published : 2015.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper the optimal structure of a neural network based on OpenCV for a golf ball recognition and the intensity of ROI(Region Of Interest) are calculated. The system is composed of preprocess, image processing and machine learning, and a learning model is obtained by multi-layer perceptron using the inputs of 7 Hu's invariant moments, box ration extracted by vertical and horizontal length or ${\pi}$ calculated by area of ROI. Simulation results show that optimal numbers of hidden layer and the node of neuron are selected to 2 and 9 respectively considering the recognition rate and running time, and optimal intensity of ROI is selected to 200.

본 논문은 OpenCV 라이브러리를 기반으로 골프공 인식을 위한 신경망의 최적화 구조와 관심영역의 빛의 명도를 계산한다. 개발된 시스템은 전처리, 영상처리, 기계 학습 과정으로 구성되며, 기계 학습과정은 테스트 영상으로부터 골프공과 다른 오브젝트에 대한 Hu의 7 불변 모멘트, 가로 및 세로 비율 또는 면적으로부터 계산된 ${\pi}$를 입력으로 사용하여 다층 퍼셉트론을 기반으로 학습모델을 구한다. 다층 퍼셉트론에 대한 최적의 은닉층과 노드의 수를 결정하도록 모의 실험한 결과 2개의 은닉층과 각 은닉층에 9개의 노드를 가질 때 최대의 인식율과 최소 실행 시간을 얻었다. 그리고 관심영역의 최적 명도는 200으로 계산되었다.

Keywords

References

  1. I.-S. Oh, Pattern Recognition, Korea, Kyobobook publisher, 2008.
  2. R. Laganiere, OpenCV 2 Computer Vision Application Programming Cookbook, UK, Packt Publishing, 2011.
  3. G. Bradski, A. Kaebler, Learning OpenCV: Computer Vision with the OpenCV Library, CA, O'Reilly Media, 1st edition, October, 2008.
  4. J. Zhu, J. Chong, K-C Kim, "The Recognition and Distance Estimation of a Golf Ball using a WebCam," J. of Korea Institute of Electronic Communication Sciences, vol. 8, no. 12, 2013, pp. 1833-1839. https://doi.org/10.13067/JKIECS.2013.8.11.1833
  5. K.-C. Kim, S.-Y. Lee, S.-Y. Moon, "Design of the recognition and position estimation system for a golf ball collecting robot," SCTA, KwangJu, 2012, pp. 104-106.
  6. T. Wanmei, "The Study of the Optimal Structure of BP Neural Network," Systems Engineering Theory and Practice, vol. 25, no. 10, 2005, pp. 95-100.
  7. R. C. Gonzalez, R. E. Woods, Digital Image Processing, Prentice Hall, Third edition, 2008.
  8. http://www.cse.iitd.ernet.in/-pkalra/csl783/canny.pdf
  9. X. He, J. Li, D. Wei, W. Jia, Q. Wu, "Canny Edge Detection on a Virtual Hexagonal Image Structure,"JCPC2009, Sydney, 2009, pp. 167-172.
  10. M.-K. Hu, "Visual pattern recognition by moment invariants,"IRE Trans. Information Theory, Vol. 8, 1962, pp. 179-187.
  11. K.-B Kim, Y.-W Woo, "Content-based Image Retrieval Using HSI Color Space and Neural Networks," J. of Korea Institute of Electronic Communication Sciences, vol. 5, no. 2, 2010, pp. 152-157.

Cited by

  1. Tracking Method for Moving Object Using Depth Picture vol.19, pp.4, 2016, https://doi.org/10.9717/kmms.2016.19.4.774