Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Analysis of Hough Transform Using Extended Lookup Table

확장 참조표를 활용한 허프변환의 성능 분석

  • Oh, Jeong-su (Department of Display Engineering, Pukyong National University)
  • Received : 2021.09.29
  • Accepted : 2021.10.18
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes the Hough transform(HT) using an extended lookup table(LUT) to reduce the computational burden of the HT that is a typical straight line detection algorithm, and analyzes its performance. The conventional HT also uses a LUT to the calculation of the parameter 𝜌 of all straight lines passing through an edge pixel of interest(ePel) in order to reduce the computational burden. However, the proposed HT adopts an extended LUT that can be applied to straight lines across the ePel as well as its peripheral edge pixels to induce more computational reduction. This paper proves the validity of the proposed algorithm mathematically and also verifies it through simulation. The simulation results show that the proposed HT reduces the multiplication computation from 49.6% up to 16.1%, depending on the image and the applied extended LUT, compared to the conventional HT.

본 논문은 대표적인 직선 검출 알고리즘인 허프변환이 갖고 있는 계산적인 부담을 줄이기 위해 확장된 참조표를 활용한 허프변환을 제안하고, 성능을 분석하고 있다. 기존 허프변환도 계산 부담을 줄이기 위해 관심 에지 화소를 지나는 모든 직선들의 매개 변수 𝜌 계산에 참조표를 적용한다. 그러나 제안된 허프변환은 더 많은 계산 감소를 유도하기 위해 관심 에지 화소뿐만 아니라 그 주변 에지 화소들을 지나는 직선들에도 적용할 수 있는 확장 참조표를 채택하고 있다. 본 논문은 제안된 알고리즘의 유효성을 수학적으로 증명하고 또한 모의실험을 통해 확인하고 있다. 모의 실험 결과는 제안된 허프변환이 기존 허프변환과 비교해 곱셈 계산량을 영상과 적용된 확장 참조표에 따라 49.6%에서 최대 16.1%까지 감소시키는 것을 보여주고 있다.

Keywords

Acknowledgement

This work was supported by a Research Grant of Pukyong National University (2021)

References

  1. Y. S. Wang, Y. Qi, and Y. Man, "An improved hough transform method for detecting forward vehicle and lane in road," Journal of Physics: Conference Series, vol. 1757. no. 1, pp. 24-25, 2021.
  2. S. Das and R. Kumari, "Application of Extended Hough Transform Technique for Stationary Images in Vehicle License Plate," International Conference for Convergence in Technology, Pune, pp. 1-4, 2021.
  3. N. N. Kamal and E. Tariq, "License Plate Tilt Correction: A Review," Engineering and Technology Journal, vol. 39, no. 5, pp. 101-116, Mar. 2021. https://doi.org/10.30684/etj.v39i1B.1839
  4. R. O. Duda and P. E. Hart. "Use of the Hough transformation to detect lines and curves in pictures," Communications of the Association for Computing Machinery, vol. 15, no. 1, pp. 11-15, Jan. 1972. https://doi.org/10.1145/361237.361242
  5. R. C. Gonzalez and E. W. Richard, Digital Image Processing, 3rd ed. New Jersey, NJ:Prentice Hall, 2008.
  6. A. Kaehler and G. Bradski, Learning OpenCV3, Wikibooks, Paju, 2018.
  7. J. S. Oh, "An Improved Hough Transform Using Valid Features," Journal of The Korea Institute of Information and Communication Engineering, vol. 18, no. 9, pp. 2203-2208, Sep. 2014. https://doi.org/10.6109/JKIICE.2014.18.9.2203
  8. S. K. Hwang, Visual C++ Image Processing, Programming, Gilhut, Seoul, 2015.