Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Efficient Correction of a Rotated Object Using Radon Transform

라돈 변환을 이용한 회전된 물체의 효율적인 보정

  • Published : 2008.05.15
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an input image reduction method to solve the problems of Radon transform which is a line structure analysis tool to correct a rotated object through a vision system. First we extract an object image removed background from the input image. Then we also select a reduced object image as a final input mage of Radon transform from the object image by considering slope. Finally we extract a rotated angle by using Radon transform with the final input image and correct the rotated object with the angle. In experimental results, we could improve the process time of about 64%, reduce the memory space of about 18% and make progress the line detection rate of about 18%.

본 논문은 비전 시스템을 통하여 입력되어 들어오는 회전된 물체를 보정하기 위해 사용하는 선 구조 분석 도구인 라돈변환의 문제점을 해결하기 위해 입력 영상 간소화 방법을 제안한다. 먼저, 비전 시스템을 통하여 입력된 영상 내에서 불필요한 배경 부분을 제거하여 물체 영상을 추출한다. 다음, 추출된 물체 영상에 대하여 기울기를 고려하여 제한된 물체 영상만을 라돈 변환의 최종 입력 영상으로 추출한다. 마지막으로 최종 입력 영상에 대하여 라돈 변환을 사용하여 회전각을 추출한 후, 원 영상 내의 회전된 물체를 보정한다. 실험 결과, 제안한 방법은 처리 속도를 약 64% 향상시킬 수 있었고, 기억용량은 약 18% 줄일 수 있었으며, 선 검출율은 약 18%까지 향상시킬 수 있었다.

Keywords

References

  1. J. Radon, "Uber die Bestimmung von Funktionen durch ihre Integralwerte langs gewisser Mannig- faltigkeiten," Berichte Sachsische Akademie der Wissenschaften, Leipzig, Mathematisch-Physikal- ische Klasse, Vol.69, pp. 262-277, 1917
  2. Nguyen Dinh Thuc and Duong Anh Duc, "The Hough Transform - A Radon - Like Transform," International Conference on Electronics, Information, and Communications, pp. 274-275, 2004
  3. Seung Jin Park, Muhammad Bilal Ahmad, Rhee Seung-Hak, Seung Jo Han, and Jong An Park, "Image Corner Detection Using Radon Transform," LNCS 3046, pp. 948-955, 2004
  4. Nitin Aggarwal and William Clem Karl, "Line Detection in Images Through Regularized Hough Transform," IEEE Trans. on Image Processing, Vol.15, No.3, pp. 582-591, 2006 https://doi.org/10.1109/TIP.2005.863021
  5. William H. Press, "Discrete Radon transform has an exact, fast inverse and generalizes to operations other than sums along lines," PNAS, Vol.103, No.51, pp. 19249-19254, 2006 https://doi.org/10.1073/pnas.0609228103
  6. Cris L. Luengo Hendriks et al., "The generalized Radon transform: Sampling, accuracy and memory considerations," Pattern Recognition, Vol.38, No.12, pp. 2494-2505, 2005 https://doi.org/10.1016/j.patcog.2005.04.018
  7. John A. Martiney, Uriel Rodriguez, and Michael Nechyba, "An automated implementation of beam- lets to classify frames of triggered lightning," FCRAR 2003, pp. 1-6, 2003
  8. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Addison Wesley, 1992
  9. N. Otsu, "A Threshold Selection Method from Gray-Level Histogram," IEEE Trans. on Systems, Man, and Cybernetics SMC-9, pp. 62-66, 1979