The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Image Rotation Correction of Real Time Using ACB Algorithm Based on Sobel Edge

Sobel Edge 기반의 ACB 알고리즘을 적용한 실시간 이미지 회전보정 방법연구

  • Received : 2015.03.23
  • Accepted : 2015.04.24
  • Published : 2015.06.30
⟨ Previous Next ⟩

Abstract

The latest image processing system does not have only one processor but various processor that works simultaneously. In an optimized memory that includes fast processing speed and high recognition ratio are essential because of recognition ratio is very important for a certain things. In this paper, the proposed ACB (Active Contour Boundary) algorithm can correct rotated image for various real time image recognition system. Basically, for important features of simple expression as an inputted image, SOBEL edge algorithm was used. Then the angle of rotated image can be calculated using ACB, and it can be implemented the ACB using the filtering process within a specific rage. Comparing with the conventional CORDIC algorithm to the proposed ACB algorithm shows the result which is about 17 times much faster that the computed time.

최근 영상처리 시스템은 하나의 프로세스만이 아닌 다양한 종류의 프로세스가 동시에 동작하여 처리 된다. 무엇보다도, 특정 사물에 대한 인식률은 매우 중요하기 때문에 최적화 된 메모리를 비롯하여 빠른 처리 속도 및 높은 인식률에 대한 성능은 필수적이다. 본 논문에서는 각종 영상 인식 시스템의 실시간 영상에 대한 회전된 영상의 보정을 위한 ACB(Active Contour Boundary) 알고리즘을 제안한다. 기본적으로, 입력된 영상의 중요한 특징을 간단히 표현하기 위해 SOBEL 에지 알고리즘을 사용하였고, 특정 범위 안에서 필터링을 통하여 ACB를 구현함으로써 회전된 영상의 각도를 산출하였다. 기존 방식인 CORDIC 알고리즘과 비교하였으며, 처리속도 면에서 약 17배 이상의 개선된 결과를 확인하였다.

Keywords

Acknowledgement

Grant : Development of a smart automotive ADAS SW-Soc for a self-driving car

Supported by : Ministry of Trade, industry & Energy

References

  1. N. Modi, C. Modi, C. Paunwala, and S. Pantnaik, "Skew Correction for Vehicle License Plates using Principal Component of Harris Corner Feature", International Conference on Communication Systems and Network Technologies, 2011.
  2. G. Jones, D. Lee, N. Holliman, and D. Ezra, "Controlling Perceived Depth in Stereoscopic Image", Stereoscopic Displays and Vertual Systems VIII, Proceedings of SPIE, Vol. 4297, pp. 42-53, June 2001.
  3. T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns", IEEE Trans. on pattern analysis and machine intelligence, Vol. 24, No. 3, pp. 971-987, July 2002. https://doi.org/10.1109/TPAMI.2002.1017623
  4. Keun-Nyoung Yang and Byung-Joo Oh, "Rotation Invariant Face Detection using Sub-Window rotation in Adaboosting Algorithm", JKIIT, Vol. 4 No. 2, pp. 27-34, Apr. 2006.
  5. Y. H. Hu and H. H. M. Chern, "A novel implementation of CORDIC algorithm using backward angle recoding(BAR)", IEEE Trans. on computers, Vol. 45, No. 12, pp. 1370-1378, Dec. 1996. https://doi.org/10.1109/12.545967
  6. J. Valls, M. Kuhlmann, and K. K. Parhi, "Evaluation of CORDIC algorithms for FPGA design", J. VLSI Signal Process. Syst., Vol. 32, No. 3, pp. 207-222, Nov. 2002. https://doi.org/10.1023/A:1020205217934
  7. Jia Xin, Hu Zhencheng, and Guan Hsin, "A New Multi-Sensor Platform for Adaptive Driving Assistance System (ADAS)", IEEE W. congress on intelligent control and automation, pp. 1224-1230, June 2011.
  8. T. Kumar and K. Verma, "A Theory Based on Conversion of RGB image to Gray image", IJCA, Vol. 7, No. 2, pp. 7-10, Sep. 2010.
  9. D. Guevorkian, A. Launiainen, P. Liuha, and V. Lappalainen, "Architectures for the Sum of Absolute Differences Operation", IEEE Emer. intelligant computing technology and applications, pp. 55-62, Oct. 2002.