DOI QR코드

DOI QR Code

각막 내피 세포 영상내 육각형 경계의 검출과 보완법

Extraction and Complement of Hexagonal Borders in Corneal Endothelial Cell Images

  • 김응규 (한밭대학교 정보통신공학과)
  • Kim, Eung-Kyeu (Department of Information and Communication Engineering, Hanbat National University)
  • 투고 : 2012.09.08
  • 발행 : 2013.03.25

초록

본 연구에서는 저 명암 대비 영상에서 잡음이 많은 육각형을 포함하는 윤곽 검출과 보완의 2단계 처리방법을 제안한다. 이 방법은 라플라시안-가우시안 필터(LGF)의 조합과 형상에 의존하는 필터의 아이디어에 기초한다. 먼저, 1단계에서는 모서리에서 특히 육각형상의 에지를 검출하기 위한 검출기로서 6개의 마스크를 갖는 알고리즘을 사용한다. 여기에서 두 개의 삼각화살 모양의 필터는 육각형의 삼각화살 모양의 접속부를 검출하기 위해 사용되고, 기타 네 개의 필터는 육각형 주변의 에지를 검출하기 위해 사용된다. 자연영상으로서 보통 규칙적인 육각형상의 각막 내피 세포를 선택하며, 이 각막 내피 세포의 형상을 자동적으로 계측하는 것은 임상진단에 있어서 중요하다. 그 유효성을 평가하기 위해 제안 방법과 기존 방법을 잡음을 포함하는 육각형 영상에 적용한다. 그 결과, 제안 알고리즘이 기존의 다른 방법에 비해 잡음에 대한 강인성과 출력 신호 대 잡음비, 에지 일치율 및 검출 정확도의 면에서 보다 양호한 검출률을 나타냈다. 다음으로, 2단계에서는 에너지 최소화 알고리즘에 의한 세선화 영상의 결손 부분을 보완한 후 임상진단에 필요한 정보를 제공하는 세포의 면적과 분포를 계산한다.

In this paper, two step processing method of contour extraction and complement which contain hexagonal shape for low contrast and noisy images is proposed. This method is based on the combination of Laplacian-Gaussian filter and an idea of filters which are dependent on the shape. At the first step, an algorithm which has six masks as its extractors to extract the hexagonal edges especially in the corners is used. Here, two tricorn filters are used to detect the tricorn joints of hexagons and other four masks are used to enhance the line segments of hexagonal edges. As a natural image, a corneal endothelial cell image which usually has regular hexagonal form is selected. The edge extraction of hexagonal shapes in corneal endothelial cell is important for clinical diagnosis. The proposed algorithm and other conventional methods are applied to noisy hexagonal images to evaluate each efficiency. As a result, this proposed algorithm shows a robustness against noises and better detection ability in the aspects of the output signal to noise ratio, the edge coincidence ratio and the extraction accuracy factor as compared with other conventional methods. At the second step, the lacking part of the thinned image by an energy minimum algorithm is complemented, and then the area and distribution of cells which give necessary information for medical diagnosis are computed.

키워드

참고문헌

  1. LS. Davis, "A survey of Edge Detection Techniques," Computer Graphics and Image Processing, Vol.4, pp.248-270, 1975. https://doi.org/10.1016/0146-664X(75)90012-X
  2. D. Marr, E. Hidreth, "Theory of edge detection," Processing R., Society, Lond, Vol.B207, pp.187-217, 1980.
  3. N. Yamaguchi, N. Tamori, and A. Shiomi, "A Lane Detection Method Using Adaptive Edge Preservative Smoothing," The ICEC Trans. on Information Systems, Part 2, Vol.J88-D-II, No.8, pp.1421-1431, Aug. 2002.
  4. M. Basu, "Gaussian-based edge-detection method-a survey," IEEE Trans. System, Man and Cybernetics, Part C, Vol.32, Issue 3, pp.252-260, Aug. 2002. https://doi.org/10.1109/TSMCC.2002.804448
  5. Na Mi Kim, Min Kyu Shin, Su Jin Kim, "Confocal Microscopic Findings of Transplanted Cornea 10 Years After Penetrating Keratoplasty," Journal of the Korean Ophthalmological Society, Vol.50, No.5, pp.779-784, 2009. https://doi.org/10.3341/jkos.2009.50.5.779
  6. Sanjay V. Patel, William M. Bourne, "Corneal Endothelial Cell Loss 9 Years After Excimer Laser Keratorefractive Surgery," JAMA Ophthalmology, Vol.127, No.11, pp.1423-1427, 2009.
  7. B. Lipkin, A. Rosenfeld, Picture Processing and Psychopictorics, JMS Prewitt: Object Enhancement and Extraction, Academic Press, New York, 1970.
  8. K. Suzuki, I. Horiba and N. Sugie, "Neural edge enhance for supervised edge enhancement from noisy images," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.25, Issue 12, pp.1582-1596, Dec. 2003. https://doi.org/10.1109/TPAMI.2003.1251151
  9. F. Gasparini, S. Corchs, R. Schettini, "Adaptive Edge Enhancement using a Neurodynamical Model of Visual Attention," ICIP, pp.972-975, 2005.
  10. P. Shivakumara, W. Huang, and C. Tan, "An Efficient Edge based Technique for Text Detection in Video Frames," IEEE The Eighth International Association of Pattern Recognition(IAPR) International Workshop on Document Analysis Systems(DAS), 307-314, 2008.
  11. Sung Woong Shin, Jun Chul Kim, Kum Hui Oh, Yung Ran Lee, "Automatic Matching of Multi-Sensor Images Using Edge Detection Based on Thining Algorithm," Korean Journal of Geomatics, Vol.26, No.4, pp.407-414, 2008.
  12. Jun-Sik Kwon, "Obtaining 1-pixel Width Line Using an Enhanced Parallel Thinning Algorithm," Journal of the Institute of Electronics Engineers of Korea, Vol.46, No.1, SP, pp.1-6, 2009.
  13. Yun-Hee Woo, Mi-Na Ha, Seung-Min Jung, "A Hardware Implementation of Fingerprint Identification Thinning Algorithm," Spring Conference Proceedings 2012 of The Korean Institute of Maritime Information and Communication Sciences, Vol.14, No.1, pp.493-496, 2010.
  14. S. E. Umbaugh, Computer Imaging Digital Image Analysis and Processing, A CRC Press Book, pp.328-355: pp.377-391, 2005.
  15. R. C. Gonzalez, R. E. Woods, S. L. Eddins, Digital Image Processing using MATLAB, PEASON Prentice Hall, Inc., pp.125-140, 2005.
  16. A. Kass, A. Witkin, D. Terzopoulos, "Snakes Active Contour Models," International Journal of Computer Vision, Vol.1, No.3, pp.321-331, 1988. https://doi.org/10.1007/BF00133570
  17. Eung-Kyeu Kim, "Extraction of Renal Glomeruli Region using Genetic Algorithm," Journal of the Institute of Electronics Engineers of Korea, Vol.46 SP, No.2, 2009.