The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Estimation of transformation parameters using shape matching

형상 정합을 통한 변환 파라미터 추출

  • 박용희 (충남대학교 컴퓨터공학과) ;
  • 전병호 (공주전문대학 산업영상과) ;
  • 김태균 (충남대학교 컴퓨터공학과)
  • Published : 1997.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

Image registration is concerned with the establishment of correspondence between images of the same scene with translational, rotational, and scaling differences. The estimated transformation parameters between images are very important information in the field of many applications. In this paper, we propose a shape matching scheme for finding correspondence points for images with various differences, Tranditional solutions to this area are unreliable for the rotational and schaling changes between images, and the feature extraction of partially occluded scene. To solve those problems, dominant points on digital curves are detected by scale-space filtering, and initial matching is performed by similarity measure of cumulative curvatures for dominant points. For initial matching segments pairs, optimal matching points are calculated using dynamic programming.Finally, transformation parameters are estimated.

Keywords

References

  1. IEEE Trans. on Geoscience and Electronics v.GE-8 Spatial registration of multispectral and multitemporal digital imagery using FFT techniques P. E. Anuta
  2. in Proc. SPIE v.220 SAR image registration by multiresolution correlation R. T. Frankot
  3. Motion Analysis and Image Sequence Processing M. Ibrahim Sezan;Reginald L. Lagendijk
  4. Comput. Vision, Graphics, Image Processing v.35 Algorithms for subpixel registration Q. Tian;M. N. Huhns
  5. IEEE Trans. on Image Processing A computational vision approach to image registration Q. Zheng;R. Chellappa
  6. Proc. IEEE Conf. Comput. Vision Pattern Recognition A feature based approach to face recognition B. S. Manjunath;R. Chellappa;C. Malsburg
  7. Photogrammetric Eng., Remote Sensing v.57 Automated multisensor registration:Requirements and techniques E. Rignot (et al.)
  8. IEEE Trans Geosci. Remote Sensing v.28 Image registration by recognition of corresponding structures A. Ventura;A. Rampini;R. Schettini
  9. IEEE Trans. Geosci. Remote Sensing v.24 A region-based approach to digital image registration with subpixel accuracy A. Goshtasby;G. Stockman;C. Page
  10. IEEE Trans. on Image Processing v.4 no.3 A contour-based approach to Multisensor Image Registration Hui Li;B. S. Manjunath;Sanjit K.Mitra
  11. Computer and Robot Vision Robert M. Haralick;Linda G. Shapiro
  12. Proceedings of the Royal Society, B v.207 Theory of edge detection Marr D.;E. Hildreth
  13. Digital Image Processing W. Pratt
  14. Pattern Recognition v.28 no.11 Corner detection using iterative gaussian smoothing with constant window size Bimal Kumar Ray;Kumar S. Ray
  15. Photogrammetry, Dept. Of Geodetic Science no.1 Aerial Image Matching Using Ψ-S Representation Li J. C.;A. F. Schenk
  16. Pattern Recognition v.28 no.2 Matching of partially Occluded Palnar Curves Arie Pikaz;Itshak Dinstein
  17. Pattern Recognition v.25 no.11 The detection of Dominant points on digital curves by scale space filtering Soo-Chang Pei;Chao-Nan Lin
  18. IEEE Trans. Acoustics, Speech,and Signal Processing v.37 no.2 A Dynamic Programming Algorithm for Elastic Registration of Distorted Pictures Based on Autoregressive Model Henri Maitre;Yifeng Wu
  19. IEEE Trans. on PAMI v.10 no.2 Partial Shape Recognition Using Dynamic Programming John W. Gorman;O. Robert Mitchell;Frank P. Kuhl