Registration of Seal Images Using Contour Analysis

  • Yung-Sheng Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


Many types of noise can be present in an image. Registration becomes difficult when the concerned pattern contains a “seal noise.” In this paper, the seal noise appearing inherently in a seal image is introduced. The registration of seal images used widely in many commercial applications in Chinese society is presented. An effective approach using contour analysis for finding the principal orientation of a seal image is developed for the registration task. Three types of seal image of the author’s own are used for experiments, and results obtained by a moment-based method are given for comparison.


Fourier Descriptor Registration Result Contour Pixel Principal Orientation Concerned Pattern 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Brault, J. J., Plamondon, R.: Segmentation handwritten signatures at their perceptually important points, IEEE Trans. Pattern. Anal. Mach. Intell., Vol. 15, No. 9 (1993) 953–957.CrossRefGoogle Scholar
  2. 2.
    Yang, Y., Horiuchi, T., Toraichi, K.: Automatic seal identification using fluency function approximation and relaxation matching method, Proc. 2nd Intl Conf. Document Anal. Recognition, Tsukuba Science City, Japan (1993) 786–789.Google Scholar
  3. 3.
    Chen, Y.S.: “Automatic identification for a Chinese seal image, Pattern Recognition, Vol. 29, No. 11 (1996) 1807–1820.CrossRefGoogle Scholar
  4. 4.
    Shapiro, L.G., Stockman, G.C.: Computer Vision, Prentice Hall, Inc., New Jersey (2001).Google Scholar
  5. 5.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, Addison Wesley, New York (1992).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Yung-Sheng Chen
    • 1
  1. 1.Department of Electrical EngineeringYuan Ze UniversityChung-LiTaiwan ROC

Personalised recommendations