Advertisement

Efficient Object Recognition Method for Adjacent Circular-Shape Objects

  • Sung-Jong Eun
  • Taeg-Keun Whangbo
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 215)

Abstract

The general object recognition method is based on the various area segmentation algorithms. However, there might be difficulties with segmenting the adjacent objects when their boundaries are not clear. In order to solve this problem, we propose an efficient method of dividing adjacent circular-shape objects into single object through three steps: detection of the region of interest (ROI), determination of the candidate segmentation points, and creation of a segmentation boundary. The simulation shows robust results of 6.5 % average difference ratio compared to the existing methods, even when SNR was severe.

Keywords

Object recognition Adjacent circular-shape objects Local feature Curve fitting 

Notes

Acknowledgments

This research was supported by Gachon University in 2012; by the Ministry of Knowledge Economy of Korea under its Convergence Information Technology Research Center support program (NIPA-2012-H0401-12-1001) supervised by the National IT Industry Promotion Agency.

References

  1. 1.
    Kang CC, Wang WJ A novel edge detection method based on maximization of the objective function. Pattern Recognit 40(2):609–618Google Scholar
  2. 2.
    Norio B, Norihiko I, Toshiyuki T Image area extraction of biological objects from a thin section image by statistical texture analysis. Electron Microse 45:298–306Google Scholar
  3. 3.
    Muerle JL, Allen DC (1968) Experimental evaluation of a technique for automatic segmentation of objects in complex scenes. IPPR, ThopmsonGoogle Scholar
  4. 4.
    Unser M (1995) Texture classification and segmentation for using wavelet frames. IEEE Trans Image Process 4(11):1549–1560Google Scholar
  5. 5.
    Li W, Zhou C, Zhang Z (2004) Segmentation of the body of the tongue based on the improved snake algorithm in traditional Chinese medicine. In: Proceedings of the 5th world congress on intelligent control and automation, pp 15–19Google Scholar
  6. 6.
    Zabih R, Kolmogorov V (2004) Spatially coherent clustering using graph cuts. In: Proceedings of computer vision and pattern recognition, vol 2, pp 437–444Google Scholar
  7. 7.
    Rother C, Kolmogorov V, Blake A (2004) GrabCut: interactive foreground extraction using iterated graph cuts. ACM Trans Graphics 23(3):309–314CrossRefGoogle Scholar
  8. 8.
    Kass M, Witkin A (2004) Demetri Terzopoulos active contour models. Int J Comput Vision 1:321–331CrossRefGoogle Scholar
  9. 9.
    Ng EYK, Chen Y (2006) Segmentation of the breast thermogram: improved boundary detection with the modified snake algorithm. J Mech Med Biol 6(2):123–136Google Scholar
  10. 10.
    Kang DJ, Kweon IS (1999) A fast and stable snake algorithm for medical images. Pattern Recogn Lett 20(10):1069CrossRefGoogle Scholar
  11. 11.
    Murphy TM, Math M, Finke LH (2003) Curvature covariation as a factor of perceptual salience. In: International IEEE EMBS CNECI, pp 16–19Google Scholar
  12. 12.
    Comaniciu D, Meer P (1997) Mean shift analysis and application. In: Seventh international conference computer vision and pattern recognition, pp 750–755Google Scholar
  13. 13.
    Catmull E, Rom R (1974) A class of local interpolating splines. Comput Aided Geom Des 317–326Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.Department of Computer ScienceGachon UniversityGyunggi-DoSouth Korea

Personalised recommendations