Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Dominant Feature based Nomalization and Relational Description of Shape Signature for Scale/Rotational Robustness

2차원 형상 변화에 강건한 지배적 특징 기반 형상 시그너쳐의 정규화 및 관계 특징 기술

  • Song, Ho-Geun (Dept. of Computer&Information Engineering, Hanseo University) ;
  • Koo, Ha-Sung (Dept. of Computer&Information Engineering, Hanseo University)
  • 송호근 (한서대학교 컴퓨터정보공학과) ;
  • 구하성 (한서대학교 컴퓨터정보공학과)
  • Received : 2011.10.22
  • Accepted : 2011.11.09
  • Published : 2011.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a Geometrical Centroid Contour Distance(GCCD) which is described by shape signature based on contour sequence. The proposed method uses geomertrical relation features instead of the absolute angle based features after it was normalized and aligned with dominant feature of the shape. Experimental result with MPEG-7 CE-Shape-1 Data Set reveals that our method has low time/spatial complexity and scale/rotation robustness than the other methods, showing that the precision of our method is more accurate than the conventional desctiptors. However, performance of the GCCD is limited with concave and complex shaped objects.

본 논문에서는 윤곽선의 순열을 기반으로 하여 형상 시그너쳐를 추출하고, 주도적 특징을 기반으로 형상 정열 및 정규화한 뒤, 기존 절대각도기반 관계성질 대신 기하 관계성질을 이용하는 새로운 형상 기술자, 기하학적 중심거리값(Geometrical Centroid Contour Distance : GCCD)을 제안하였다. 비교 실험을 통하여 제안 방식은 기존 기술자들에 비해 시간 복잡도와 공간 복잡도가 작아 실시간 처리에 유리하면서, 2차원 객체의 크기와 회전 변화에 강건함을 보였다. 또한 MPEG-7 표준 영상을 대상으로 한 정확도 실험을 통하여 다양한 영상군에 대한 비교를 수행하여 제안 방식이 기존 방식들보다 높은 정확도를 보임을 확인하였다. 하지만 제안 방식은 볼록형 객체에 대한 높은 정확도를 보이는 반면 오목형이면서 복잡한 형상을 가지는 객체에 대하여는 형상 변별력이 제한된다는 것도 알게 되었다.

Keywords

References

  1. Bober,M.,"MPEG-7 visual shape descriptors," IEEE Trans. Circuits System Video Technology, Vol. 11, No.6, pp.716-719, Jun. 2001. https://doi.org/10.1109/76.927426
  2. Y.C.Jeon, K.I.Lee and K.Kang,"Simply Separation of Head Face Region and Extraction of Facial Feature for Image Security," Journal of Korea Society of Computer and Information, pp.125-133 ,Vol. 13, No. 5, Jan. 2009.
  3. Herbert Freeman,"Computer processing of line dra wing images," ACM Computing Surveys, Vol.6, No.1 , pp.57-97, Mar., 1974 https://doi.org/10.1145/356625.356627
  4. P.Tresadern and I.Reid, "An Evaluation of Shape Des criptors for Image Retrieval in Human Pose Estimation,"The 18th British Machine Vision Conf. Vol.2, pp.800-809, 2007.
  5. B.G.Prasad, K.K.Biswas and S.K.Gupta,"Region base d image retrieval using intergrated color, shape and location index,"Computer Vision and Image Unders tanding, Vol.94, pp.193-233, Jan. 2004 https://doi.org/10.1016/j.cviu.2003.10.016
  6. Z.Wang, Z.Chi and D. Feng, "Shape based leaf image retrieval," IEEE Procs. of Image and Signal Processing, Vol.150, No.1, pp.34-43, Apr., 2003 https://doi.org/10.1049/ip-vis:20030160
  7. G.Mori, S.Belongie and J.Malik,"Efficient Shape Matching using shape Context," IEEE Trans. on Pattern Analysis and Matching Intelligence, Vol.27, No.11, pp.1832-1837, Sep., 2005 https://doi.org/10.1109/TPAMI.2005.220
  8. H.G.Song, K.H.Kang, D.W.Jung and Y.I.Yoon,,"Sha pe Descriptor for 3D Foot Pose Estimation," Journal of The Korean Institute of Maritime Information and Communication Sciences, Vol.14., No.2, pp.469-478, Feb., 2010. https://doi.org/10.6109/jkiice.2010.14.2.469
  9. C.H.Nho, S.R.Lee, J.W.Jung, S.H.Kim and D.W.Ki m, "SoSiM:Shape-based Object Similarity Matching using Shape Feature Descriptors," Journal of the Korean Institute of Information Scientists and Engineers, Vol. 36, No. 2, pp. 73-83, Apr., 2009.
  10. F. Su, T, Nu and R. Yang, "A New Shape Descriptor for Object Recognition and Retrieval," Advances in Multimedia Information Processing-PCM 2010, LNCS 6297, pp.493-502, 2010
  11. Y. Xie and O,M. "Shape Descriptor based on Stru ctural Curvature Histotram for Image Retrieval," Proc. on Computer Science and Information Engineering, 2009 WRI World Congress. Mar. 31 2009-Apr. 2 2009, pp.411-415, Losangeles, CA.
  12. D. Zhang and G. Lu, "Review of Shape Represe ntation and Description Techniques," Pattern Recognition, Vol. 37, pp.1-19, Jan. 2004. https://doi.org/10.1016/j.patcog.2003.07.008
  13. Chang F., Chen C.J. and Lu C.J.,"A linear time component-labeling algorithm using contour tracing technique," Elsevier Inc. Computer Vison and Image Understanding, Feb., 2004
  14. k-nearest neighbor algorithm, Wikipedia, http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
  15. S.H.Kim, S.B.Nam and H.J.Lim, "An Improved Area Edge Detection for Real-Time Image Processing," Journal of Korea Society of Computer and Information, Vol. 14, No. 1, Jan. 2009.
  16. Latechki L. J., Shape Data for the MPEG-7 Core Experiment CE-Shape-1, Web Page : http//www.dis.temple.edu/-latecki/TestData/mpeg7shapeB.tar.gz, 2002
  17. Wayne L. Winston, M. Venkararamanan , "Introdu ction to Mathermatical Programming : Operations Research," Thomson Learning, 2003.