The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Contour-Based Partial Object Recognition Of Elliptical Objects Using Symmetry

대칭특성을 이용한 타원형 객체의 외형기반 부분인식에 관한 연구

  • 조준서 (한국외국어대학교 경영학과)
  • Published : 2006.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In This Paper, We Propose The Method To Reconstruct And Estimate Partially Occluded Elliptical Objects In Images From Overlapping And Cutting. We Present The Robust Method For Recognizing Partially Occluded Objects Based On Symmetry Properties, Which Is Based On The Contours Of Elliptical Objects. A Proposed Method Provides Simple Techniques To Reconstruct Occluded Regions Via A Region Copy Using The Symmetry Axis Within An Object. Based On The Estimated Parameters For Partially Occluded Objects, We Perform Object Recognition On The Classifier. Since A Proposed Method Relies On Reconstruction Of The Object Based On The Symmetry Properties Rather Than Statistical Estimates, It Has Proven To Be Remarkably Robust In Recognizing Partially Occluded Objects In The Presence Of Scale Changes, Object Pose, And Rotated Objects With Occlusion, Even Though h Proposed Method Has Minor Limitations Of Object Poses.

이 논문에서 겹쳐지고 잘린 이미지내의 타원형 객체들 가운데 부분적으로 겹쳐져 보이지 않는 외형과 영역을 재구성하고 계산하기 위한 방법을 제안한다. 대칭적인 속성에 기반을 두고, 불완전한 객체 인식을 위해 타원형 객체의 윤곽에 기반을 둔 방법이다. 이 방법은 한 객체 안에서 대칭 축을 이용하는 영역 복사를 통한 겹쳐져 보이지 않는 영역을 재구성하는 간결한 기교를 제공한다. 부분적으로 겹쳐져 보이지 않는 영역에 대한 측정된 변수에 기반을 두고, 분류 트리의 객체 인지를 수행하는데, 이 방법은 통계 수치보다 대칭에 기반을 둔 객체 재구성에 의존하기 때문이다. 이는 크기 변경과, 객체의 자세, 회전, 등에서 비록 객체 자세에는 한계를 가지고 있지만 부분적으로 겹쳐져 보이지 않는 객체의 인지에서 탁월하다.

Keywords

References

  1. 조준서, '내용기반으로한 이미지 검색에서 이미지 객체틀의 외형특정추출' 정보처리학회논문지B, 제10-B권 제7호, 2003 https://doi.org/10.3745/KIPSTB.2003.10B.7.823
  2. H. Bischof and A.Leonard, Robust recognition of scaled eigenimages through a hierachical approach, In IEEE Conference on CVPR, 1998 https://doi.org/10.1109/CVPR.1998.698675
  3. H. Blum and R.N. Nagel. Shape description using weighted symmetric axis features. Pattern Recognition, 1978 https://doi.org/10.1016/0031-3203(78)90025-0
  4. O. Carmichael and M. Hebert, Shape-Based Recognition of Wiry Objects, IEEE Trans. on PAMI, 2004 https://doi.org/10.1109/TPAMI.2004.128
  5. J. Cho and J. Choi. Object Classification based on the Probabilities of Pre-Assigned Intervals. In IEEE Conference on IKE, 2004
  6. P. David and D. DeMenthon. Object Recognition in High ？Clutter Images Using Line Features. In IEEE International Conference of Computer Vision, 2005 https://doi.org/10.1109/ICCV.2005.173
  7. J. Edwards and H. Murase. Appearance matching of occluded objects using coarse-to-fine adaptive masks. In IEEE Conference on Computer Vision and Pattern Recognition, 1997 https://doi.org/10.1109/CVPR.1997.609377
  8. M. Fleck. Local Rotational Symmetries. In IEEE Conference on CVPR, 1986
  9. C. Ho and L. Chan. A fast ellipse/circle detector using geometric symmetry. Pattern Recognition, 1995 https://doi.org/10.1016/0031-3203(94)00077-Y
  10. J. Hornegger, H. Niemann, and R. Risack. Appearancebased object recognition using optimal feature transforms. Pattern Recognition, 2000 https://doi.org/10.1016/S0031-3203(99)00048-5
  11. D. W. Jacobs and R. Basri. 3D to 2D recognition with regions. In IEEE Conference on CVPR, 1997 https://doi.org/10.1109/CVPR.1997.609379
  12. G. Jones and B. Bhanu. Recognition of articulated and occluded objects. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999 https://doi.org/10.1109/34.777371
  13. J. Krumm. Object detection with vector quantized binary features. In IEEE Conference on CVPR, 1997 https://doi.org/10.1109/CVPR.1997.609317
  14. A. Leonardis and H. Bishof. Dealing with Occlusions in the Eigenspace Approach. In IEEE Conference on CVPR, 1996 https://doi.org/10.1109/CVPR.1996.517111
  15. D. G. Lowe. Object Recognition from Local Scale-Invariant Features. In International Conference on Computer Vision, 1999 https://doi.org/10.1109/ICCV.1999.790410
  16. K. Mikolajczyk, A. Zisserman, and C. Schmid, Shape Recognition with Edge-Based Features. Proc. British Machine Vision Conference, 2003
  17. K. Ohba and K. lkeuchi. Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. IEEE Trans. Pattern Anal. 1997 https://doi.org/10.1109/34.615453
  18. N. Rajpal, S. Chaudhury, and S. Banerjee. Recognition of partially occluded objects using neural network based indexing. Pattern Recognition, 1999 https://doi.org/10.1109/34.790437
  19. R. Rao. Dynamic appearance-based recognition. In IEEE Conference on CVPR, 1997 https://doi.org/10.1109/CVPR.1997.609378
  20. John C. Russ. The Image Processing Handbook. CRC Press, 3rd edition, 1998
  21. W. Wu and M. J. Wang. Elliptical object detection by using its geometrical properties. Pattern Recognition 1993 https://doi.org/10.1016/0031-3203(93)90155-P
  22. Lance R. Williams. Topological reconstruction of a smooth manifold-solid from its occluding contour. Journal of Computer Vision, 1997 https://doi.org/10.1023/A:1007967925618