The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Partial Object Recognition based on Ellipse of Objects using Symmetry in Image Databases

이미지 데이터베이스에서 객체의 타원형 부분의 대칭특성에 기반을 둔 부분객체인식방법

  • 조준서 (한국외국어대학교 경영학과)
  • Published : 2008.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper discusses the problem of partial object recognition in image databases. We propose the method to reconstruct and estimate partially occluded shapes and regions of 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 an ellipse of objects. Our method provides simple techniques to reconstruct occluded regions via a region copy using the symmetry axis within an object. Since our method relies on reconstruction of the object based on the symmetry rather than statistical estimates, it has proven to be remarkably robust in recognizing partially occluded objects in the presence of scale changes, rotation, and viewpoint changes.

이 논문에서 겹쳐지고 잘린 이미지내의 타원형 객체들 가운데 부분적으로 겹쳐져 보이지 않는 외형과 객체 내 영역을 재구성하고 계산하기 위한 방법을 제안한다. 대칭 속성을 이용하여 부분적으로 겹쳐져 보이지 않는 객체를 인식하기 위해서 객체내의 부분인식에 기반을 둔 방법이다. 이 방법은 객체 내에서 대칭축을 이용하여 영역 복사를 통한 보이지 않는 영역을 복원하는 간결한 방법을 제시한다. 이 방법은 통계적 예측보다 대칭 기반의 객체 복원에 의존하기 때문에 부분적으로 겹쳐져 보이지 않는 부분에 대해서 측정된 변수를 가지고 분류 트리를 이용하여 객체 인식를 수행한다. 이는 비록 객체의 자세에는 한계를 가지고 있지만 크기 변경이나 회전, 시각의 변화에서 부분적으로 가려진 객체를 인식하는데 뛰어난 것으로 나타났다.

Keywords

References

  1. H. Bischof and A. Leonardis. Robust recognition of scaled eigenimages through a hierachical approach. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 664-670, 1998
  2. O. Carmichael and M. Hebert, Shape-Based Recognition of Wiry Objects, IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 1537.1552, 2004 https://doi.org/10.1109/TPAMI.2004.128
  3. W. J. Chimitt and L. G. Hassebrook. Automatic scene re-construction from partially overlapping images using on line filter design. In Proceedings of the SPIE Conference on Storage and Retrieval for Image and Video Databases, pp. 171-181,1998
  4. J. Cho and J. Choi. Object Classification based on the Probabilities of Pre-Assigned Intervals. In IEEE Conference on IKE, pp. 49-55, 2004
  5. J. Cho, Feature Extraction for Content-based Image search in Electronic Commerce. 한국정보처리학회 논문지, 2003
  6. P. David and D. DeMenthon. Object Recognition in High Clutter Images Using Line Features. In IEEE International Conference of Computer Vision, pp. 1581- 1588, 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, pp. 533-539, 1997
  8. Ho and L. Chan. A fast ellipse/circle detector using geometric symmetry. Pattern Recognition, pp. 117-124, 1995
  9. W. Jacobs and R. Basri. 3-d to 2-d recognition with regions. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 547-553, 1997
  10. J. Krumm. Object detection with vector quantized binary features. IEEE Computer Vision and Pattern Recognition, pp. 179-185, 1997
  11. K. Mikolajczyk, A. Zisserman, and C. Schmid, Shape Recognition with Edge-Based Features. Proc. British Machine Vision Conference, pp. 779-788, 2003
  12. K. Ohba and K. Ikeuchi. Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. IEEE Trans. Pattern Anal. Mach. Intell., pp. 1043-1048, 1997 https://doi.org/10.1109/34.615453
  13. N. Rajpal, S. Chaudhury, and S. Banerjee. Recognition of partially occluded objects using neural network based indexing. Pattern Recognition, pp.1737.1749, 1999
  14. R. Rao. Dynamic appearance-based recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 540-546, 1997
  15. B. Schiele and A. Pentland. Probabilistic Object Recognition and Localization. In International Conference on Computer Vision, pp. 171-182, 1999
  16. H. Schneiderman and T. Kanade. Probabilistic modeling of local appearance and spatial relationships for object recognition. In IEEE Conference on Computer Vision and PatternRecognition, pp. 45-51, 1998
  17. L. R. Williams and A. R. Hanson. Perceptual completion of occluded surfaces. Computer Vision and Image Understanding, pp. 1-20, 1996 https://doi.org/10.1006/cviu.1996.0043
  18. W. Wu and M. Wang. Elliptical object detection by using its geometircal properties. Pattern Recognition, pp. 1499-1509, 1993 https://doi.org/10.1016/0031-3203(93)90155-P
  19. H. Yuen, J. Illingworth, and J. Kittler. Detecting partially occluded ellipses using the hough transform. Image and Vision Computing, pp. 31-37, 1989 https://doi.org/10.1016/0262-8856(89)90017-6