Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Image Segmentation using Multi-scale Normalized Cut

다중스케일 노멀라이즈 컷을 이용한 영상분할

  • Lee, Jae-Hyun (Department of Electronic Engineering, Sogang University) ;
  • Lee, Ji Eun (Department of Electronic Engineering, Sogang University) ;
  • Park, Rae-Hong (Department of Electronic Engineering, Sogang University)
  • Received : 2013.03.13
  • Accepted : 2013.07.19
  • Published : 2013.07.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a fast image segmentation method that gives high segmentation performance as graph-cut based methods. Graph-cut based image segmentation methods show high segmentation performance, however, the computational complexity is high to solve a computationally-intensive eigen-system. This is because solving eigen-system depends on the size of square matrix obtained from similarities between all pairs of pixels in the input image. Therefore, the proposed method uses the small-size square matrix, which is obtained from all the similarities among regions obtained by segmenting locally an image into several regions by graph-based method. Experimental results show that the proposed multi-scale image segmentation method using the algebraic multi-grid shows higher performance than existing methods.

본 논문은 기존 그래프 컷 기반 영상분할의 성능은 유지하면서 연산속도가 빠른 영상분할 방법을 제안한다. 기존 그래프 컷 기반 영상분할은 높은 성능을 보이지만 고유쌍 연산으로 인해 분할 속도가 느리다는 단점을 지닌다. 이는 고유쌍 연산에서 영상 내 모든 화소 사이의 유사도를 고려하여 정방행렬을 만들기 때문이다. 그러므로 제안하는 방법은 영상을 여러 영역으로 분할하여 작은 크기의 정방행렬을 구성하고 이를 통해 고유쌍 연산 속도를 크게 향상시킨다. 본 논문에서는 대수적 다중 격자를 이용한 다중스케일 영상분할법을 제안하고 실험 결과를 통해 제안하는 방법이 기존 영상분할 방법보다 그 성능이 더 우수함을 보인다.

Keywords

References

  1. H. Han, J. Jeong, E. Arai, Y. Choi, and J. Jo, "3D perception enhancement using depth map based color processing", Proc. IEEE Int. Conf. Consumer Electronics, pp. 177-178, Jan. 2011.
  2. X. Wei, S. L. Phung, and A. bouzerdoum, "Scene segmentation and pedestrian classification from 3-D range and intensity images", Proc. IEEE Int. Conf. Multimedia and Expo, pp. 103-108, Jul. 2012.
  3. M. Fric, P. Kamencay, and P. Lukac, "Automatic segmentation and impact for retrieval images", Proc. Conf. Signal Processing Algorithms, Architectures, Arrangements, and Applications, pp. 1-5, Sept. 2011.
  4. T. Junwei and H. Yongxuan, "Histogram constraint based fast FCM cluster image segmentation", Proc. IEEE Int. Symposium on Industrial Electronics, pp. 1623-1627, Jun. 2007.
  5. K. Hu, G. Y. Tang, D. P. Xiong, and Q. Qiu, "A novel image segmentation algorithm based on hidden Markov random field model and finite mixture model parameter estimation", Proc. Int. Conf. Wavelet Analysis and Pattern Recognition, pp. 1-6, Jul. 2012.
  6. C. Cigla and A. A. Alatan, "Depth assisted object segmentation in multi- view video", Proc. Conf. 3DTV: The True Vision - Capture, Transmission and Display of 3D Video, pp. 185-188, May 2008.
  7. C. D. Mutto, P. Zanuittigh, and G. M. Cortelazzo, "Fusion of geometry and color information for scene segmentation", IEEE Journ. Selected Topics in Signal Processing, vol. 6, no. 5, pp. 505-521, Sept. 2012. https://doi.org/10.1109/JSTSP.2012.2194474
  8. M. Dahan, N. Chen, A. Shamir, and D. C. Or, "Combining color and depth for enhanced image segmentation and retargeting", The Visual Computer, vol. 28, no. 12, pp. 1181-1193, Dec. 2011.
  9. D. Rao, Q. V. Le, T. Phoka, M. Quigley, A. Sudsang, and A. Y. Ng, "Grasping novel objects with depth segmentation", Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, pp. 2578-2584, Taipei, Taiwan, Oct. 2010.
  10. Z. Wu and R. Leahy, "An optimal graph theoretic approach to data clustering", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1101-1113, Nov. 1993. https://doi.org/10.1109/34.244673
  11. J. Shi and J. Malik, "Normalized cuts and image segmentation", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, Aug. 2000. https://doi.org/10.1109/34.868688
  12. H. Wang, N. Ray, and H. Zhang, "Graph-cut optimization of the ratio of functions and its application to image segmentation", Proc. Int. Conf. Image Processing, pp. 749-752, Oct. 2008.
  13. T. H. Le, S.-W. Jung, K.-S. Choi, and S.-J. Ko, "Image segmentation based on modified graph-cut algorithm, Electronic Letters, vol. 46, no. 16, pp. 1121-1123, Aug. 2010. https://doi.org/10.1049/el.2010.1692
  14. Y. Li, Y. Du, B. Liou, H. Li, Q. Zhang, and L. Yaqian, "Image segmentation method based on improved graph cut algorithm", Proc. IEEE Int. Conf. Computer Science and Automation Engineering, vol. 2, pp. 335-340, May 2012.
  15. E. Sharon, A. Brandt, and R. Basri, "Fast multiscale image segmentation", Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, vol. 1, no. 2, pp. 70-77, Jun. 2000.
  16. S. X. Yu, "Segmentation using multiscale cues", Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, vol. 1, no. 27, pp. 247-254, Jul. 2004.
  17. J. Malik, S. Belongie, T. Leung, and J. Shi, "Contour and texture analysis for image segmentation, Int. J. Computer Vision", vol. 43, no. 1, pp. 29-44, Jun. 2001. https://doi.org/10.1023/A:1011126920638