A Multi-stage Segmentation based on Inner-class Relation with Discriminative Learning

Haoqi Fan, Yuanshi Zhang, Guoyu Zuo

Abstract

In this paper, we proposed a segmentation approach that not only segment an interest object but also label different semantic parts of the object, where a discriminative model is presented to describe an object in real world images as multiply, disparate and correlative parts. We propose a multi-stage segmentation approach to make inference on the segments of an object. Then we train it under the latent structural SVM learning framework. Then, we showed that our method boost an average increase of about 5% on ETHZ Shape Classes Dataset and 4% on INRIA horses dataset. Finally, extensive experiments of intricate occlusion on INRIA horses dataset show that the approach have a state of the art performance in the condition of occlusion and deformation.

References

  1. Maji, Subhransu, and Jitendra Malik, 2009. Object detection using a max-margin hough transform. In Computer Vision and Pattern Recognition. CVPR 2009. IEEE Conference on, pp. 1038-1045. IEEE.
  2. Li, Zhenguo, Xiao-Ming Wu, and Shih-Fu Chang, 2012. Segmentation using superpixels: a bipartite graph partitioning approach. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 789-796. IEEE.
  3. Hu, Rui, Tinghuai Wang, and John Collomosse, 2011. A bag-of-regions approach to sketch-based image retrieval. In Image Processing (ICIP), 2011 18th IEEE International Conference on. IEEE.
  4. Gould, Stephen, Jim Rodgers, David Cohen, Gal Elidan, and Daphne Koller, 2008. Multi-class segmentation with relative location prior. In International Journal of Computer Vision 80, no. 3: 300-316. Springer.
  5. Sun, Jian, and Marshall F. Tappen. Learning non-local range markov random field for image restoration, 2011. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conf. on, pp. 2745-2752. IEEE.
  6. Yu, Chun-Nam John, and Thorsten Joachims, 2009. Learning structural SVMs with latent variables. In Proceedings of the 26th Annual International Conference on Machine Learning, pp. 1169-1176.
  7. Joachims, Thorsten, Thomas Finley, and Chun-Nam John Yu, 2009. Cutting-plane training of structural SVMs. In Machine Learning 77, no. 1 (2009): 27-59.
  8. Cour, Timothee, Florence Benezit, and Jianbo Shi, 2005. Spectral segmentation with multiscale graph decomposition. In Computer Vision and Pattern Recognition, vol. 2, pp. 1124-1131. IEEE.
  9. Andaló, F. A., P. A. V. Miranda, R. da S. Torres, and A. X. Falcão, 2010. Shape feature extraction and description based on tensor scale. In Pattern Recognition 43, no. 1: 26-36.
  10. Liu, Guang-Hai, Lei Zhang, Ying-Kun Hou, Zuo-Yong Li, and Jing-Yu Yang, 2010. Image retrieval based on multi-texton histogram. In Pattern Recognition 43, no. 7 (2010): 2380-2389.
  11. Ferrari, Vittorio, Frederic Jurie, and Cordelia Schmid, 2010. From images to shape models for object detection. In International Journal of Computer Vision 87, no. 3: 284-303.
  12. Winn, John, Antonio Criminisi, and Thomas Minka, 2005. Object categorization by learned universal visual dictionary. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, vol. 2, pp. 1800-1807. IEEE.
  13. Arbeláez, Pablo, Bharath Hariharan, Chunhui Gu, Saurabh Gupta, Lubomir Bourdev, and Jitendra Malik, 2012. Semantic segmentation using regions and parts. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 3378-3385. IEEE.
  14. Chen, Xi, Arpit Jain, Abhinav Gupta, and Larry S. Davis, 2011. Piecing together the segmentation jigsaw using context. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE.
Download


Paper Citation


in Harvard Style

Fan H., Zhang Y. and Zuo G. (2014). A Multi-stage Segmentation based on Inner-class Relation with Discriminative Learning . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 486-493. DOI: 10.5220/0004717404860493


in Bibtex Style

@conference{visapp14,
author={Haoqi Fan and Yuanshi Zhang and Guoyu Zuo},
title={A Multi-stage Segmentation based on Inner-class Relation with Discriminative Learning },
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={486-493},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004717404860493},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - A Multi-stage Segmentation based on Inner-class Relation with Discriminative Learning
SN - 978-989-758-004-8
AU - Fan H.
AU - Zhang Y.
AU - Zuo G.
PY - 2014
SP - 486
EP - 493
DO - 10.5220/0004717404860493