LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH

S. Albertini, I. Gallo, M. Vanetti, A. Nodari

Abstract

In this study we propose a new strategy to perform an object segmentation using a multi neural network approach. We started extending our previously presented object detection method applying a new segment based classification strategy. The result obtained is a segmentation map post processed by a phase that exploits the GrabCut algorithm to obtain a fairly precise and sharp edges of the object of interest in a full automatic way. We tested the new strategy on a clothing commercial dataset obtaining a substantial improvement on the quality of the segmentation results compared with our previous method. The segment classification approach we propose achieves the same improvement on a subset of the Pascal VOC 2011 dataset which is a recent standard segmentation dataset, obtaining a result which is inline with the state of the art.

References

  1. Bengio, Y. (2009). Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2(1):1- 127.
  2. Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2011). The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results. http://www.pascalnetwork.org/challenges/VOC/voc2011/workshop/.
  3. Gallo, I. and Nodari, A. (2011). Learning object detection using multiple neural netwoks. In VISAP 2011. INSTICC Press.
  4. Hartigan, J. and Wang, M. (1979). A k-means clustering algorithm. Applied Statistics, 28:100-108.
  5. Hernandez, A., Reyes, M., Escalera, S., and Radeva, P. (2010). Spatio-temporal grabcut human segmentation for face and pose recovery. In AMFG10, pages 33-40.
  6. Hu, M.-K. (1962). Visual pattern recognition by moment invariants. Information Theory, IRE Transactions on, 8(2):179-187.
  7. Jaccard, P. (1912). The distribution of the flora in the alpine zone. New Phytologist, 11(2):37-50.
  8. Li, F., Carreira, J., and Sminchisescu, C. (2010). Object recognition as ranking holistic figure-ground hypotheses. In CVPR, pages 1712-1719. IEEE.
  9. Riesenhuber, M. and Poggio, T. (1999). Hierarchical models of object recognition in cortex. Nature Neuroscience, 2(11):1019-1025.
  10. Rother, C., Kolmogorov, V., and Blake, A. (2004). Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 23:309-314.
  11. Serre, T., Wolf, L., and Poggio, T. (2005). Object recognition with features inspired by visual cortex. In Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR 7805, pages 994-1000, Washington, DC, USA. IEEE Computer Society.
  12. Sharkey, A. J. (1999). Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems, chapter Multi-Net Systems. Springer.
  13. Wang, F., Yu, S., and Yang, J. (2010). Robust and efficient fragments-based tracking using mean shift. AEU - International Journal of Electronics and Communications, 64(7):614 - 623.
Download


Paper Citation


in Harvard Style

Albertini S., Gallo I., Vanetti M. and Nodari A. (2012). LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 521-530. DOI: 10.5220/0003833705210530


in Bibtex Style

@conference{visapp12,
author={S. Albertini and I. Gallo and M. Vanetti and A. Nodari},
title={LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={521-530},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003833705210530},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH
SN - 978-989-8565-03-7
AU - Albertini S.
AU - Gallo I.
AU - Vanetti M.
AU - Nodari A.
PY - 2012
SP - 521
EP - 530
DO - 10.5220/0003833705210530