Image Labeling by Integrating Global Information by 7 Patches and Local Information

Takuto Omiya, Takahiro Ishida, Kazuhiro Hotta

Abstract

We propose an image labeling method by integrating the probabilities of local and global information. Many conventional methods put label to each pixel or region by using the features extracted from local regions and local contextual relationships between neighboring regions. However, labeling results tend to depend on a local viewpoint. To overcome this problem, we propose the image labeling method using not only local information but also global information. The probability by global information is estimated by KNearest Neighbor. In the experiments using the MSRC21 dataset, labeling accuracy is much improved by using global information.

References

  1. Shotton, J., Winn, J., Rother, C., Criminisi, A., (2006). 'Textonboost: joint appearance, shape and context modeling for multi-class object recognition and segmentation.78 European Conference on Computer Vision, pp. 1-15.
  2. Tu, Z., (2008). 'Auto-context and its application to highlevel vision tasks.78 Computer Vision and Pattern Recognition, pp. 1-8.
  3. Omiya, T., Hotta, K., (2013). 'Image labeling using integration of local and global features.78 International Conference on Pattern Recognition Applications and Methods, pp. 613-618.
  4. Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C, (2004). 'Visual categorization with bags of keypoints.78 ECCV Workshop on statistical learning in computer vision, pp. 1-22.
  5. Fix, E., Hodges, J., (1951). 'Discriminatory analysis nonparametric discrimination: Consistency properties.78 Technique Report No. 4, U.S. Air Force School of Aviation Medicine, Randolf Field Texas.
  6. Achanta, R., Shaji A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S., (2012). 'SLIC Superpixels Compared to State-of-the-art Superpixel Methods.78 IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 11 pp. 2274-2282.
  7. Arandjelovic, R., Zisserman, A., (2012). 'Three things everyone should know to improve object retrieval.78 Computer Vision and Pattern Recognition. pp. 2911- 2918.
  8. Ojala, T., Pietikainen, M., Maenpaa, T., (2002). 'Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.78 IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, pp. 971-987.
  9. Vedaldi, A., Zisserman, A., (2012) 'Efficient additive kernels via explicit feature maps.78 IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 3, pp. 480-492.
  10. Chang, C.-C., Lin, C.-J., (2001). LIBSVM: a library for support vector machines. Available at: http://www.csie.ntu.edu.tw/cjlin/libsvm/ (Accessed: 11 November 2014).
  11. Fei-Fei, L., Perona, P., (2005). 'A Bayesian hierarchical model for learning natural scene categories.78 Computer Vision and Pattern Recognition, Vol. 2, pp. 524-531.
  12. Gould, S., (2012). 'Multiclass pixel labeling with nonlocal matching constraints.78 Computer Vision and Pattern Recognition, pp. 2783-2790.
Download


Paper Citation


in Harvard Style

Omiya T., Ishida T. and Hotta K. (2015). Image Labeling by Integrating Global Information by 7 Patches and Local Information . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 536-541. DOI: 10.5220/0005356005360541


in Bibtex Style

@conference{visapp15,
author={Takuto Omiya and Takahiro Ishida and Kazuhiro Hotta},
title={Image Labeling by Integrating Global Information by 7 Patches and Local Information},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={536-541},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005356005360541},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Image Labeling by Integrating Global Information by 7 Patches and Local Information
SN - 978-989-758-090-1
AU - Omiya T.
AU - Ishida T.
AU - Hotta K.
PY - 2015
SP - 536
EP - 541
DO - 10.5220/0005356005360541