![](bg6.png)
objects with complex structure, and labeling results
fall into a local minimum. Experimental results
show that global viewpoint overcome these
problems. In addition, label consistency process
provides more smooth labeling results.
The main problem of the proposed method is that
global feature can not handle multiple classes and
represent the position of the objects. This is because
Bag-of-Words method classifies only one object in
an image. For example, when the global features are
extracted from the image contained car and building,
we obtain probability of each class not both classes.
Current global feature can not recognize building
and car simultaneously, and position of each object
is not obtained. We want to introduce the new global
feature which can recognize multiple classes and
position of the objects. That is a subject for future
works.
ACKNOWLEDGEMENTS
This work was supported by KAKENHI No.
24700178.
REFERENCES
Arandjelovic, R. Zisserman, A. (2012). Three things
everyone should know to improve object retrieval.
Proc. Computer Vision and Pattern Recognition, pp.
2911-2918.
Barnard, K. and Forsyth, D. (2001). Learning the
semantics of words and pictures. Proc. International
Conference on Computer Vision. vol. 2, pp. 408-415.
Chang, C. and Lin, J. (2001). LIBSVM: a library for
support vector machines. http://www.csie.ntu.edu.tw/
~cjlin/libsvm
Chapelle, O., Haffner, P. and Vapnik, V. (1999). Support
vector machines for histogram-based image
classification. Neural Networks, vol. 10, pp. 1055-
1064.
Csurka, G., Dance, C., Fan, L., Willamowski, J. and Bray,
C. (2004). Visual categorization with bags of
keypoints. Proc. ECCV Workshop on Statistical
Learning in Computer Vision, pp. 59-74.
Fei-Fei, L. and Perona, P. (2005). A bayesian hierarchical
model for learning natural scene categories. Proc.
Computer Vision and Pattern Recognition, vol. 2, pp.
524-531.
Galleguillos, C., Rabinovich, A. and Belongie, S. (2008).
Object categorization using co-occurrence, location
and appearance. Proc. Computer Vision and Pattern
Recognition, pp. 1-8.
Gould, S., Rodgers, J., Cohen, D., Elidan, G. and Koller,
D. (2008). Multi-class segmentation with relative
location prior. International Journal of Computer
Vision, vol. 80, pp. 300-316.
Ladicky, L., Russell, C., Kohli, P. and Torr, P. (2010).
Graph cut based inference with co-occurrence
statistics. Proc. European Conference on Computer
Vision. pp. 239-253.
Lafferty, J., McCallum, A. and Pereira, F. (2001).
Conditional random fields: probabilistic models for
segmenting and labeling sequence data. Proc.
International Conference on Machine Learning, pp.
282-289.
Lowe, D. (1999). Object recognition from local scale-
ivariant features. Proc. International Conference on
Computer Vision, vol. 2, pp. 1150-1157.
Nowak, E., Jurie, F. and Triggs, B. (2006). Sampling
strategies for bag-of-features image classification.
Proc. European Conference on Computer Vision, pp.
490-503.
Ojala, T. (2002). Multiresolution gray-scale and rotation
invariant texture classification with local binary
patterns. Pattern Analysis and Machine Intelligence,
vol 24, pp. 971-987.
Shotton, J., Winn, J., Rother, C. and Criminisi, A. (2006).
Textonboost: joint appearance, shape and context
modelling for multi-class object recognition and
segmentation. Proc. European Conference on
Computer Vision, pp. 1-15.
Smith, J. and Chang, S. (1996). Tools and techniques for
color image retrieval. Symposium on Electronic
Imaging: Science and Technoloy-Strage and Retrieval
for Image and Video Database IV, pp. 426-437.
Tu, Zhuowen. (2008). Auto-context and its application to
high-level vision tasks.
Proc Computer Vision and
Pattern Recognition, pp. 1-8.
Vapnik, V. (1995). The nature of statistical learning
theory, Springer-verlag New York. New York.
Zhang, J., Marzaklek, M., Lazebnik, S. and Schmid, C.
(2007). Local features and kernels for classification of
texture and object categories: a comprehensive study.
International Journal of Computer Vision, vol. 73, pp.
213-238.
ICPRAM2013-InternationalConferenceonPatternRecognitionApplicationsandMethods
618