Object Annotation Based on Middle Semantic Manifold

Wen Gang Feng; Xipin Zhou

doi:10.4028/www.scientific.net/AMM.220-223.2204

Paper Titles

Time Scale Variation of the Yellow River Ice in the Inner Mongolia Section Using Wavelet Analysis
p.2184

Synergetic Multi-Semantic Multi-Instance Learning for Scene Recognition
p.2188

Dual-Butterfly Parallel Access Constant Geometry Pipeline Radix-2 FNT Algorithm
p.2192

Image Registration Based on Mutual Information and Harris Corner Points
p.2199

Object Annotation Based on Middle Semantic Manifold
p.2204

Motion Compensation Based on Keystone Transform and Wigner-Hough Transform
p.2208

Object Remarkable Features Extraction Strategy Based on Imagery Conceptual Network
p.2213

BOU-Based Cycle Determination for Different Kinds of Mechanical Vibration Signals
p.2217

An Effective Method for Combining Kernels with Class Separability
p.2224

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 220-223Object Annotation Based on Middle Semantic...

Object Annotation Based on Middle Semantic Manifold

Abstract:

A novel bionic, middle semantic object annotation framework is presented in this paper. Moreover, we build the model based on the perception as defined by the human visual system. At first, the super-pixel is used to represent the images, and conditional random field could label each of the super-pixels, which means annotating the different classes of objects. In next step, on the basis of the previous result, image pyramid is used to represent the image, and get the sub-region of some objects of the same class. After extracting descriptor to represent the patches, all the patches are projected to a manifold, which could annotate the different views of objects from the same class. Experiments show that the bionic, middle semantic object annotation framework could obtain superior results with respect to accuracy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 220-223)

Pages:

2204-2207

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.220-223.2204

Citation:

Cite this paper

Online since:

November 2012

Authors:

Wen Gang Feng, Xipin Zhou

Keywords:

Conditional Random Field, Object Annotation, Pyramid Presentation, Semantic Manifold

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] R. Forgus. Visual Object Category Recognition. PhD thesis, Oxford University, 2005.

Google Scholar

[2] P. Felzenszwalb and D. Huttenlocher. Pictorial structures for object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2000, 2066-2073.

DOI: 10.1109/cvpr.2000.854739

Google Scholar

[3] L. Fei-Fei, R. Forgus and P. Perona. A Baysian approach to unsupervised one-shot learning of object categories. In Proceedings of the 9th International Conference on Computer Vision, 2003, 1134-1141.

DOI: 10.1109/iccv.2003.1238476

Google Scholar

[4] A. Vailaya, A. Figueiredo, A. Jain, H. Zhang. Image classification for content-based indexing. IEEE Transactions on Image Processing, 2001, 10: 117-129.

DOI: 10.1109/83.892448

Google Scholar

[5] M. Szummer, R. W. Picard. Indoor-outdoor image classification. In: IEEE International Workshop on Content-based Access of Image and Video Databases, in conjunction with ICCV'98, Bombay, India, 1998, 42-50.

DOI: 10.1109/caivd.1998.646032

Google Scholar

[6] J. Vogel, B. Schiele. Natural scene retrieval based on a semantic modeling step. In: International Conference on Image and Video Retrieval , LNCS, Dublin, Ireland, 2004, 3115: 207-215.

DOI: 10.1007/978-3-540-27814-6_27

Google Scholar

[7] K. Barnard. Matching Words and Pictures. J. Machine Learning Research, 3: 1107-1135, 2003.

Google Scholar

[8] D. Blei and M.I. Jordan, Modeling Annotated Data, Proc. 26th Ann. Int'l ACM SIGIR Conf. Research and Development in Information Retrieval, 127-134, 2003.

DOI: 10.1145/860435.860460

Google Scholar