Automatic Discovery Approach of Digital Image Topic

Abstract:

A topic discovery approach of the image has been proposed. First, the training images are segmented into some blocks. After clustering blocks, we obtained class set generated by cluster centers, and extracted all nouns from text annotation of each training image to obtain a keyword set. Secondly, the un-label testing image is also segmented into some blocks as same as training images, we calculated the correlation between the block and keyword, and the keyword set for each block may be obtained. Finally, the number of the same keyword appearing in the each block is calculated, we let the keywords with maximum to appear times be as the topics of the image. The experimental results confirm that proposed approach for the image is effectiveness and has good performance.

• Periodical: Applied Mechanics and Materials (Volume 610)
• Pages: 449-453
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.610.449
• Online since: August 2014
• Authors: Cong Jin, Shu Wei Jin*
• Keywords:

  Found Keywords

  Digital Image

  , Clustering, KNN, Segmentation, Topic Discovery

References

[1] Z. Chen, J. Hou, D.S. Zhang, X. Qin: An annotation rule extraction algorithm for image retrieval, Pattern Recogn. Lett., Vol. 33(2012), pp.1257-1268.

DOI: 10.1016/j.patrec.2012.03.008

[2] S. Zhu,Y. Liu: Semi-supervised learning model based efficient image annotation. IEEE Signal Process. Lett. Vol. 16(2009), pp.989-992.

DOI: 10.1109/lsp.2009.2028114

[3] S.H. Zhu, J.J. Hu, B.Y. Wang, S.H. Shen: Image annotation using high order statistics in non-Euclidean spaces. J. Vis. Commun. Image R., Vol. 24(2013), pp.1342-1348.

DOI: 10.1016/j.jvcir.2013.09.004

[4] A. Said, A. Drukarev: Simplified segmentation for compound image compression. International Conference on Image Processing, Vol. 1(1999), pp.229-233.

DOI: 10.1109/icip.1999.821603

[5] Goldberger J, Gordon S, Greenspan H.: Unsupervised image-set clustering using an information theoretic framework. IEEE Trans. Image Process., Vol. 15(2006), pp.449-458.

DOI: 10.1109/tip.2005.860593