Research on Constructing a Multi-Label Image Annotation and Retrieval System

Abstract:

In this paper, we design and construct a multi-label image annotation and retrieval system. Various MPEG-7 low level visual features are employed for representing images. For image annotation, a bi-coded genetic algorithm is employed to select optimal feature subsets and corresponding optimal weights for every one vs. one SVM classifiers. After an unlabelled image is segmented into several regions, pre-trained SVMs are used to annotate each region, final label is obtained by merging all the region labels. Based on multi-label of image, image retrieval system provides keyword-based image retrieval service. Multi-labels can provide abundant descriptions for image content in semantic level, high precision annotation algorithm further improve annotation performance.

• Periodical: Applied Mechanics and Materials (Volumes 20-23)
• Pages: 559-564
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.20-23.559
• Online since: January 2010
• Authors: Yu Long Tian, Ran Li, Jian Jiang Lu, Ya Fei Zhang, Zi Ning Lu
• Keywords: Genetic Feature Selection, Image Retrieval, Multi-Label Image Annotation

References

[1] X. Wang, L. Zhang, et al. AnnoSearch: Image auto-annotation by search. In: Proceedings of IEEE Computer Vision and Pattern Recognition, 2006, 1483-1490.

DOI: 10.1109/cvpr.2006.58

[2] T. Mei, Y. Wang, X. S. Hua, et al. Coherent image annotation by learning semantic distance. In: Proceedings of Conference on Computer Vision and Pattern Recognize, 2008: 1-8.

DOI: 10.1109/cvpr.2008.4587386

[3] X. Li, L. Chen, L. Zhang, et al. Image annotation by large-scale content-based image retrieval. In: Proceedings of the 14th Annual ACM international Conference on Multimedia, 2006: 607- 610.

DOI: 10.1145/1180639.1180764

[4] C. H. Wang, L. Zhang, H. J. Zhang. Scalable Markov model-based image annotation. In: Proceedings of Computer Vision and Pattern Recognize, 2008: 113-118.

[5] A. Torralba, R. Fergus, W. T. Freeman. 80 million tiny images: a large dataset for nonparametric object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, November, 2008: 1958-(1970).

DOI: 10.1109/tpami.2008.128

[6] Y. Jing, S. Baluja. PageRank for product image search. In: Proceedings of the WWW 2008. Beijing, 2008: 307-316.

[7] P. Viola, M. Jones. Robust real-time object detection. International Journal of Computer Vision, 2004, (57): 137-154.

DOI: 10.1023/b:visi.0000013087.49260.fb

[8] H. Schneiderman. Learning a restricted Bayesian network for object detection. In: Proceedings of the Conference on Computer Vision and Pattern Recognition. Washington. D, 2004: 639646.

DOI: 10.1109/cvpr.2004.1315224

[9] D. Nister, H. Stewenius. Scalable recognition with a vocabulary tree. In: Proceedings of the Conference on Computer Vision and Pattern Recognition. Volume 2, New York, 2006: 2161- 2168.

DOI: 10.1109/cvpr.2006.264

[10] ISO/IEC JTC1/SC29/WG11/N4062. 2001b. Text of ISO/IEC 15938-3 multimedia content description interface part 3: visual. (2001).

DOI: 10.1109/cmpcon.1991.128828

[11] X. J. Qi, Y. T. Han. Incorporation multiple SVMs for automatic image annotation. Pattern Recognition 2007, 40(4): 728-741.

DOI: 10.1016/j.patcog.2006.04.042

[12] T. M. Hamdani, A. M. Alimi, F. Karray. Distributed genetic algorithm with bi-coded chromosomes and a new evaluation function for features selection. In: Proceedings of the IEEE Congress on Evolutionary Computation, Canada, 2006: 581-588.

DOI: 10.1109/cec.2006.1688362

[13] J.J. Lu, T.Z. Zhao, Y.F. Zhang, Feature selection based-on genetic algorithm for image annotation, Knowledge-Based Systems, 21 (2008) 887-891.

DOI: 10.1016/j.knosys.2008.03.051

[14] J. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.

DOI: 10.1109/34.868688