Author : Yogini B. Bhadane 1
Date of Publication :17th August 2017
Abstract: The passing keywords to images is of huge attention as it allows one to retrieve, directory and recognize big collections of image data. Various systems have been designed for image annotation that gives a realistic presentation on consistent datasets. Here, studied multi-label image annotation with dictionary learning methods. In multi-label image annotation, new (SLED) semantic label embedding dictionary demonstration used, which is solved the problem of annotation, under the softly supervised situation. Several of the consumers have the skill to produce and store images. Peoples did not spend their time for organizing and grouping their particular (private) image collections. So it's difficult for peoples to finding particular (exact) images. Image annotation contains a number of methods that goals to find the link between words and images. The multi-label image annotation system divided into two branches, i.e. the training branch and the testing branch. In training branch, datasets are divided into exclusive groups. In it, Fisher discrimination law used for the train the label of that image. Then co-occurrence labels would offer the context data of that image. This context data adds into the novel dictionary table. In the testing branch, use label propagation and reconstruction coefficient to get the score of each image labe
Reference :
-
- C. Wang, S. Yan, L. Zhang, and H.-J. Zhang, “Multi-label sparse coding for automatic image annotation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 1643-1650, Jun. 2009.
- G. Carneiro, A. B. Chan, P. J. Moreno and N. Vasconcelos, “Supervised learning of semantic classes for image annotation and retrieval,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 3, pp. 394-410, Mar. 2007.
- L. Wu, R. Jin, and A. K. Jain, "Tag completion for image retrieval," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 3, pp. 716-727, Mar. 2013.
- A. Makadia, V. Pavlovic and S. Kumar, “A new baseline for image annotation,” in Proc. ECCV, pp. 316- 329, 2008.
- S. Lazebnik and M. Raginsky, “Supervised learning of quantizer codebooks by information loss minimization,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 7, pp. 1294–1309, Jul. 2009.
- V. Lavrenko, R. Manmatha, and J. Jeon, "A model for learning the semantics of pictures," in Proc. NIPS, pp. 553-560, 2003.
- X. Chen, X.-T. Yuan, Q. Chen, S. Yan and T.-S. Chua, “Multi-label visual classification with label exclusive context,” in Proc. ICCV, pp. 834-841, Nov. 2011.
- L. Wu, S. C. H. Hoi, and N. Yu, "Semanticspreserving bag-of-words models and applications," IEEE Trans. Image Process., vol. 19, no. 7, pp. 1908-1920, Jul. 2010
- M. Aharon, M. Elad, and A. Bruckstein, "KSVD: An algorithm for designing overcomplete dictionaries for sparse representation," IEEE Trans. Signal Process., vol. 54, no. 11, pp. 4311-4322, Nov. 2006
- X. Cao, H. Zhang, X. Guo, Si Liu and Dan Meng, “SLED: Semantic label embedding dictionary representation for multi-label image annotation,” IEEE Trans. Image Process., vol. 24, no. 9, pp. 2746-2759, Sep. 2015