ABSTRACT
Image annotation plays an important role in image retrieval and management. However, the results of the state-of-the-art image annotation methods are often unsatisfactory. Therefore, it is necessary to refine the imprecise annotations obtained by existing annotation methods. In this paper, a novel approach to automatically refine the original annotations of images is proposed. On the one hand, for Web images, textual information, e.g. file name and surrounding text, is used to retrieve a set of candidate annotations. On the other hand, for non-Web images that are lack of textual information, a relevance model-based algorithm using visual information is used to decide the candidate annotations. Then, candidate annotations are re-ranked and only the top ones are reserved as the final annotations. To re-rank the annotations, an algorithm using Random Walk with Restarts (RWR) is proposed to leverage both the corpus information and the original confidence information of the annotations. Experimental results on both non-Web images of Corel dataset and Web images of photo forum sites demonstrate the effectiveness of the proposed method.
- http://images.google.comGoogle Scholar
- http://www.photosig.comGoogle Scholar
- Blei, D. M. and Jordan, M. I. Modeling annotated data. In Proc. SIGIR, Toronto, July. 2003. Google ScholarDigital Library
- Chang, E., Kingshy, G., Sychay, G., and Wu, G. CBSA: content-based soft annotation for multimodal image retrieval using Bayes point machines. IEEE Trans. on CSVT, 13(1):26--38, Jan. 2003. Google ScholarDigital Library
- Cusano, C., Ciocca, G., and Schettini, R. Image annotation using SVM. In Proc. Of Internet imaging IV, Vol. SPIE, 2004Google Scholar
- Duygulu, P. and Barnard, K. Object recognition as machine translation: learning a lexicon for a fixed image vocabulary. In Proc. of ECCV, 2002. Google ScholarDigital Library
- Feng, S. L., Manmatha, R., and Lavrenko, V. Multiple bernoulli relevance models for image and video annotation. In Proc. of CVPR, Washington, DC, June, 2004. Google ScholarDigital Library
- Jeon, J., Lavrenko, V., and Manmatha, R. Automatic Image Annotation and Retrieval Using Cross-media Relevance Models. In Proc. of SIGIR, Toronto, July 2003. Google ScholarDigital Library
- Jin, Y., Khan, L., Wang, L., and Awad, M. Image Annotations By Combining Multiple Evidence & Wordnet. Proc. of ACM Multimedia, Singapore, 2005 Google ScholarDigital Library
- Lavrenko, V. and Croft, W. Relevance-based language models. Proc. of SIGIR, 2001. Google ScholarDigital Library
- Lavrenko, V., Manmatha, R., and Jeon, J. A Model for Learning the Semantics of Pictures. In Proc. NIPS, 2003.Google Scholar
- Li, J. and Wang, J. Z. Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. on PAMI, 25(10), Oct. 2003. Google ScholarDigital Library
- Miller, G. A. WordNet: A lexical database for English. Communication of ACM, 38, 11 (Nov. 1995), 39--41. Google ScholarDigital Library
- Mori, Y., Takahashi, H., and Oka, R. Image-to-word transformation based on dividing and vector quantizing images with words. In MISRM, 1999.Google Scholar
- Page, L., Brin, S., Motwani, R., and Winograd, T. The Pagerank Citation Ranking: Bringing Order to the web. technical report, Stanford University, Stanford, CA, 1998.Google Scholar
- Zhang, L., Chen, L., Jing, F., Deng, K. F., and Ma, W.Y. EnjoyPhoto-A Vertical Image Search Engine for Enjoying High-Quality Photos. In ACM multimedia 2006. Google ScholarDigital Library
Index Terms
- Image annotation refinement using random walk with restarts
Recommendations
A novel graph-based image annotation refinement algorithm
FSKD'09: Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5A novel graph-based approach to automatically refine image annotation is presented in this paper. Given an unannotated image, a set of candidate annotations is extracted by the existing image annotation method. Then, each candidate annotation is ...
A Novel Graph-Based Image Annotation Refinement Algorithm
FSKD '09: Proceedings of the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 05A novel graph-based approach to automatically refine image annotation is presented in this paper. Given an unannotated image, a set of candidate annotations is extracted by the existing image annotation method. Then, each candidate annotation is ...
An efficient refinement algorithm for multi-label image annotation with correlation model
With the explosively rising popularity of photography devices, collections of personal digital images are growing rapidly both in number and size. There is an increasing desire to effectively index and search these images to meet user requirements. The ...
Comments