ABSTRACT
Image annotation has been an active research topic in recent years due to its potentially large impact on both image understanding and Web image search. In this paper, we target at solving the automatic image annotation problem in a novel search and mining framework. Given an uncaptioned image, first in the search stage, we perform content-based image retrieval (CBIR) facilitated by high-dimensional indexing to find a set of visually similar images from a large-scale image database. The database consists of images crawled from the World Wide Web with rich annotations, e.g. titles and surrounding text. Then in the mining stage, a search result clustering technique is utilized to find most representative keywords from the annotations of the retrieved image subset. These keywords, after salience ranking, are finally used to annotate the uncaptioned image. Based on search technologies, this framework does not impose an explicit training stage, but efficiently leverages large-scale and well-annotated images, and is potentially capable of dealing with unlimited vocabulary. Based on 2.4 million real Web images, comprehensive evaluation of image annotation on Corel and U. Washington image databases show the effectiveness and efficiency of the proposed approach.
- K. Barnard, P. Duygulu, D. Forsyth, N. Freitas, D. Blei, and M. Jordan. Matching words and pictures. JMLR, 2003.]] Google ScholarDigital Library
- G. Carneiro and N. Vasconcelos. A Database Centric View of Semantic Image Annotation and Retrieval. SIGIR, 2005.]] Google ScholarDigital Library
- P. Duygulu, K. Barnard, N. Freitas and D. Forsyth. Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary. ECCV, 2002.]] Google ScholarDigital Library
- J. Jeon, V. Lavrenko and R. Manmatha. Automatic Image Annotation and Retrieval using Cross-Media Relevance Models. SIGIR, 2003.]] Google ScholarDigital Library
- X. Wang, L. Zhang, F. Jing and W. Ma. AnnoSearch: Image Auto-Annotation by Search. CVPR, 2006.]] Google ScholarDigital Library
- C. Yang, M. Dong and F. Fotouhi. Region Based Image Annotation Through Multiple-Instance Learning. ACM MM, 2004.]] Google ScholarDigital Library
- H. Zeng, Q. He, Z. Chen and W. Ma. Learning to cluster web search results. SIGIR, 2004.]] Google ScholarDigital Library
- L. Zhang, Y. Hu, M. Li, W. Ma and H. Zhang. Efficient Propagation for Face Annotation in Family Albums. ACM MM, 2002.]]Google Scholar
- H. Ferhatosmanoglu, E. Tuncel, D. Agrawal and A. Abbadi. Vector Approximation Based Indexing for Non-uniform High Dimensional Data Sets. CIKM, 2000.]] Google ScholarDigital Library
- A. Gionis, P. Indyk, and R. Motwani. Similarity search in high dimensions via hashing. VLDB, 1999.]] Google ScholarDigital Library
- H. Ferhatosmanoglu, E. Tuncel, D. Agrawal and A. Abbadi. Approximate neighbor searching in multimedia databases. ICDE, 2001.]] Google ScholarDigital Library
- S. E. Robertson, S. Walker, S. Jones, M. M. Hancock- Beaulieu and M. Gatford. Okapi at TREC-3. TREC-3, 1995.]]Google Scholar
Index Terms
- Image annotation by large-scale content-based image retrieval
Recommendations
Scalable search-based image annotation of personal images
MIR '06: Proceedings of the 8th ACM international workshop on Multimedia information retrievalWith the prevalence of digital cameras, more and more people have considerable digital images on their personal devices. As a result, there are increasing needs to effectively search these personal images. Automatic image annotation may serve the goal, ...
Review: Automatic Image Annotation for Semantic Image Retrieval
Image and Signal ProcessingAbstractNowadays, the number of digital data sets grows exponentially. Hence, the need to conceive efficient and powerful image indexation and retrieval systems grows as well. Automatic image annotation was adopted by several research as the emerging ...
Automatic Image Annotation Using Global and Local Features
SMAP '11: Proceedings of the 2011 Sixth International Workshop on Semantic Media Adaptation and PersonalizationAutomatic image annotation methods require a quality training image dataset, from which annotations for target images are obtained. At present, the main problem with these methods is their low effectiveness and scalability if a large-scale training ...
Comments