The Community for Technology Leaders
Green Image
Issue No. 11 - November (2008 vol. 30)
ISSN: 0162-8828
pp: 1919-1932
Xin-Jing Wang , Microsoft Research Asia, Beijing
Lei Zhang , Microsoft Research Asia, Beijing
Xirong Li , University of Amsterdam, Amsterdam
Wei-Ying Ma , Microsoft Research Asia, Beijing
In this paper, we propose a novel attempt of model-free image annotation which annotates images by mining their search results. It contains three steps: 1) the search process to discover visually and semantically similar search results; 2) the mining process to identify salient terms from textual descriptions of the search results; and 3) the annotation rejection process to filter out noisy terms yielded by step 2). To ensure real time annotation, two key techniques are leveraged - one is to map the high dimensional image visual features into hash codes, the other is to implement it as a distributed system, of which the search and mining processes are provided as Web services. As a typical result, the entire process finishes in less than 1 second. Our proposed approach enables annotating with unlimited vocabulary, and is highly scalable and robust to outliers. Experimental results on both real web images and a bench mark image dataset show the effectiveness and efficiency of the proposed algorithm.
Computer vision, Applications, Pattern Recognition, Computing Methodologies, Retrieval models, Clustering, Information Search and Retrieval, Information Storage and Retrieval, Information Technology a

X. Wang, X. Li, W. Ma and L. Zhang, "Annotating Images by Mining Image Search Results," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 1919-1932, 2008.
79 ms
(Ver 3.3 (11022016))