Narrowing the semantic gap - improved text-based web document retrieval using visual features Export

@article{citeulike:202057, abstract = {We present the results of our work that seek to negotiate the gap between low-level features and high-level concepts in the domain of web document retrieval. This work concerns a technique, called the latent semantic indexing (LSI), which has been used for textual information retrieval for many years. In this environment, LSI determines clusters of co-occurring keywords so that a query which uses a particular keyword can then retrieve documents perhaps not containing this keyword, but containing other keywords from the same cluster. In this paper, we examine the use of this technique for content-based web document retrieval, using both keywords and image features to represent the documents. Two different approaches to image feature representation, namely, color histograms and color anglograms, are adopted and evaluated. Experimental results show that LSI, together with both textual and visual features, is able to extract the underlying semantic structure of web documents, thus helping to improve the retrieval performance significantly, even when querying is done using only keywords.}, author = {Zhao, Rong and Grosky, W. I.}, citeulike-article-id = {202057}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TMM.2002.1017733}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1017733}, day = {07}, doi = {10.1109/TMM.2002.1017733}, journal = {Multimedia, IEEE Transactions on}, keywords = {image-search, information-retrieval, mitchell-group, text-retrieval}, month = {August}, number = {2}, pages = {189--200}, posted-at = {2007-11-04 22:14:22}, priority = {2}, title = {Narrowing the semantic gap - improved text-based web document retrieval using visual features}, url = {http://dx.doi.org/10.1109/TMM.2002.1017733}, volume = {4}, year = {2002} }

TY - JOUR ID - citeulike:202057 L3 - citeulike-article-id:202057 N2 - We present the results of our work that seek to negotiate the gap between low-level features and high-level concepts in the domain of web document retrieval. This work concerns a technique, called the latent semantic indexing (LSI), which has been used for textual information retrieval for many years. In this environment, LSI determines clusters of co-occurring keywords so that a query which uses a particular keyword can then retrieve documents perhaps not containing this keyword, but containing other keywords from the same cluster. In this paper, we examine the use of this technique for content-based web document retrieval, using both keywords and image features to represent the documents. Two different approaches to image feature representation, namely, color histograms and color anglograms, are adopted and evaluated. Experimental results show that LSI, together with both textual and visual features, is able to extract the underlying semantic structure of web documents, thus helping to improve the retrieval performance significantly, even when querying is done using only keywords. IS - 2 JF - Multimedia, IEEE Transactions on EP - 200 TI - Narrowing the semantic gap - improved text-based web document retrieval using visual features VL - 4 SP - 189 KW - image-search KW - information-retrieval KW - mitchell-group KW - text-retrieval AU - Zhao, Rong AU - Grosky, WI PY - 2002/08/07/ UR - http://dx.doi.org/10.1109/TMM.2002.1017733 ER -