Fig 1 - uploaded by Euripides Petrakis
Content may be subject to copyright.
Source publication
Searching for effective methods to retrieve information from the World Wide Web (WWW) has been in the center of many research efforts during the last few years. The relevant technology evolved rapidly thanks to advances in Web systems technology [1] and information retrieval research [15]. Image retrieval on the Web, in particular, is a very import...
Citations
... However, PicASHOW supports only keyword queries and cannot handle image content or example image queries. To solve this problem, [43] and [44] proposed WPicASHOW (weighted PicASHOW), allowing a weighted ranking of cocitation analysis that is based on the combination of textual and visual content to regulate the influence of links between pages. The experiments showed a better performance of WPicASHOW over PicASHOW. ...
Due to the explosive growth of digital images, new efficient and effective methodologies and tools are needed in the image retrieval field. Compared to the content-based image retrieval approach that suffers from the semantic gap, the text-based image retrieval approach has demonstrated its efficiency in retrieving relevant images for a given query. However, this approach suffers from some limitations. For example, query keywords could not match to the textual content of the document or only some images in a document are relevant to the given query. Therefore, a major challenge of the text-based approach is how to improve the image retrieval accuracy without using the image itself, i.e., by using the surrounding information (context) such as the document structure, the links, etc. To achieve this challenge, some works proposed to explore hyperlinks (explicit links) between documents to re-rank images, while more recent works proposed to automatically build implicit links between images and exploit them in the retrieval process. The aim of this paper is thus to compare the exploration of implicit links versus explicit links, either in image ranking or re-ranking. The Image CLEF 2011 collection on Wikipedia shows that not all top-ranked results are interesting to create and analyze linkages between images. In fact, only the aggregate ranking metric makes notice of the fact that linkages improve image retrieval. We also discover that the retrieval strategy—text-based retrieval with no links, implicit link-based re-ranking, or explicit link-based re-ranking—has a significant impact on the efficiency of the query process.
... However, it only supports keyword queries and can not handle image content and example image queries. To solve this problem, Petrakis [43] and Voutsakis et al. [54] proposed WPicASHOW (weighted PicASHOW), allowing a weighted ranking of cocitation analysis that is based on the combination of text and visual content to regulate the influence of links between pages. WPi-cASHOW showed a better performance than PicASHOW. ...
Using hyperlinks to enhance page ranking has been widely studied in the literature. The main motivation is that an hyperlink underlines a page relevance. However, several hyperlinks in the web are used for navigation or marketing purposes. In addition, hyperlinks are created manually, so it is impossible to semantically link all similar pages. In our work, we propose to uncover hidden semantic links and create them automatically between all the collection’s images. For this aim, we propose first to format textual context of images into topic distributions via LDA technique, and then compute semantic similarities to create links. Experiments carried out in the Wikipedia Retrieval Task of ImageClef 2011 showed that the whole textual context of images is useful for uncovering hidden links and consequently enhancing the retrieval accuracy.
... In the PicASHOW system, only textual queries have been supported. For this reason, authors in [20] [21] enhanced this system by incorporating the text and image content of the query and the page. The new system, called WPicASHOW (Weighted PicASHOW), has improved results. ...
In this paper, we are interested in XML multimedia retrieval, the aim of which is to find relevant multimedia objects such as images, audio and video through their context as document structure. In context-based multimedia retrieval, the most common technique is based on the text surrounding the image. However, such textual information can be irrelevant to the image content. Therefore many works are oriented to the use of alternative techniques to extend the image description, such as the use of ontologies, relevance feedback, and user profiles. We studied in our work the use of links between XML elements to improve image retrieval. More precisely, we propose dividing the document into regions through the document structure and image position. Then we weight links between these regions according to their hierarchical positions, in order to distinguish between links that are useful and those that are not useful. We then apply an updated version of the HITS algorithm at the region level, and compute a final image score by combining link scores with initial image scores. Experiments were done on the INEX 2006 and 2007 multimedia tracks, and showed the potential of our method.
