A study of Impact of Integration Structural Context in Multimedia Retrieval: Application on Image Media

The expansion in volume of information organized according to a structure in multiple applications introduces a new equivocal in multimedia retrieval in semi-structured documents. We study in this paper the impact of introduce a structural context on multimedia retrieval in XML document thus we present a indexing model which combines textual and structural information. We propose a geometric method who use implicitly of textual and structural context of XML elements and we are particularly interested by improve the effectiveness of various structural factors for multimedia retrieval. Using a geometric metric, we can represent structural information in XML document with a vector for each element. Experimental evaluation is carried out using the INEX Ad Hoc Task 2007, ImageCLEF Wikipedia Retrieval Task 2010 and ImageCLEF Plant Task 2014 in the framework of our participation in CLEF 2014 campaign. The results show that integration of structural context significantly improves compared results of using a single textual context. Our proposed method perform as compared to other systems evaluated on two coolection INEX 2007 and ImageCLEF 2010.