Other Links

Indexed By

    •

Volume 7 Issue 2 - July 2016

  • 1. Visual analytics for semantic based image retrieval (sbir): semantic tool

    Authors : Aravindhan R, Dr.shanmugalakshmi R

    Pages : 300-312

    DOI : http://dx.doi.org/10.21172/1.72.548

    Keywords : Image RetrievalOntologyBio Medical ImageSemantic ToolSemantic gap

    Abstract :

    Semantic-based image retrieval (SBIR) is a retrieval technique based on the intuition of user. However, implementing a meticulous strategy without incurring a semantic gap (disparity between the retrieved images and the user desired images) is a challenging task. The semantic gap is not trivial, when it comes to sensitive medical diagnostic images. Also, with rapid digitization of medical diagnostic images, statistics reveal that data from US health care system alone reached 150 Exabyte’s and so with the presumption that this diagnostic medical data will shoot up, memory requirements and computational expenses should be reduced substantially. Furthermore, as only a region of image will be most relevant (ROI-Region of Interest) while retrieving diagnostic medical data, the feature dimensionality is reduced and thereby the speed of the retrieval process is increased. As, most SBIR algorithms do not intuitively explain why the retrieved images are considered relevant to the user query, there is a chance that the user may miss out relevant images which may be outliers. Semantic technologies like ontology offers auspicious approach to image retrieval as it tries to map the low level image features to high level ontology concepts. So a tool called Visual Analytics Tool for Semantic Retrieval (VATSR) is proposed which allows user to visually interact and refine the query and/or search results. Moreover, in this paper, a hierarchical classifier is proposed which classifies at different levels with different set of features, which ensures that a relevant image missed out in one classifier may be retrieved in another classifier. Along with this, a boosting algorithm is use to improve the precision of the search results.

    Citing this Journal Article :

    Aravindhan R, Dr.shanmugalakshmi R, "Visual analytics for semantic based image retrieval (sbir): semantic tool ", Volume 7 Issue 2 - July 2016, 300-312

    Click here to Submit Copyright Takedown Notice for this article.

    View Paper