چکیده:
Several semantic image search schemes have been recently proposed to retrieve
images from the web. However, the query context is regularly ignored in these
techniques and hence, many of the returned images are not adequately relevant.
In this paper, we make use of context to further confine the outcome of the
semantic search engines. For this purpose, we propose a hybrid search engine
which utilizes concept and context for retrieving precise results. In the proposed
model, an ontology is exploited for annotating images and accomplishing search
process in the semantic level. Furthermore, the query of the user is modified
with the concepts available in the ontology. Next, we make use of search context
of the user and augment the query with the information extracted from the user’s
context to additionally eliminate irrelevant results. Experimental results show
that the combination of concept and context is effective in retrieving and
presenting the most relevant results to the user
خلاصه ماشینی:
For this purpose, we propose a hybrid search engine which utilizes concept and context for retrieving precise results.
In the proposed model, an ontology is exploited for annotating images and accomplishing search process in the semantic level.
Keywords: Context, Image Retrieval, Ontology, Semantic Search Introduction The growth of digital cameras and even mobile phones leads to the explosion in the number of images and videos available in the web.
In the text-based search systems, keyword queries are matched with the texts associated to each image such as filename, tag, etc (Yang, Wu, Lee, Lin, Hsu, & Chen, 2008).
We exploit the LSCOM (Naphade, Smith, Tesic, & Chang, 2006) ontology to construct a semantic search engine for image retrieval.
In content-based image retrieval (CBIR) techniques such as (Pentland, Picard, & Sclaroff, 1996), (Gupta & Jain, 1997), (Flickner, Sawhney, Niblack, & Ashley, 1995), and (Smith & Chang, 1996), image searching is accomplished based on features automatically extracted from images.
In addition, the model offers recommendations of search keywords, which are semantically related to the query to assist the users to navigate around the relevant images.
ling, Wang, Yao, Deng, & Zhang (2006) implement a semantic image search engine called IGroup, which clusters search results into different groups and enables users to identify their required group at a glance.
By making the web documents meaningful, the search scheme changes from text-based to concept-based and hence retrieved images become more accurate and many of the irrelevant results vanish.
As a result, the proposed search engine performs well in retrieving images especially for queries that contain contextual data.