Abstract | ||
---|---|---|
Immense increase in digital images demands an efficient and accurate image retrieval system. In text based image retrieval, images are annotated with keywords based on human perception. On the other hand, keywords are included in a user query based on his/her requirements. Query keywords are matched with the annotated keywords for image retrieval. This process has been extended with ontology to resolve semantic heterogeneities. However, crisp annotation and querying processes could not produce the desired results because both involve human perception. To overcome this problem, we have proposed a fuzzy ontology based retrieval system that makes use of ontology for improving retrieval performance. For modeling the semantic description of image, it is divided into regions and regions are classified into concepts. The concepts are combined into categories. The concepts, categories and images are linked among themselves with fuzzy values in ontology. Retrieved results are ranked based on the relevancy between the keywords of a query and images. Experimental results show that the proposed system performs comparatively better than the existing systems in terms of retrieval performance. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-44215-0_9 | Lecture Notes in Computer Science |
Keywords | DocType | Volume |
Image retrieval,Text based image retrieval,Fuzzy ontology | Conference | 9847 |
ISSN | Citations | PageRank |
0302-9743 | 2 | 0.49 |
References | Authors | |
14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Madiha Liaqat | 1 | 3 | 0.84 |
Sharifullah Khan | 2 | 40 | 11.64 |
Muhammad Majid | 3 | 3 | 0.84 |