Research Article
Towards Perception Based Image Retrieval
@INPROCEEDINGS{10.1007/978-3-642-27317-9_29, author={B. Imran and M. Beg}, title={Towards Perception Based Image Retrieval}, proceedings={Advances in Computer Science and Information Technology. Computer Science and Information Technology. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part III}, proceedings_a={CCSIT PART III}, year={2012}, month={11}, keywords={Extended fuzzy logic f-image retrieval f-principle perception based image retrieval f-geometry}, doi={10.1007/978-3-642-27317-9_29} }- B. Imran
M. Beg
Year: 2012
Towards Perception Based Image Retrieval
CCSIT PART III
Springer
DOI: 10.1007/978-3-642-27317-9_29
Abstract
To deal with the rising need of perception based image retrieval, we present a novel approach of fuzzy image retrieval. Indeed, with an abrupt increase in crimes, the whole world is looking forward for an intelligent image retrieval system, which retrieves facial features of criminals as input queries. The present work is focused towards retrieving fuzzy images, with features in perceptions as inputs. We begin with retrieving fuzzy geometric shapes by describing its features in natural language propositions as query. Zadeh proposed computing with words (CW) which deals with perceptions, wherein the natural language is a major source of perceptions. That is, the perception based information is the inputs for image retrieval. We devise our image retrieval system with query processing, search module and Lucene. Moreover, the ranking of retrieving fuzzy objects is based on the highest value of query relevance vector. We found that the fuzzy geometric shapes are retrieved correctly based on the perception based query.