INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
The performance of the CBIR system can be improved by reducing the semantic gap between visual features and human semantics. Relevance Feedback (RF) approach refines the retrieval process as per users feedback. A variety of Relevance Feedback (RF) methods have been widely used to reduce the semantic gap. Related works on CBIR are also investigated and it was observed that existing Relevance Feedback techniques face the challenges of number of iterations and the execution time. To improve the retrieval efficiency of the existing system, the proposed RF approach makes use of binary classifier and a feature selection technique to reduce the dimensionality of the image feature space. In each RF iteration, the positive and negative examples provided by the user will be used to determine a small number of the most important features for the classification. After the feature selection has been performed, a binary classifier will be trained to distinguish between relevant and irrelevant images according to the preferences of the user for the given query. The trained classifier will be used later to provide an updated ranking of the database images represented in the space of the selected features.
"Efficient Relevance Feedback for CBIR System", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.1, Issue 3, page no.95 - 99, March-2016, Available :http://www.ijsdr.org/papers/IJSDR1603018.pdf
Downloads:
000337070
Publication Details:
Published Paper ID: IJSDR1603018
Registration ID:160062
Published In: Volume 1 Issue 3, March-2016
DOI (Digital Object Identifier):
Page No: 95 - 99
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn