Sketch based image retrieval using grid approach on large scale database

Several approaches are found in study for image retrieval from the database. A sketch based system is an efficient method which does not require the user to have a high skill to draw the query sketch. Sketch-to-image matching system on a large-scale image database should ensure that the system alway...

Full description

Saved in:
Bibliographic Details
Main Authors: Rajput, G.G, Prashantha
Format: Conference Proceeding
Language:English
Subjects:
features
non-overlapping grid
overlapping grid
similarity measure
Sketc-Based image retrieval
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Several approaches are found in study for image retrieval from the database. A sketch based system is an efficient method which does not require the user to have a high skill to draw the query sketch. Sketch-to-image matching system on a large-scale image database should ensure that the system always tries to find correct matches for a given sketch query. In this paper, we present an efficient method for image retrieval from large database using sketch as a query image. Features are extracted from the image by placing a non-overlapping grid and overlapping grid over the image, respectively. Using a weighted similarity approach, the most similar images to the query are then retrieved from the image dataset. For performing experiments images of flickr15k dataset are used. The proposed method shows excellent retrieval performance in comparison to methods available in the literature.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2020.01.089