Gradient Field Descriptor for Sketch based Retrieval and Localization

Hu, R, Barnard, M and Collomosse, J (2010) Gradient Field Descriptor for Sketch based Retrieval and Localization In: IEEE International Conference on Image Processing, 2010-09 - ?, Hong Kong.

Preview	Text Hu-ICIP-2010.pdf - Accepted version Manuscript Available under License : See the attached licence file. Download (4MB)
Preview	Text (licence) SRI_deposit_agreement.pdf Download (33kB)

Abstract

We present an image retrieval system driven by free-hand sketched queries depicting shape. We introduce Gradient Field HoG (GF-HOG) as a depiction invariant image descriptor, encapsulating local spatial structure in the sketch and facilitating efficient codebook based retrieval. We show improved retrieval accuracy over 3 leading descriptors (Self Similarity, SIFT, HoG) across two datasets (Flickr160, ETHZ extended objects), and explain how GF-HOG can be combined with RANSAC to localize sketched objects within relevant images. We also demonstrate a prototype sketch driven photo montage application based on our system.

Item Type:	Conference or Workshop Item (Conference Paper)
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :	Hu, R, Barnard, M and Collomosse, J
Date :	September 2010
DOI :	10.1109/ICIP.2010.5649331
Contributors :	Contribution Name Email ORCID http://www.loc.gov/loc.terms/relators/PBL IEEE,
Additional Information :	© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Depositing User :	Symplectic Elements
Date Deposited :	31 May 2012 10:32
Last Modified :	06 Jul 2019 05:10
URI:	http://epubs.surrey.ac.uk/id/eprint/605299

Actions (login required)

View Item

Downloads