Gradient field descriptor for sketch based retrieval and localization

Author

Hu, Rui ; Barnard, Mark ; Collomosse, John

Author_Institution

Centre for Vision, Speech & Signal Process., Univ. of Surrey, Guildford, UK

fYear

2010

fDate

26-29 Sept. 2010

Firstpage

1025

Lastpage

1028

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.

Keywords

gradient methods; image retrieval; random processes; GF-HOG; RANSAC; depiction invariant image descriptor; free-hand sketched query; gradient field HoG; gradient field descriptor; image retrieval system; retrieval accuracy; sketch based retrieval; sketched objects; spatial structure; Histograms; Image edge detection; Image retrieval; Pixel; Shape; Visualization; Bag-of-visual-words; HoG; RANSAC; Sketch based Image Retrieval;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2010 17th IEEE International Conference on

Conference_Location

Hong Kong

ISSN

1522-4880

Print_ISBN

978-1-4244-7992-4

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2010.5649331

Filename

5649331