Skip navigation
Skip navigation

Spatial encoding of visual words for image classification

Liu, Dong; Wang, Shengsheng; Porikli, Fatih

Description

Appearance-based bag-of-visual words (BoVW) models are employed to represent the frequency of a vocabulary of local features in an image. Due to their versatility, they are widely popular, although they ignore the underlying spatial context and relationships among the features. Here, we present a unified representation that enhances BoVWs with explicit local and global structure models. Three aspects of our method should be noted in comparison to the previous approaches. First, we use a...[Show more]

CollectionsANU Research Publications
Date published: 2016-05-31
Type: Journal article
URI: http://hdl.handle.net/1885/108600
Source: Journal of Electronic Imaging
DOI: 10.1117/1.JEI.25.3.033008

Download

File Description SizeFormat Image
01_Liu_Spatial_Encoding_2016.pdf1.51 MBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator