White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Context-aware Image-to-class Distances from Image Classification

Peng, Peng (2017) Context-aware Image-to-class Distances from Image Classification. MPhil thesis, University of Sheffield.

[img]
Preview
Text
Cover.pdf
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (38Kb) | Preview
[img]
Preview
Text
Title_Page.pdf
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (9Kb) | Preview
[img]
Preview
Text
Part I.pdf
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (106Kb) | Preview
[img]
Preview
Text
Part II.pdf
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (1829Kb) | Preview

Abstract

Parametric image classification methods are usually complex because they require intensive training. Therefore, non-parametric Nearest Neighbour (NN) classifiers are preferred in many cases. Naive Bayes Nearest Neighbour (NBNN) and its modified version, local NBNN, are recently proposed classifiers that present decent performance with reduced complexity. They compute image-to-class (I2C) distance instead of image-to-image (I2I) distance. As a result, local image features will not be quantised and the effectiveness of classifiers thereby stays in a relatively good level. In this thesis, NBNN and local NBNN are further improved. With the idea of fully taking advantage of contextual information, we use saliency detectors to classify local features of reference images into foreground and background. We base our I2C distance computation on foreground and background separately. The suggestions from these distances can make label estimation more reliable. Though the times of I2C distance computation have been increased for each query image, we accelerate our classification procedure based on the evidence that the performances of NBNN and local NBNN are hardly affected when enough anchor points, which are produced by clustering, are put into use to replace the large number of referring features in each class. On the basis of the novel works stated above, the proposed context-aware methods outperform NBNN or local NBNN in both accuracy and efficiency. The comparisons have been made on three databases: Pami-09, Caltech-5, and 15-Scene.

Item Type: Thesis (MPhil)
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Electronic and Electrical Engineering (Sheffield)
The University of Sheffield > Faculty of Engineering (Sheffield)
Depositing User: Mr Peng Peng
Date Deposited: 31 Aug 2017 14:11
Last Modified: 31 Aug 2017 14:11
URI: http://etheses.whiterose.ac.uk/id/eprint/17976

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)