The University of Southampton
University of Southampton Institutional Repository

Visual scene recognition with biologically relevant generative models

Visual scene recognition with biologically relevant generative models
Visual scene recognition with biologically relevant generative models
This research focuses on developing visual object categorization methodologies that are based on machine learning techniques and biologically inspired generative models of visual scene recognition. Modelling the statistical variability in visual patterns, in the space of features extracted from them by an appropriate low level signal processing technique, is an important matter of investigation for both humans and machines. To study this problem, we have examined in detail two recent probabilistic models of vision: a simple multivariate Gaussian model as suggested by (Karklin & Lewicki, 2009) and a restricted Boltzmann machine (RBM) proposed by (Hinton, 2002). Both the models have been widely used for visual object classification and scene analysis tasks before. This research highlights that these models on their own are not plausible enough to perform the classification task, and suggests Fisher kernel as a means of inducing discrimination into these models for classification power. Our empirical results on standard benchmark data sets reveal that the classification performance of these generative models could be significantly boosted near to the state of the art performance, by drawing a Fisher kernel from compact generative models that computes the data labels in a fraction of total computation time. We compare the proposed technique with other distance based and kernel based classifiers to show how computationally efficient the Fisher kernels are. To the best of our knowledge, Fisher kernel has not been drawn from the RBM before, so the work presented in the thesis is novel in terms of its idea and application to vision problem.
Azim, Tayyaba
c1f7c748-f020-4566-8486-94c8fbee4836
Azim, Tayyaba
c1f7c748-f020-4566-8486-94c8fbee4836
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f

Azim, Tayyaba (2014) Visual scene recognition with biologically relevant generative models. University of Southampton, Physical Sciences and Engineering, Doctoral Thesis, 193pp.

Record type: Thesis (Doctoral)

Abstract

This research focuses on developing visual object categorization methodologies that are based on machine learning techniques and biologically inspired generative models of visual scene recognition. Modelling the statistical variability in visual patterns, in the space of features extracted from them by an appropriate low level signal processing technique, is an important matter of investigation for both humans and machines. To study this problem, we have examined in detail two recent probabilistic models of vision: a simple multivariate Gaussian model as suggested by (Karklin & Lewicki, 2009) and a restricted Boltzmann machine (RBM) proposed by (Hinton, 2002). Both the models have been widely used for visual object classification and scene analysis tasks before. This research highlights that these models on their own are not plausible enough to perform the classification task, and suggests Fisher kernel as a means of inducing discrimination into these models for classification power. Our empirical results on standard benchmark data sets reveal that the classification performance of these generative models could be significantly boosted near to the state of the art performance, by drawing a Fisher kernel from compact generative models that computes the data labels in a fraction of total computation time. We compare the proposed technique with other distance based and kernel based classifiers to show how computationally efficient the Fisher kernels are. To the best of our knowledge, Fisher kernel has not been drawn from the RBM before, so the work presented in the thesis is novel in terms of its idea and application to vision problem.

PDF
Azim.pdf - Other
Download (12MB)

More information

Published date: May 2014
Organisations: University of Southampton, Southampton Wireless Group

Identifiers

Local EPrints ID: 366666
URI: http://eprints.soton.ac.uk/id/eprint/366666
PURE UUID: c6d11cd9-eeb8-49ea-8d93-66134937b1bf

Catalogue record

Date deposited: 04 Sep 2014 08:54
Last modified: 18 Jul 2017 02:09

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×