CORRELATED TOPIC RANDOM FIELD FOR SIMULTANEOUS OBJECT RECOGNITION AND SEGMENTATION

MPhil Thesis Defence


Title: "CORRELATED TOPIC RANDOM FIELD FOR SIMULTANEOUS OBJECT RECOGNITION AND 
SEGMENTATION"

By

Miss Jingni Chen


Abstract

In this thesis, we propose a generative topic model for image labeling 
applications and demonstrate it specifically on the problem of 
simultaneous multi-class object recognition and segmentation. Our proposed 
model has been inspired by some recently proposed topic models, such as 
latent Dirichlet allocation (LDA) and correlated topic model (CTM). 
However, borrowing such language models directly for vision applications 
is inappropriate due to their “bags of words” assumption, which implies 
that each word is drawn independently given its latent topic. To relax 
this restrictive assumption, we propose an extended topic model called 
correlated topic random field (CTRF) by modeling the latent topics of the 
patches in an image as a Markov random field (MRF). Due to the difference 
in nature between text and images, we introduce a global appearance model 
which generalizes from a discrete vocabulary space for text to a 
continuous feature space for images. Furthermore, we introduce a local 
appearance model to adaptively represent the data-dependent features for 
accurate segmentation. Inference in the CTRF model is based on an 
integrated expectation maximization (EM) framework. Extensive experiments 
performed on benchmark data sets demonstrate the success of CTRF for 
simultaneous multi-class object recognition and segmentation.


Date:				Friday, 22 May 2009

Time:				10:30am – 12:30pm

Venue:				Room 4480
 				Lifts 25-26

Committee Members:		Prof. Dit-Yan Yeung (Supervisor)
 				Dr. Chi-Keung Tang (Chairperson)
 				Dr. Nevin Zhang


**** ALL are Welcome ****