MPhil Thesis Defence


"Image Super-resolution Using Neighbor Embedding over Visual Primitive
Manifolds"

By

Mr. Wei Fan


Abstract

Image super-resolution refers to the process by which a higher-resolution
enhanced image is synthesized from one or more low-resolution images.  It
finds a number of real-world applications in computer vision and computer
graphics.  In this thesis, we propose a novel learning-based method for
the problem of single-image super-resolution.  Given a low-resolution
image, its underlying higher-resolution details are synthesized based on a
set of training images.  In order to build a compact yet descriptive
training set, we investigate the characteristic local primitive structures
contained in large volumes of small image patches. Inspired by recent
progress in manifold learning research, we take the assumption that these
small primitive patches in the low-resolution and high-resolution images
form manifolds with similar local geometry in the corresponding image
feature spaces.  This assumption leads to a super-resolution approach
which reconstructs the feature vector corresponding to an image patch by
its neighbors in the feature space.  To speed up the process of searching
for the nearest neighbors for any input image patch, we partition the
training set into multiple clusters and also sample the training set
probabilistically so that the data distribution is as uniform as possible.
These two preprocessing techniques make the neighbor embedding algorithm
more efficient as well as more effective.  Experimental results show that
our super-resolution method can synthesize higher-quality images compared
with existing methods.


Date:				Friday, 1 June 2007

Time:				4:00p.m.-6:00p.m.

Venue:				Room 3416
				Lifts 17-18

Committee Members:		Dr. Dit-Yan Yeung (Supervisor)
				Dr. Albert Chung (Chairperson)
				Prof. Long Quan


**** ALL are Welcome ****