My computer science diploma thesis "Object Classification using Local
Image Features" has been written in between September 2005 and May 2006 at the
Technical University of Berlin
supervision of Marc Jäger and Professor Olaf Hellwich at the Computer Vision and Remote Sensing
The thesis was graded 1.0 (very good, "sehr gut").
Object classification in digital images remains one of the most challenging
tasks in computer vision. Advances in the last decade have produced methods to
repeatably extract and describe characteristic local features in natural
images. In order to apply machine learning techniques in computer vision
systems, a representation based on these features is needed.
A set of local features
is the most popular representation and often
used in conjunction with Support Vector Machines for classification problems.
In this work, we examine current approaches based on set representations and
identify their shortcomings.
To overcome these shortcomings, we argue for extending the set representation
into a graph representation
, encoding more relevant information.
Attributes associated with the edges of the graph encode the geometric
relationships between individual features by making use of the meta data of
each feature, such as the position, scale, orientation and shape of the
feature region. At the same time all invariances provided by the original
feature extraction method are retained.
To validate the novel approach, we use a standard subset of the ETH-80
last update: Sun, 2nd July 2006