@thesis{4064,
  title = {Object Classification using Local Image Features},
  abstract = {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 classification
  benchmark.},
  degree_type = {Diplom},
  institution = {Technical University of Berlin, Berlin, Germany},
  school = {Biologische Kybernetik},
  month = may,
  year = {2006},
  slug = {4064},
  author = {Nowozin, S.},
  month_numeric = {5}
}