Automatic image annotation by ensemble of visual descriptors

Akbas E., VURAL F. T. Y.

IEEE Conference on Computer Vision and Pattern Recognition, Minnesota, United States Of America, 17 - 22 June 2007, pp.3620-3621 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/cvpr.2007.383484
  • City: Minnesota
  • Country: United States Of America
  • Page Numbers: pp.3620-3621
  • Middle East Technical University Affiliated: Yes


Automatic image annotation systems available in the literature concatenate color, texture and/or shape features in a single feature vector to learn a set of high level semantic categories using a single learning machine. This approach is quite naive to map the visual features to high level semantic information concerning the categories. Concatenation of many features with different visual properties and wide dynamical ranges may result in curse of dimensionality and redundancy problems. Additionally, it usually requires normalization which may cause an undesirable distortion in the feature space.