Object Recognition by Discriminative Combinations of Line Segments, Ellipses, and Appearance Features

@article{Chia2012ObjectRB,
  title={Object Recognition by Discriminative Combinations of Line Segments, Ellipses, and Appearance Features},
  author={Alex Yong Sang Chia and Deepu Rajan and Maylor Karhang Leung and Susanto Rahardja},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2012},
  volume={34},
  pages={1758-1772}
}
We present a novel contour-based approach that recognizes object classes in real-world scenes using simple and generic shape primitives of line segments and ellipses. Compared to commonly used contour fragment features, these primitives support more efficient representation since their storage requirements are independent of object size. Additionally, these primitives are readily described by their geometrical properties and hence afford very efficient feature comparison. We pair these… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS