Institutionen för systemteknik (ISY)

Sparse Feature Maps in a Scale Hierarchy

Per-Erik Forssén, Gösta Granlund
AFPAC00, Kiel, Germany
AFPAC, Algebraic Frames for the Perception Action Cycle
Pages 186-196
September 2000

Abstract

This article describes an essential step towards what is called a view centered representation of the low-level structure in an image. Instead of representing low-level structure (lines and edges) in one compact feature map, we will separate structural information into several feature maps, each signifying features at a characteristic phase, in a specific scale. By characteristic phase we mean the phases 0, PI, and +-PI/2, corresponding to bright, and dark lines, and edges between different intensity levels, or colours. A lateral inhibition mechanism selects the strongest feature within each local region of scale represented. The scale representation is limited to maps one octave apart, but can be interpolated to provide a continuous representation. The resultant image representation is sparse, and thus well suited for further processing, such as pattern detection.

Full Paper

Portable document format file PDF ()
Poster in A4 format: PDF (2.1 MB)
Proceedings by Springer LNCS vol 1888

---

Bibtex entry

@InProceedings{fg2000,
  author = 	 {Per-Erik Forss\'en and G\"osta Granlund},
  title = 	 {Sparse Feature Maps in a Scale Hierarchy},
  booktitle = 	 {AFPAC, Algebraic Frames for the Perception Action Cycle},
  year = 	 {2000},
  organization = {},
  publisher = {Springer Berlin / Heidelberg},
  isbn =         {978-3-540-41013-3},
  address = 	 {Kiel, Germany},
  month = 	 {September},
  note =         {{LNCS} 1888},
  pages = 	 {186-196},
}