
ReppeR - Representation for Perceptual Organization
- We propose a new representation for segmented images useful for Perceptual Organization. The representation has four distinct properties:
- It is topologically consistent, i.e. the image plane is completely described.
- the representation treats fore- and background symmetrically, a change of fore- and background has a well-defined and transparent impact on the representation.
- the hierarchical structure of the representation explicitly reflects the aggregation of parts and objects
- finally the representation has an associated scale, which refers to the significance of image parts and of their relationships.
- Up to now we have one example for such a representation, where the images consist of area type features and the significance of the relationships of the blobs are based on their proximity.
- There are some slides available describing the approach.
Literature
- Stephan Heuel, Wolfgang Förstner A Dual, Scalable and Hierarchical Representation for Perceptual Organization of Binary Images. To appear at the IEEE Workshop on Perceptual Organization in Computer Vision. Santa Barbara, June 26 1998.
- Stephan Heuel Duale, Skalierbare und Hierarchische Partitionierung und Gruppierung von Binärfiguren Diploma Thesis, September 1997 (only available in german).