Perceptual organization is scale-invariant. In turn, a segmentation that separates features consistently at all scales is the desired one that reveals the underlying structural organization of an image. Addressing cross-scale correspondence with interior pixels, we develop this intuition into a general segmenter that handles texture and illusory contours through edges entirely without any explicit characterization of texture or curvilinearity. Experimental results demonstrate that our method not only performs on par with either texture segmentation or boundary completion methods on their specialized examples, but also works well on a variety of real images.
Segmentation induced by scale invariance
01.01.2005
1173923 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Scale Invariance in Meridional Distribution of Stratospheric Ozone
British Library Conference Proceedings | 1997
|Receiving Two Consequences: Tests of Monotonicity and Scale Invariance
Online Contents | 2000
|Invariance Signatures: Characterizing Contours by Their Departures from Invariance
British Library Online Contents | 2000
|A Practical Pattern Recognition System for Translation, Scale, and Rotation Invariance
British Library Conference Proceedings | 1994
|