TRIPLET GEOMETRIC REPRESENTATION - A NOVEL SCALE, TRANSLATION AND ROTATION-INVARIANT FEATURE REPRESENTATION BASED ON GEOMETRIC CONSTRAINTS FOR RECOGNITION OF 2D OBJECT FEATURES
R. Kumar et P. Rockett, TRIPLET GEOMETRIC REPRESENTATION - A NOVEL SCALE, TRANSLATION AND ROTATION-INVARIANT FEATURE REPRESENTATION BASED ON GEOMETRIC CONSTRAINTS FOR RECOGNITION OF 2D OBJECT FEATURES, Image and vision computing, 15(3), 1997, pp. 235-249
Citations number
25
Categorie Soggetti
Computer Sciences, Special Topics",Optics,"Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Software Graphycs Programming","Computer Science Theory & Methods
We present a novel representation for scale, translation and rotation
independent recognition of 2D object features based on the invariance
properties of the included angles of a triangle which we exploit to co
nstruct signature histograms of local shape. We describe the practical
implementation of this new technique together with its properties, an
d present a statistical quantification of performance in the presence
of: fragmentation, additive noise and clutter. The scale-invariant pro
perties are assessed, the results of which imply a fundamental limit o
n scale-invariant recognition from a single model.