Parameterisation Invariant Statistical Shape Models

In this paper novel theory to automate shape modelling is described. The main idea is to develop a theory that is intrinsically defined for curves, as opposed to a finite sample of points along the curves. The major problem here is to define shape variation in a way that is invariant to curve parameterisations. Instead of representing continuous curves using landmarks, the problem is treated analytically and numerical approximations are introduced at the latest stage. The problem is solved by calculating the covariance matrix of the shapes using a scalar product that is invariant to global reparameterisations. An algorithm for implementing the ideas is proposed and compared to a state of the art algorithm for automatic shape modelling. The problems with instability in earlier formulations are solved and the resulting models are of higher quality.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Johan Karlsson, Anders Ericsson, Kalle Åström
• Keywords: Automatic Shape Modelling, Computer Vision, Continuous Curves, ICPR 2004, Shape Variation