This paper describes how the early visual process of contour organisation can be realised using the EM algorithm. The underlying computational representation is based on fine spline coverings. According to our EM approach the adjustment of spline parameters draws on an iterative weighted least-squares fitting process. The expectation step of our EM procedure computes the likelihood of the data ...

This research proposes a computation approach to address the evaluation of end product machining accuracy in elliptical surfaced helical pipe bending using 6dof parallel manipulator as a pipe bender. The target end product is wearable metal muscle supporters used in build-to-order welfare product manufacturing. This paper proposes a product testing model that mainly corrects the surface directi...

Model fitting refers to problem that computing the most ideal parameters of a model so that the model gives the greatest extent of coincidence with the data. The most widely used method for fitting data with Gaussian noises should be ordinary least squares. However, the ordinary least squares method treats each datum equally, which makes it unsuitable for fitting the data containing outliers. T...

The predictive capability central to engineering science and design is provided both by mathematical models and by experimental measurements. In practice models and measurements best serve in tandem: the models can be informed by experiment; and the experiments can be guided by the models. In this nutshell we consider perhaps the most common approach to the integration of models and data: fitti...

This paper shows a new approach for non-linear least squares fitting with NURBS as curves and surfaces to measured data by the Gauss-Newton method. A Trust Region algorithm is used to reach global convergence as well as variable substitution and simple bounds. Key–Words: Non-linear least squares, NURBS, curve and surface fitting, reverse engineering, optimisation, GaussNewton