We present an approach for modeling and filtering digitally scanned images. The
digital contour of an image is segmented to identify the linear segments, the nonlinear segments and critical corners. The nonlinear segments are modeled by B-splines. To remove the contour noise, we propose a weighted least q m s model to account for both the fitness of the splines as well as their approximate curvatures. The solutions of the least squares models provide the control vertices of the splines. We show the effectiveness of our approach with several representations constructed from various scanned images