Recognition of partially occluded objects using B-spline representation

摘要

An object recognition method using the B-spline representation of the boundary is described. Curve segments are represented using B-splines which are piecewise polynomial curves guided by a sequence of points. The B-spline control points found from the boundary points are then used to extract local features of the curve. Comparison of a set of control points, obtained from the two images, is possible only if they are normalized. Normalization of the two curve segments (or control points) involves the detection of a consistent set of scale, rotation and translation parameters. A Hough transform like method is applied to normalize the two curve boundaries using extracted local features. The merit of a match is evaluated using the normalized B-spline control points. The ability of the technique to handle partial boundary information is also demonstrated.