A Computer Vision System that Assembles Canonical Jigsaw Puzzles Using the Euclidean Skeleton and Isthmus Critical Points

This paper describes a computer vision system which can assemble canonical jigsaw puzzles. The most novel aspect of this system is that the methodology presented here derives a new set of critical points which define a feature which can be used in matching partial boundaries (or contours) of planar regions. This global feature, called an Isthmus, can be efficiently and reliably computed from the Euclidean skeleton or Medial Axis Transformation (MAT) of an object. A heuristic matching technique using Isthmus critical points is applied to the partial boundary matching problem of jigsaw puzzle fitting. The Isthmus feature may also be a useful feature in a broader class of image processing problems such as: the narrowing of arteries in medical applications, geographic images, collision avoidance problems in robot path planning, and any application in which the point of narrowest necking of a planar region needs to be located. * This work is based upon a project supported by the National Science Foundation (NSF) under Grant No. USE905037 1 and the Faculty Grants Committee of Millersville University.