A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves
IEEE Transactions on Pattern Analysis and Machine Intelligence
A global approach to automatic solution of jigsaw puzzles
Proceedings of the eighteenth annual symposium on Computational geometry
Comparing Images Using the Hausdorff Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multiscale Method for the Reassembly of Two-Dimensional Fragmented Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
This paper proposes a novel approach to automatic reconstruction of two-dimensional fragments. The contour matching task in fragment reassembly is reduced into a feature segment matching problem. Efficient techniques have been applied to find the proper matching segments. Specifically, the extracted contour of every fragment is defined as a set of feature segments on it. The probability of matching for fragments is measured by the Hausdorff distance between the corresponding feature segments. If the two feature segments are matchable, one of them is rotated and translated to be coincided with another, and then the overlap contact is detected automatically under this transformation. Fragments without overlap is merged to form a new one through contour updating. Then the matching process is continued until the original object is reconstructed. Experimental results demonstrate the algorithm is reliable and efficient.