A Region Alignment and Matching Method for Fractured Object Reassembly

Abstract

Reassembling fractured objects has many popular applications, such as relics restoration and solving puzzle. Mostly corrosions are encountered on the shared regions of the fractured object pieces and this data loss makes the reassembly process much more difficult. In this study a minimum bounding box (MBB) based alignment and key-point based matching method is proposed. Our method first divides every single fractured object piece into regions and generates MBB for each region. Then the key-points are determined based on the distances of the middle surface computed from two opposing surfaces of the MBB of the base region. Matching between the base and the candidate regions is carried out depending on similarities of the distances computed according to key-points. The alignment surface is one of the MBB surfaces of the base region and candidate regions are also regenerated on the alignment surface, so the base and the candidate regions are aligned in this manner. We have tested our alignment and matching method on sample fractured corroded objects. The similarity results show that the proposed method aligns and matches right candidate region from other candidates accurately.