|Title||:||Solutions for Apictorial Jigsaw Puzzle: Hand Shredded Content-less Pages and 3D Fragments|
|Speaker||:||Lalitha K S (IITM)|
|Details||:||Tue, 4 Oct, 2016 3:00 PM @ BSB 361|
|Abstract:||:||Reassembly of fragmented 3D objects, fragments of shredded sheets of paper and highly fragmented bone fractures are tasks of great importance. These find application in fields like medicine, archaeology, entertainment and forensics. Manual reassembly in all these cases is time-consuming and difficult to perform. Thus, the digital reassembly is of significant research interest to the imaging and graphics communities.
In the reassembly of hand shredded sheets of paper, the task is to find the geometric Euclidean transformation that should be applied to each fragment for complete reassembly. We propose an efficient iterative framework to solve apictorial jigsaw puzzles of hand shredded content-less pages, using only the shape information. The proposed framework consists of four phases. In the first phase, normalized shape features are extracted from fragment contours. Then, for all possible matches between pairs of fragments transformation parameters for alignment of fragments and three goodness scores are estimated. In the third phase, incorrect matches are eliminated based on the score values. The alignments are refined by pruning the set of pairwise matched fragments. Finally, a modified graph-based framework for agglomerative clustering is used to globally reassemble the page(s). Experimental evaluation of our proposed framework on an annotated dataset of shredded documents shows the efficiency in the reconstruction of multiple content-less pages from arbitrarily torn fragments. Future scope of our work will target reassembling geometrical 3D objects using the RGBD (4-D) images acquired from multiple views of the fragments.