Image re-assembling (Matlab project)

    The problem of reassembling image fragments arises  in many scientific fields, such as forensics and archaeology. In the field of archaeology, the pictorial excavation findings  are almost always in the form of painting fragments.  The manual execution of this task is very difficult, as it  requires great amount of time, skill and effort. Thus, the  automation of such a work is very important and can lead  to faster, more efficient, painting reassembly and to a significant  reduction in the human effort involved. In this paper, an integrated  method for automatic color based 2-D image fragment reassembly  is presented. The proposed 2-D reassembly technique is divided into four steps. Initially, the image fragments which are  probably spatially adjacent, are identified utilizing techniques  employed in content based image retrieval systems. The second  operation is to identify the matching contour segments for every  retained couple of image fragments, via a dynamic programming technique. The next step is to identify the optimal transformation  in order to align the matching contour segments. Many registration  techniques have been evaluated to this end. Finally, the overall  image is reassembled from its properly aligned fragments. This is achieved via a novel algorithm, which exploits the alignment angles found during the previous step. In each stage, the most robust algorithms having the best performance are investigated and their results are fed to the next step. We have experimented with the proposed method using digitally scanned images of actual torn pieces of paper image prints and we produced very satisfactory reassembly results.