Image fragmentation is the main problem in the field of forensics and archaeology. The manual execution of aligning the fragmented images require great amount of time skill and effort. Hence we propose an integrated method for automatic color based 2-D image fragment reassembly.
The proposed method is mainly divided in to four steps:
1. Image fragments which are probably spatially adjacent are identified.
2. Identify matching contour segments for every retained couple of image fragments.
3. Identify the optimal transformation in order to align the matching counter segments.
4. Image is reassembled from its properly aligned fragments.
In each stage the most robust algorithms having the best performance are used and their results are fed to the next step.