Semi-automatic Forensic Reconstruction of Ripped-up Documents

Abstract

Manual reconstruction of ripped-up documents can be a very difficult and time-consuming task. This paper discusses a semi-automatic toolset that can be used for reconstructing ripped-up documents. First, we present a brief overview of our current fragment scanning,image segmentation and feature computation methods. Then, we discuss how fragments can be matched using their computed features. Next, we report on our global multi-fragment matching strategy and discuss the interactive components of the toolset that can be used to control and iterate through an entire reconstruction process. Finally, we illustrate the efficiency of the proposed approach with experimental results.