A Solution to Reconstruct Cross-Cut Shredded Text Documents Based on Character Recognition and Genetic Algorithm

Abstract

The reconstruction of destroyed paper documents is of more interest during the last years. This topic is relevant to the fields of forensics, investigative sciences, and archeology. Previous research and analysis on the reconstruction of cross-cut shredded text document (RCCSTD) are mainly based on the likelihood and the traditional heuristic algorithm. In this paper, a feature-matching algorithm based on the character recognition via establishing the database of the letters is presented, reconstructing the shredded document by row clustering, intrarow splicing, and interrow splicing. Row clustering is executed through the clustering algorithm according to the clustering vectors of the fragments. Intrarow splicing regarded as the travelling salesman problem is solved by the improved genetic algorithm. Finally, the document is reconstructed by the interrow splicing according to the line spacing and the proximity of the fragments. Computational experiments suggest that the presented algorithm is of high precision and efficiency, and that the algorithm may be useful for the different size of cross-cut shredded text document.

A reconstruction method for cross-cut shredded documents based on the extreme learning machine algorithm

“…In the previous splicing strategy Chen et al (2019); Xu et al (2014), it is difficult to obtain correct pairing in a large number of fragments by only considering the edges of the pixels. Therefore, the row features of the text in the fragments are used as important information to classify different rows.…”

“…In order to eliminate the influence of some unpredictable factors on the feasibility of the algorithm and the accuracy of the splicing test, a feasible approach is to analyze the performance of the algorithm using a computer simulated dataset (Xu et al (2014); Gong et al (2016); Chen et al (2019)).…”

“…This is a viable solution, but it is difficult to guarantee the accuracy of the pairing. Xu et al (2014) presented a feature-matching algorithm based on character recognition using a database of the letters. Like the two-step strategy, this method reconstructs the shredded document by row clustering, intra-row splicing, and inter-row splicing.…”

“…The second step uses feature matching to merge the reconstructed fragments. This is currently the most commonly used method to solve the RCCSTD Wang & Ji (2014); Xu et al (2014); Chen et al (2019). However, because the clustering algorithm relies too much on the row distribution features, the scope of application is limited, and the error of the cluster will further affect the accuracy of the row reconstruction so that the global error increases.…”

Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning

“…If page order is not relevant (or does not apply), the definition of a positive pair of shreds can be relaxed, such that a pair (s i , s j ) is also positive if s i and s j are, respectively, the last and first shreds of different pages, even for j = i+1. The optimization problem of minimizing Equation 1 has been extensively investigated in literature, mainly using genetic algorithms [4,10,11,35] and other metaheuristics [2,24,26]. The focus of this work is, nevertheless, on the compatibility evaluation between shreds (i.e., the function c), which is critical to lead the search towards accurate reconstructions.…”