Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents

TL;DR

This paper introduces a self-supervised deep learning method for reconstructing multiple mixed shredded documents simultaneously, significantly improving accuracy over traditional pixel-based approaches in complex scenarios.

Contribution

It extends previous single-page reconstruction methods to handle multiple mixed shreds using a self-supervised pattern recognition model trained on simulated data.

Findings

Achieves over 90% accuracy on complex shredded document datasets.

Outperforms existing methods in mixed document reconstruction scenarios.

Introduces a new dataset of 100 strip-shredded documents for evaluation.

Abstract

The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solutions compromise significantly time performance. The solution presented in this work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario: the reconstruction of several mixed shredded documents at once. In our approach, the compatibility evaluation is modeled as a two-class (valid or invalid) pattern recognition problem. The model is trained in a self-supervised manner on samples extracted from simulated-shredded documents, which obviates manual annotation. Experimental results on three datasets -- including a new collection of 100 strip-shredded documents produced for this work -- have shown that the proposed method outperforms the competing ones on complex scenarios, achieving accuracy superior to 90%.