IMAGE-BASED TECHNIQUES FOR SHREDDED DOCUMENT RECONSTRUCTION

An image-based technique for shredded document reconstruction includes the steps of: employing an image processing process to obtain shred images of the shredded document, and then extracting several features of shred images for reconstruction with two similarity measures, and then employing an algorithm using the shred coding scheme and average word length that is insensitive to the shredding noise on image boundaries, and then a weighted digraph is then carried out to derive the optimal shred sorting result for document reconstruction in terms of the shortest path. Experiments are presented for both the synthetic and real data sets. The results show that the proposed method has correctly merged the majority of the shredded document.