Publication Date

Spring 2018

Degree Type

Master's Project


Computer Science


Sensitive documents are usually shredded into strips before discarding them. Shredders are used to cut the pages of a document into thin strips of uniform thickness. Each shredded piece in the collection bin could belong to any of the pages in a document. The task of document reconstruction involves two steps: Identifying the page to which each shred belongs and rearranging the shreds within the page to their original position. The difficulty of the reconstruction process depends on the thickness of the shred and type of cut (horizontal or vertical). The thickness of the shred is directly proportional to the ease of reconstruction. Horizontal cuts are easier to reconstruct because sentences in a page are intact and not broken. Vertical cuts are harder because there is very little information to glean from each shred. In this project, an Android app is developed to reconstruct the pages of a shredded document by using a photograph of the shreds as input. However, no prior knowledge of the page to which each shred belongs is assumed. The thickness of each shred should conform to the measurements of a standard strip shredder. The type of shredder cut is vertical. This work is an enhancement of an existing work of puzzle reconstruction developed by Hammoudeh and Pollett. Through the experiments conducted on both the existing model and the proposed model, it was found that the proposed pixel correlation metric model performed with 80 to 90% better accuracy than the existing RGB metric model on grayscale document images. However, the performance on high contrast images remained almost the same at 90% accuracy for both the RGB model and pixel correlation metric model.