Reconstructing Regular Shredded Documents by Similarity Measure
Cheng Le, Nanjie Deng, Jin Xiao · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2014
This paper describes a method to the problem of reconstructing regular shredded documents by similarity measure.Regular shredded document can be quantized as gray-level matrix or two-value matrix.So we can match the gray value of the edge of the shredded document, which is indicated as similarity value.We calculate the similarity value by using improved minimum-error method, a kind of similarity measure method.The two shredded owning the biggest similarity value is probable to be the neighboring ones.So we can reconstruct these regular shredded documents through this method until it is recovered.