Matching Digital Copies of Documents Based on OCR
Oleg Slavin, Elena Andreeva, Nikolay Paramonov · 2019
The paper deals with methods for comparison of digitized copies of business documents. This task arises when comparing two copies of documents signed by two parties in order to find possible modifications made by one party. For example, this task is quite actual in the banking sector when concluding contracts in paper form. The comparison method of two digitized images based on the combination of several ways of comparing the words images that are descriptors of text feature points is proposed. The proposed method is well proven on own dataset (Russian). The results show the high quality and reliability of differences search in two samples of the same document.