Framework for Image Forgery Detection and Classification Using Machine Learning

摘要

In the recent times, the rates of cyber-crimes have been surging prodigiously. It has been proven incredibly easy to create fake documents with powerful photo editing soft-wares being as pervasive as ever. Documents can be scanned and forged within minutes with the help of these softwares that have tools readily available just to do that. While photo manipulation software is handy and ubiquitous, there are also means to deftly investigate these morphed documents. This paper lays a foundation on investigation of digitally manipulated documents and provides a solution to distinguish original document from a digitally morphed document. A Graphical User Interface (GUI) was created for detection of digitally tampered images. This method has accuracy of 96.4% and has proven to be efficient and handy.