On Automatic Authenticity Verification of Printed Security Documents

Abstract

This paper presents a pioneering effort to involve machine in checking document authenticity. A particular class of security documents has been considered for the present experiment. Bank cheques, several kinds of tickets like lottery tickets, air tickets, etc., legal deeds, certificates, mark sheets, postal stamps, etc. all these documents fall under the same class as far as security is concerned. Criminals' efforts for generating fraudulent version of such documents are on the rise. This study attempts to develop a general framework for automatic authenticity verification of such security documents. The proposed method first computationally extracts the security features from the document images and then the notion of authenticity vs. duplicity is defined in the feature space. Bank cheques are taken as a reference for conducting experiment. Support Vector Machines (SVMs) are used to verify authenticity of these cheques. Non-linear kernel functions are used to conduct this experiment. Results show that a polynomial kernel based SVM gives about 99.5% accuracy discriminating duplicate cheques from genuine ones. This strongly attests the viability of the proposed approach for machine authentication of printed security documents.

Irregular Rotation Deformation from Paper Scanning: An Investigation

“…Alternatively, flatbed scanners are both widely available and cheap (for example, the reader can refer to [4], [5] and [6]). …”

A Voting Based Approach to Detect Recursive Order Number of Photocopy Documents Using Probability Distributions

“…Literature survey in this direction reveals that the above research attempts are made in the following issues: Discriminating duplicate cheques from genuine ones [5] using non-linear kernel function; Detecting counterfeit or manipulation of printed document [4] and this work is extended to classify laser and inkjet printouts; Recognition and verification of currency notes of different countries [6] using society of neural networks along with a small work addressing on fake currencies; Identification of forged handwriting [3] using wrinkles as a feature is attempted along with comparison of genuine handwriting. One of the interesting features is a measure of the variability of the handwriting on a small scale.…”

“…whether the document belongs to the genuine document class or not. Support Vector Machines (SVMs) [5] are used to verify authenticity of these cheques.…”

Detection of Fabrication in Photocopy Document Using Texture Features Through K-Means Clustering

“…In this work, attempt is made to detect fabrication of photocopy documents in which text in variable region is fabricated by putting new contents in many ways. Many research attempts are carried out on original documents instead on photocopied documents, like signature verification, detection of forged signature [5], handwriting forgery [6], printed data forgery [7], and finding authenticity of printed security documents [8]. Literature survey in this direction reveals that the above research attempts have been made in the following issues: Discriminating duplicate cheques from genuine ones [8] using Non-linear kernel function; Detecting counterfeit or manipulation of printed document [7] and this work is extended to classify laser and inkjet printouts; Recognition and verification of currency notes of different countries [9] using society of neural networks along with a small work addressing on forged currencies; Identification of forged handwriting [6] using wrinkles as a feature is attempted along with comparison of genuine handwriting.…”