Faculty Article



A fraudulent addition or alteration in financial or legal documents, such as bank cheques, business contracts, medical bills, academic certificates, etc., not only causes non-recoverable damage to institutions but also the subsequent compensation of individual concerned, and also demolishes the financial condition of the commonwealth. Cheque fraud and counterfeiting are among the fastest growing problems affecting the Nation’s financial system.

White-collar crimes through addition or alteration of valuable data on financial or other legal documents are among the fastest emerging problems around the world. A fraudulent addition to cheques, contracts, and other authorized documents may cause irreparable damage in terms of human suffering as well as serious financial loss. Several such cases are reported every day to law enforcement agencies around the globe. According to Ernst & Young [Source: http:/www.ckfraud.org/statistics.html], more than 500 million cheques are forged annually, with losses totalling more than $10 billion all over the world. According to a report issued by the American Banker, an Industry Bankers Magazine, estimation of losses from cheque fraud will grow by 2.5% annually in the coming years [Source: National Check Fraud Center, USA, http:/www.ckfraud.org/statistics.html].

Solutions to examine such fraud cases are still limited to literature, specially, the automatic detection of fraud by non-destructive techniques, which has a lot of limitations. From this point of view, it has numerous significance in terms of financial safety and security for a Nation. This kind of forgery activity causes huge negative impact on the economy of a Nation. These types of events also create a very bad impact in our social life. So it has worldwide importance in the research field of Forensic Science.

It is a big challenge to identify frauds in authorised documents automatically using some software, particularly when frauds are done with same color ink and with same orientation. Alteration is a broad term its meaning is a change either by addition, deletion, or by adding additional strokes. Few specific examples of handwritten forgery activities in legal documents in terms of alteration are: (1) Payee name may be changed in a bank cheque; (2) Cheque may be raised to a higher amount; (3) A contract may be changed after the parties have come to an agreement and signed it; (4) Data on an official document may be changed, (5) Alteration may happen in medical or Academic records, etc.

Forensic analysis demands for human expertise in visual inspection of the document. Writer identification is a widely studied research topic. Script dependent approaches of writer identification derive patterns of how individuals write the alphabets in a language. Similarly, offline signature verification tends to look at curvature and other features in a signature. Inspite of latest advances in research, organizations like Forensic Labs and Banks rely on human expertise for signature verification. Pen ink identification/differentiation is another widely studied topic in Forensic Science. In document forensic, it is often important to be able to separate ink strokes of two different pens automatically, especially when frauds are done by same color ink and orientation. Fraud detection techniques can be categorized in two major pathways. The first approach is based on destructive techniques ranging from basic and modern chromatographic techniques to neutron activation analysis and chemical analysis. The second category, non-destructive techniques, includes different approaches in the fields of machine learning and modern chromatographic image processing. Few particular non-destructive approaches like Raman spectroscopy and infrared spectroscopy need special kind of imaging set up to carry out the experiments. Only a handful of approaches attempt to carry out the analysis of pen inks on images captured in visible light spectrum using normal imaging equipment. In these techniques, two basic steps, namely feature extraction (e.g., contrast, homogeneity, energy, intensity from different colour channels, etc.) and classification (e.g., MLP, NN classifier, SVM, etc.) are used to get fast processing and better accuracy.

Cheque fraud and counterfeiting are among the fastest growing problems affecting the Nation’s financial system.

Now-a-days, we are living in a digital society. Our country is changing progressively to become a digitally smart country. This is one of the key missions and visions of our government. From this point of view, this is the right time to give much more emphasis on different aspects of Forensic Science to make Digital India Mission successful.