Evaluation of Deep Learning models on UV ink : a Fake Money detection scheme with RPN

As soon as coins or money was invented, there were people trying to make counterfeits. Counterfeit money is fake money that is produced without the permission of the state or government, usually to imitate the currency and deceive the intended recipient. In Bangladesh, this is a significant problem and the problem is becoming more and more phenomenon as the days are passing by. Today’s modern bank notes have several security features that makes easier to identify fake notes. One of the security features is the use of UV ink. Bank notes deliberately put random flecks of color scattered all over the surface of the money - which acts as a extra layer of protection against counterfeiters. We propose an automatic authentication model for identifying counterfeit money based on these random flecks of color which is visible under UV light. To obtain a benchmark result, existing object detection pre-trained models were used, followed by MobileNet, Inception, ResNet50, ResNet101, and Inception-ResNet architectures. After that, using the Region Proposal Network (RPN) method with Convolutional Neural Network (CNN) based classification the optimal model was proposed. The proposed model had a 96.3 percent accuracy. It is critical to reduce the circulation of counterfeit money in a country’s economy to stop inflation. This study will aid in the detection of counterfeit money and, hopefully, reduce its spread.

Competitively-Issued Convertible Bank Notes in a Theory of Finance: Earl Thompson Meets Fischer Black

In this paper, I show the validity of and the relationship between two previously unrelated claims in monetary theory. The first claim, made by Earl Thompson, is that privately-issued bank notes pay a positive rate of return in a competitive equilibrium. The second claim, made by Fischer Black, is that it is possible to have a gold standard in which the gold reserves of the central bank are near zero. I show that both of these claims are correct under the assumption of complete markets and perfect commitment. The link between these claims is the Black-Scholes equation applied to convertible bank notes. In commodity-based monetary systems, bank notes are perpetual American options. I extend the model to consider the implications of a lack of commitment on the part of the bank and incomplete markets. I show that both arguments break down when banks lack commitment to redemption or markets are incomplete. I conclude with implications for macroeconomic theory.

Considerations on Fractional Reserve Banking and Free-Banking

In this article, our goal is to examine a controversy very dear to Austrian economists: that of the legitimacy of the fractional reserve banking system, defined as a system in which the bankers keep in their vaults a quantity of money (narrowly defined) lower than the quantity of cash deposits granted to their clients. In the Austrian vision, the monetary supply, broadly defined (Mises, 1971), consists of money properly said, plus monetary substitutes (bank notes, cash deposits), plus credit-money, this one corresponding to any future right to a monetary sum (time deposits, promissory notes, pre-fixed derivatives). In a narrow sense, money supply consists in money properly said (fiat-money or commodity money). We must, however, clarify some aspects of the money supply. Monetary substitutes have their origin in the monetary certificates. Monetary certificates, in their turn, are tools utilized to confer information about the medium of exchange. For instance, precious metal coins mintage confers information about the metal’s purity and about the weight of the coin; bank notes and current account balances confer information about the amount, overseer and proprietor of the deposited money. So, money certificates can change the agents’ valuations concerning the particular good in question, even being able of independent valuation. Monetary certificates can be physically connected to the medium of exchange or separated from it. In the case of physically connected monetary certificates, we have what we normally call monetary substitutes. Monetary substitutes can, due to their nature, work as property titles to the very medium of exchange. Contemporaneously, monetary substitutes usually can be identified with cash deposits (current account balances) and paper checks, provided that the use of bank notes is increasingly rare. Having made those clarifications concerning monetary substitutes, we will, following Mises (1971, p. 135), call fiduciary media the quantity of monetary substitutes that exceeds the quantity of money properly said. However, before proceeding with our Investigation about the consequences of the legalization of the production of fake monetary substitutes (fiduciary media), we must explain what would be a fake monetary substitute and the nature of this counterfeiting. We must, therefore, start our argumentation establishing some differences about the nature of loan and deposit contracts [x].