Search Results (7)

This paper describes the use of microwave technology to identify anti-counterfeiting markers on banknotes. The proposed method is based on a robust near-field scanning microwave microscope specially developed to measure permittivity maps of heterogeneous paper specimens at the micrometer scale. The equipment has a built-in vector network analyzer to measure the reflection response of a near-field coaxial probe, which makes it a standalone and portable device. A new approach employing the information of a displacement laser and the cavity perturbation technique was used to determine the relationship between the dielectric properties of the specimens and the resonance response of the probe, avoiding the use of distance-following techniques. The accuracy of the dielectric measurements was evaluated through a comparative study with other well-established cavity methods, revealing uncertainties lower than 5%, very similar to the accuracy reported by other more sophisticated setups. The device was employed to determine the dielectric map of a watermark on a 20 EUR banknote. In addition, the penetration capabilities of microwave energy allowed for the detection of the watermark when concealed behind dielectric or metallic layers. This work demonstrates the benefits of this microwave technique as a novel method for identifying anti-counterfeiting features, which opens new perspectives with which to develop optically opaque markers only traceable through this microwave technique. Full article

Recently, some state-of-the-art works have used deep learning-based architectures, specifically convolutional neural networks (CNNs), for banknote recognition and counterfeit detection with promising results. However, it is not clear which design strategy is more appropriate (custom or by transfer learning) in terms of classifier performance and inference times for massive data applications. This paper presents a comparison of the two design strategies in various types of architecture. For the transfer learning (TL) strategy, the most appropriate freezing points in CNN architectures (sequential, residual and Inception) are identified. In addition, a custom model based on an AlexNet-type sequential CNN is proposed. Both the TL and the custom models were trained and compared using a Colombian banknote dataset. According to the results, ResNet18 achieved the best accuracy, with 100%. On the other hand, the network with the shortest inference times was the proposed custom network, since its performance is up to 6.48-times faster in CPU and 16.29-times faster in GPU than the inference time with the models by transfer learning. Full article

We investigated machine learning-based joint banknote recognition and counterfeit detection method. Unlike existing methods, since the proposed method simultaneously recognize banknote type and detect counterfeit detection, it is significantly faster than existing serial banknote recognition and counterfeit detection methods. Furthermore, we propose an explainable artificial intelligence method for visualizing regions that contributed to the recognition and detection. Using the visualization, it is possible to understand the behavior of the trained machine learning system. In experiments using the United State Dollar and the European Union Euro banknotes, the proposed method shows significant improvement in computation time from conventional serial method. Full article

Automatic sorting of banknotes in payment facilities, such as automated payment machines or vending machines, consists of many tasks such as recognition of banknote type, classification of fitness for recirculation, and counterfeit detection. Previous studies addressing these problems have mostly reported separately on each of these classification tasks and for a specific type of currency only. In other words, there has been little research conducted considering a combination of these multiple tasks, such as classification of banknote denomination and fitness of banknotes, as well as considering a multinational currency condition of the method. To overcome this issue, we propose a multinational banknote type and fitness classification method that both recognizes the denomination and input direction of banknotes and determines whether the banknote is suitable for reuse or should be replaced by a new one. We also propose a method for estimating the fitness value of banknotes and the consistency of the estimation results among input trials of a banknote. Our method is based on a combination of infrared-light transmission and visible-light reflection images of the input banknote and uses deep-learning techniques with a convolutional neural network. The experimental results on a dataset composed of Indian rupee (INR), Korean won (KRW), and United States dollar (USD) banknote images with mixture of two and three fitness levels showed that the proposed method gives good performance in the combination condition of currency types and classification tasks. Full article

With the advancement in imaging technologies for scanning and printing, production of counterfeit banknotes has become cheaper, easier, and more common. The proliferation of counterfeit banknotes causes loss to banks, traders, and individuals involved in financial transactions. Hence, it is inevitably needed that efficient and reliable techniques for detection of counterfeit banknotes should be developed. With the availability of powerful smartphones, it has become possible to perform complex computations and image processing related tasks on these phones. In addition to this, smartphone users have increased greatly and numbers continue to increase. This is a great motivating factor for researchers and developers to propose innovative mobile-based solutions. In this study, a novel technique for verification of Pakistani banknotes is developed, targeting smartphones with android platform. The proposed technique is based on statistical features, and surface roughness of a banknote, representing different properties of the banknote, such as paper material, printing ink, paper quality, and surface roughness. The selection of these features is motivated by the X-ray Diffraction (XRD) and Scanning Electron Microscopy (SEM) analysis of genuine and counterfeit banknotes. In this regard, two important areas of the banknote, i.e., serial number and flag portions were considered since these portions showed the maximum difference between genuine and counterfeit banknote. The analysis confirmed that genuine and counterfeit banknotes are very different in terms of the printing process, the ingredients used in preparation of banknotes, and the quality of the paper. After extracting the discriminative set of features, support vector machine is used for classification. The experimental results confirm the high accuracy of the proposed technique. Full article

Despite a decrease in the use of currency due to the recent growth in the use of electronic financial transactions, real money transactions remain very important in the global market. While performing transactions with real money, touching and counting notes by hand, is still a common practice in daily life, various types of automated machines, such as ATMs and banknote counters, are essential for large-scale and safe transactions. This paper presents studies that have been conducted in four major areas of research (banknote recognition, counterfeit banknote detection, serial number recognition, and fitness classification) in the accurate banknote recognition field by various sensors in such automated machines, and describes the advantages and drawbacks of the methods presented in those studies. While to a limited extent some surveys have been presented in previous studies in the areas of banknote recognition or counterfeit banknote recognition, this paper is the first of its kind to review all four areas. Techniques used in each of the four areas recognize banknote information (denomination, serial number, authenticity, and physical condition) based on image or sensor data, and are actually applied to banknote processing machines across the world. This study also describes the technological challenges faced by such banknote recognition techniques and presents future directions of research to overcome them. Full article

This paper describes both hardware and software components to detect counterfeits of Euro banknotes. The proposed system is also able to recognize the banknote values. Differently than other state-of-the-art methods, the proposed approach makes use of banknote images acquired with a near infrared camera to perform recognition and authentication. This allows one to build a system that can effectively deal with real forgeries, which are usually not detectable with visible light. The hardware does not use any mechanical parts, so the overall system is low-cost. The proposed solution is reliable for ambient light and banknote positioning. Users should simply lean the banknote to be analyzed on a flat glass, and the system detects forgery, as well as recognizes the banknote value. The effectiveness of the proposed solution has been properly tested on a dataset composed by genuine and fake Euro banknotes provided by Italy's central bank. Full article