Banknote Recognition Research Articles

Mobile Application for Recognizing Colombian Currency with Audio Feedback for Visually Impaired People

Context: According to the census conducted by the National Department of Statistics (DANE) in 2018, 7.1% of the Colombian population has a visual disability. These people face conditions with limited autonomy, such as the handling of money. In this context, there is a need to create tools to enable the inclusion of visually impaired people in the financial sector, allowing them to make payments and withdrawals in a safe and reliable manner. Method: This work describes the development of a mobile application called CopReader. This application enables the recognition of coins and banknotes of Colombian currency without an Internet connection, by means of convolutional neural network models. CopReader was developed to be used by visually impaired people. It takes a video or photographs, analyzes the input data, estimates the currency value, and uses audio feedback to communicate the result. Results: To validate the functionality of CopReader, integration tests were performed. In addition, precision and recall tests were conducted, considering the YoloV5 and MobileNet architectures, obtaining 95 and 93% for the former model and 99% for the latter. Then, field tests were performed with visually impaired people, obtaining accuracy values of 96%. 90% of the users were satisfied with the application’s functionality. Conclusions: CopReader is a useful tool for recognizing Colombian currency, helping visually impaired people gain to autonomy in handling money.

The HMM-based banknote recognition system

In order to satisfy the fast, accurate and high reliability of banknote image recognition, a banknote image recognition method based on hidden Markov models (MHH) is proposed in this paper. The grid method is used to extract banknote image features and the process of image preprocessing. By analysing the experimental data, the number of Markov model states, the number of iterations and the number of Gaussian models is finally determined. This method can be used to identify any currency. In this paper, 16000 pieces of RMB were collected by the self-developed banknote cleaner as experimental samples. Experimental results show that the proposed method achieves higher recognition rate than using neural network and support vector function.

State-of-the-Art Review of Deep Learning Methods in Fake Banknote Recognition Problem

State-of-the-Art Review of Deep Learning Methods in Fake Banknote Recognition Problem

Подделка денежных знаков Банка России как угроза экономической безопасности России

The article analyzes the counterfeit banknotes number growth rate, the monetary policy aimed at improving the protective elements of banknotes, the level of counterfeiting crimes detection, and the impact of counterfeiting on the Russian economic security. The purpose of the article is to analyze the growth of cash circulation level and available methods for detecting counterfeit banknotes, as well as to determine the most relevant protective elements. The author uses the statistical data of the Central Bank of Russia on the amount of cash in circulation and counterfeit banknotes, as well as statistical data of the Ministry of Internal Affairs of Russia on the number of crimes committed under the Article 186 of the Criminal Code of the Russian Federation. The research can have a positive impact on the functioning of cash in general and become a basis for creating a unified information platform for the recognition of counterfeit banknotes, which will have a positive impact on the fight against counterfeiting and ensuring Russia’s economic security.

A prototype real-time mobile application for Thai banknote recognition to support visually impaired persons

A prototype real-time mobile application for Thai banknote recognition to support visually impaired persons

An efficient deep learning model using network pruning for fake banknote recognition

In recent years, pruning methods have been proposed to reduce the size of image classification models based on CNNs and to shorten their inference times. However, most of them are based on setting the less important parameters of the model to zero, but not on reshaping the network. Therefore, in this paper we propose a pruning methodology for sequential CNNs that modifies the shape of the network (both convolutional and fully connected layers) and was applied to four sequential networks (a custom, AlexNet, VGG11 and VGG16) for the “Original and counterfeit Colombian peso banknotes” dataset. The pruned models were evaluated quantitatively and qualitatively. First, in terms of accuracy against FLOPs and parameter reduction. Second, using HiResCAM to explain the patterns on which the model is based for decision making. Quantitative results show a reduction in parameters and FLOPs of about 75% for a reduction in accuracy of up to 0.5% across all models in this study. With larger reductions of about 95%, the AlexNet-pruned and VGG16-pruned models significantly reduced their accuracy (38.1% and 21.9%, respectively), while the custom-pruned model and the VGG11-pruned model reduced their accuracy by only 0.3% and 0.9%, respectively. Furthermore, using HiResCAM, it was observed that the custom-pruned model and the VGG11-pruned model better preserved the original model activations, even at high pruning percentages, and achieved lower accuracy reductions than their competitors. With the proposed methodology, any sequential model can be pruned and reshaped while largely retaining the accuracy of the unpruned model, or even improving it for low pruning percentages.

BANK NOTE VALUE CHECKER BASED ON IMAGE RECOGNITION

This research aims to develop a banknote recognition system that can help people with special needs, especially people with visual impairments, in recognizing banknote denominations. This system uses image processing technology and machine learning models by utilizing the Create ML library which is integrated with Apple's operating system. By using the Create ML library, modeling the recognition of banknote nominal values can be made easily and without the need for special knowledge in developing machine learning models. The dataset used in this training comes from images of banknotes that have been previously collected and processed. Machine learning models are trained to recognize important features in images such as pictures, numbers and other signs and associate them with the appropriate denominations of money. The test results show that the model created can recognize banknote denominations with an accuracy rate of 71%. This shows that the use of the nominal recognition model for banknotes that is made can help the blind in identifying the nominal money more accurately and efficiently, thereby increasing the independence and quality of life of visual impaired person

Feature Based Indian Currency Detection Using Minimum Weight Distance Classifier

The Automated Currency Recognition is of great interest as a number of automated banking systems used by financial institutions make use of it as their main function. A review of the literature on banknote recognition, however, reveals that there are no methods that have been proposed or put into practice for the identification of recently issued bank notes. Real-time applications can benefit from the suggested approach's excellent performance and relative time efficiency. We believe that the composite feature described in this thesis which combines elements of both color and texture is a first in the field of banknote identification. Our contribution is that this research initiative and the suggested technology have made real-time recognition of recently released ultimate development of real-time multi-currency recognition is made feasible by banknotes.

Ethiopian banknote recognition using deep learning

Ethiopian banknote recognition using deep learning

Ethiopian banknote recognition using deep learning

Ethiopian banknote recognition using deep learning

Currency Recognition System Using Image Processing: Libyan Banknote as a Case Study

Banknote recognition in the field of image processing is used to distinguish between banknotes of different countries and determine their values. One of the problems that emerged with this process is the recognization of the banknote. The recognition operations for Myanmar currency denominations comprise six stages: image capturing, preprocessing, target region extraction, number segmentation, currency value recognition, and output with screen displaying and voice. The currency recognition system is implemented by comparing the similarity of each banknote value template via image processing steps in the Matlab environment. To prove the effectiveness of the proposed system, the number of banknote images with two types (new and medium) from each of the four types of denominations were tried

Ethiopian Banknote Recognition Using Convolutional Neural Network and Its Prototype Development Using Embedded Platform

Money transactions can be performed by automated self-service machines like ATMs for money deposits and withdrawals, banknote counters and coin counters, automatic vending machines, and automatic smart card charging machines. There are four important functions such as banknote recognition, counterfeit banknote detection, serial number recognition, and fitness classification which are furnished with these devices. Therefore, we need a robust system that can recognize banknotes and classify them into denominations that can be used in these automated machines. However, the most widely available banknote detectors are hardware systems that use optical and magnetic sensors to detect and validate banknotes. These banknote detectors are usually designed for specific country banknotes. Reprogramming such a system to detect banknotes is very difficult. In addition, researchers have developed banknote recognition systems using deep learning artificial intelligence technology like CNN and R-CNN. However, in these systems, dataset used for training is relatively small, and the accuracy of banknote recognition is found smaller. The existing systems also do not include implementation and its development using embedded systems. In this research work, we collected various Ethiopian currencies with different ages and conditions and applied various optimization techniques for CNN architects to identify the fake notes. Experimental analysis has been demonstrated with different models of CNN such as InceptionV3, MobileNetV2, XceptionNet, and ResNet50. MobileNetV2 with RMSProp optimization technique with batch size 32 is found to be a robust and reliable Ethiopian banknote detector and achieved superior accuracy of 96.4% in comparison to other CNN models. Selected model MobileNetV2 with RMSProp optimization has been implemented through an embedded platform by utilizing Raspberry Pi 3 B+ and other peripherals. Further, real-time identification of fake notes in a Web-based user interface (UI) has also been proposed in the research.

A Magnetic Field Imaging System Based on TMR Sensors for Banknote Recognition

The high sensitivity and MEMS-compatible process of tunneling magnetoresistance (TMR) sensors provide great opportunities to develop high-resolution magnetic field detection and imaging systems. In this work, we designed a magnetic field imaging (MFI) system based on TMR sensors to detect the uniaxial magnetic field components of banknotes including US dollars (USD) and Chinese Yuan (CNY), which clearly reveals the distribution of magnetic anti-counterfeiting markers inside the banknotes. Measurement results of the USD show that the magnetic ink signal is around μT level, and the person portraits on banknotes can be revealed by the sensor signals. The testing results of the CNY banknotes indicate magnetic color-shifting ink images, as well as a clear magnetic anti-counterfeiting thread. Different from the traditional optical detection, magnetic detection provides unique signals and identification methods. With a satisfactory recognition rate, the proposed MFI system based on TMR sensors demonstrates its promising potential forgery detection and denomination identification of banknotes.

Robust and Effective Banknote Recognition Model for Aiding Visual Impaired People

Visual disabled Ethiopians find great difficulty in recognizing banknotes. Each Ethiopian banknote has an identical feel, with no Braille markings, irregular edges, or other tangible features that make it easily recognizable by blind persons. In Ethiopia, there's only one device available that will assist blind people to acknowledge their notes. Internationally, there are devices available; however, they're expensive, complex, and haven't been developed to cater to Ethiopian currency. Because of these facts, visually impaired people may suffer from recognizing each folding money. This fact necessitates a higher authentication and verification system that will help visually disabled people to simply identify and recognize the banknotes. This paper presents a denomination-specific component-based framework for a banknote recognition system. Within the study, the dominant color of the banknotes was first identified and so the exclusive feature for every denomination-specific ROI was calculated. Finally, the Colour-Momentum, dominant color, and GLCM features were calculated from each denomination-specific ROI. Designing the recognition system by thereby considering the denomination-specific ROI is simpler as compared to considering the entire note in collecting more class-specific information and robust in copying with partial occlusion and viewpoint changes. The performance of the proposed model was verified by using a larger dataset of which containing banknotes in several conditions including occlusion, cluttered background, rotation, and changes of illumination, scaling, and viewpoints. The proposed algorithm achieves a 98% recognition rate on our challenging datasets.

Detection of Fake Indian Currency Notes using Deep Learning

A normal human being can easily see and distinguish any banknote, however doing the same job is extremely difficult for someone who is visually challenged or blind. Because money plays such an essential part in our everyday lives and is required for any commercial transaction, real-time detection and recognition of banknotes is a must for anyone who is blind or visually impaired. The mobilenet based CNN model-based Indian currency detection and identification system is presented for this purpose, and it is quick and accurate. To make the system more resilient, pictures of various denominations and situations were collected first, and then these images were supplemented with various geometric and image modifications. These augmented pictures are then manually tagged, and training and validation image sets are created from them. Later, the trained model's performance was assessed on a real-time scenario as well as a test dataset. The suggested mobile net model-based technique exhibits detection accuracy of 91.33% according to the test results. This standalone system operates in real-time.

Fuzzy Logic Based Perceptual Image Hashing Algorithm in Malaysian Banknotes Detection System for the Visually Impaired

Visually impaired persons have difficulty in business that dealing with banknote. This paper proposed a Malaysian banknotes detection system using image processing technology and fuzzy logic algorithm for the visually impaired. The Malaysian banknote reader will first capture the inserted banknote image, sending it to the cloud server for image processing via Wi-Fi medium. The cloud server is established to receive the banknote image sending from the banknote reader, processing them using perceptual hashing based image searching and fuzzy logic algorithm, then return the detected banknote’s value results back to the banknote reader. The banknote reader will display the results in terms of voice message played on the mini speaker attached on it, to allow visually impaired persons knowing the banknote’s value. This hardware mechanism reduces the size and costs for the banknote reader carried by the visually impaired persons. Experimental results showed that this Malaysian banknotes detection system reached an accuracy beyond 95% by running test on 600 different worn, torn and new Malaysian banknotes. After the banknote image being taken by the banknote reader’s camera, the system able to detect the banknote value in about 480 mili-seconds to 560 mili-seconds for a single sided banknote recognition. The banknotes detection speed was also comparable with human observers reading banknotes, with the response of 1.0908 second per banknote slight difference reading time. The IoT and image processing concepts were successfully blended and it provides an alternative to aid the visually impaired person their daily business transaction activities in a better way.

Currency Detection for Visually Impaired Iraqi Banknote as a Study Case

It is relatively simple for a normal human to interpret and understand every banknote, but one of the major problems for visually impaired people are money recognition, especially for paper currency.
 Since money plays such an important role in our everyday lives and is required for every business transaction, real-time detection and recognition of banknotes become a necessity for blind or visually impaired people For that purpose, we propose a real-time object detection system to help visually impaired people in their daily business transactions.
 Dataset Images of the Iraqi banknote category are collected in different conditions initially and then, these images are augmented with different geometric transformations, to make the system strong. These augmented images are then annotated manually using the "LabelImg" program, from which training sets and validation image sets are prepared.
 We will use YOLOv3 real-time Object Detection algorithm trained on custom Iraqi banknote dataset for detection and recognition of banknotes. Then the label of the banknotes is identified and then converted into audio by using Google Text to Speech (gTTS), which will be the expected output.
 The performance of the trained model is evaluated on a test dataset and real-time live video. The test results demonstrate that the proposed method can detect and recognize Iraqi paper money with high mAP reaches 97.405% and a short time.

The Detection of Counterfeit Banknotes Using Ensemble Learning Techniques of AdaBoost and Voting

The movement of cash flow transactions by either electronic channels or physically created openings for the influx of counterfeit banknotes in financial markets. Aided by global economic integration and expanding international trade, attention must be geared at robust techniques for the recognition and detection of counterfeit banknotes. This paper presents ensemble learning algorithms for banknotes detection. The AdaBoost and voting ensemble are deployed in combination with machine learning algorithms. Improved detection accuracies are produced by the ensemble methods. Simulation results certify that the ensemble models of AdaBoost and voting provided accuracies of up to 100% for counterfeit banknotes.

Fake Banknote Recognition Using Deep Learning

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.

Survey on Bank Note Recognition for Smart Transaction

The usage and existential dependence on banknote withdrawals have increased worldwide. It is actually, to an extent, impossible to perform any transactions without withdrawal of banknotes. The usage of ATM to transact this money has increased worldwide since the last decade too. Though the usage of ATMs’ has significantly increased, it is fairly impossible for the visually challenged to perform ATM transactions without the help of a third-party. Most of the problems arise when the visually challenged request for help or are uncertain of what they do. So, to prevent any security breaches or issues like that, an optical based banknote recognition system can be used. With the help of the system, image recognition can be performed to extract banknote features and Optical Character Recognition can be performed to identify the amount entered, thus, making the entire transaction process easy.