Banknote Recognition Research Articles

A High Performance Banknote Recognition System Based on a One-Dimensional Visible Light Line Sensor.

An algorithm for recognizing banknotes is required in many fields, such as banknote-counting machines and automatic teller machines (ATM). Due to the size and cost limitations of banknote-counting machines and ATMs, the banknote image is usually captured by a one-dimensional (line) sensor instead of a conventional two-dimensional (area) sensor. Because the banknote image is captured by the line sensor while it is moved at fast speed through the rollers inside the banknote-counting machine or ATM, misalignment, geometric distortion, and non-uniform illumination of the captured images frequently occur, which degrades the banknote recognition accuracy. To overcome these problems, we propose a new method for recognizing banknotes. The experimental results using two-fold cross-validation for 61,240 United States dollar (USD) images show that the pre-classification error rate is 0%, and the average error rate for the final recognition of the USD banknotes is 0.114%.

Old and Worn Banknote Detection Using Sparse Representation and Neural Networks

This paper provides a fast method to recognize a variety of Persian banknotes at different scales. In this technique, the PCA, LDA and sparse representation methods are utilized at feature extraction stage and follows with MLP neural networks, LVQ and SOM in classification. Finally, the application of sparse matrix representation method and combination of both SOM and LVQ neural networks would lead to the best efficiency with precision of 91.15% in recognition of Persian banknotes particularly the worn ones.

Recognition of Paper Currency Research Based on AGA-BP Neural Network

The genetic algorithm is a randomized search method for a class of reference biological evolution of the law evolved, with global implicit parallelism inherent and better optimization. This paper presents an adaptive genetic algorithm to optimize the use of BP neural network method, namely the structure of weights and thresholds to optimize BP neural network to achieve the recognition of banknotes oriented. Experimental results show that after using genetic algorithms to optimize BP neural network controller can accurately and quickly achieved recognition effect on banknote recognition accuracy compared to traditional BP neural network has been greatly improved, improved network adaptive capacity and generalization ability.

Reliable and User Friendly U.S Banknote Recognition Application for Visually Impaired Users on Android Smartphones

This paper introduces a reliable and user-friendly Android application that helps visually impaired users recognize U.S banknotes. The application relies only on an Android Smartphone and does not require any wireless data connection or back-end infrastructure. The application is proven to be robust and reliable under various environmental conditions which differ in lighting and background conditions. The overall banknote detection accuracy is over 94% in any lighting conditions (even in a dark room) or backgrounds with near real-time banknote detection time of 7 seconds. The main contribution of this paper is the use of a robust and reliable computer vision algorithm on the Android platform combined with a friendly “vision free” user interface.

Fast and Low-Cost Mechatronic Recognition System for Persian Banknotes

In this paper, we designed a fast and low-cost mechatronic system for recognition of eight current Persian banknotes in circulation. Firstly, we proposed a mechanical solution for avoiding extra processing time caused by detecting the place of banknote and paper angle correction in an input image. We also defined new parameters for feature extraction, including colour features (RGBR values), size features (LWR) and texture features (CRLVR value). Then, we used a Multi-Layer Perceptron (MLP) neural network in the recognition phase to reduce the necessary processing time. In this research, we collected a perfect database of Persian banknote images (about 4000 double-sided prevalent images). We reached about 99.06% accuracy (average for each side) in final banknote recognition by testing 800 different worn, torn and new banknotes which were not part of the initial learning phase. This accuracy could increase to 99.62% in double-sided decision mode. Finally, we designed an ATmega32 microcontroller-based hardware with 16MHz clock frequency for implementation of our proposed system which can recognize sample banknotes at about 480ms and 560ms for single-sided detection and double-sided detection respectively, after image scanning.

On the design of embedded solutions to banknote recognition

Banknote recognition systems have many applications in the modern world of automatic monetary transaction machines. They are tradi- tionally based on simple classifiers applied over manually selected areas. A new solution in this field, borrowed by content-based image retrieval (CBIR), which is based on dense scale-invariant feature transform fea- tures in a bag-of-words framework followed by a support vector machine (SVM) classifier, is explored. The proposed computer vision system for banknote recognition, on one hand, enables recognition at high accuracy and speed, and, on the other hand, provides basis for further applications, e.g., counterfeit detection and fitness test. This approach makes the sys- tem robust to various defects, which may occur during image acquisition or during circulation life of banknote. We implemented and tested on an embedded platform three state-of-the-art classification techniques (SVM, artificial neural network (ANN), and hidden Markov model (HMM)). The comparative results are reported for accuracy with different sizes of the training datasets and with various types of datasets. In this framework, the SVM classifier outperforms ANN and HMM on the basis of speed and accuracy on our embedded platform. © 2013 Society of Photo-

Recognition of Mexican banknotes via their color and texture features

In this paper it is introduced a recognition method for Mexican banknotes by using artificial vision. It is shown that the Mexican banknotes can be classified by extracting their color and texture features, with the RGB space and the Local Binary Patterns, respectively. We show the classification results performed with the current Mexican banknotes. We state that the proposed method can be applied to recognize banknotes of other countries which employ colors to distinguish the denominations.

Robust and Effective Component-Based Banknote Recognition for the Blind

We develop a novel camera-based computer vision technology to automatically recognize banknotes for assisting visually impaired people. Our banknote recognition system is robust and effective with the following features: 1) high accuracy: high true recognition rate and low false recognition rate, 2) robustness: handles a variety of currency designs and bills in various conditions, 3) high efficiency: recognizes banknotes quickly, and 4) ease of use: helps blind users to aim the target for image capture. To make the system robust to a variety of conditions including occlusion, rotation, scaling, cluttered background, illumination change, viewpoint variation, and worn or wrinkled bills, we propose a component-based framework by using Speeded Up Robust Features (SURF). Furthermore, we employ the spatial relationship of matched SURF features to detect if there is a bill in the camera view. This process largely alleviates false recognition and can guide the user to correctly aim at the bill to be recognized. The robustness and generalizability of the proposed system is evaluated on a dataset including both positive images (with U.S. banknotes) and negative images (no U.S. banknotes) collected under a variety of conditions. The proposed algorithm, achieves 100% true recognition rate and 0% false recognition rate. Our banknote recognition system is also tested by blind users.

Robust and Effective Component-based Banknote Recognition by SURF Features.

Camera-based computer vision technology is able to assist visually impaired people to automatically recognize banknotes. A good banknote recognition algorithm for blind or visually impaired people should have the following features: 1) 100% accuracy, and 2) robustness to various conditions in different environments and occlusions. Most existing algorithms of banknote recognition are limited to work for restricted conditions. In this paper we propose a component-based framework for banknote recognition by using Speeded Up Robust Features (SURF). The component-based framework is effective in collecting more class-specific information and robust in dealing with partial occlusion and viewpoint changes. Furthermore, the evaluation of SURF demonstrates its effectiveness in handling background noise, image rotation, scale, and illumination changes. To authenticate the robustness and generalizability of the proposed approach, we have collected a large dataset of banknotes from a variety of conditions including occlusion, cluttered background, rotation, and changes of illumination, scaling, and viewpoints. The proposed algorithm achieves 100% recognition rate on our challenging dataset.

Employing multiple-kernel support vector machines for counterfeit banknote recognition

Finding an efficient method to detect counterfeit banknotes is an imperative task in business transactions. In this paper, we propose a system based on multiple-kernel support vector machines for counterfeit banknote recognition. A support vector machine (SVM) to minimize false rates is developed. Each banknote is divided into partitions and the luminance histograms of the partitions are taken as the input of the system. Each partition is associated with its own kernels. Linearly weighted combination is adopted to combine multiple kernels into a combined matrix. Optimal weights with kernel matrices in the combination are obtained through semi-definite programming (SDP) learning. Two strategies are adopted to reduce the amount of time and space required by the SDP method. One strategy assumes the non-negativity of the kernel weights, and the other one is to set the sum of the weights to be unity. Experiments with Taiwanese banknotes show that the proposed approach outperforms single-kernel SVMs, standard SVMs with SDP, and multiple-SVM classifiers.

IMPROVMENT OF BANK NOTE CLASIFICATION RERIBILITY

Abstract Abstract This paper addresses the reliability of neuro-classifiers for bank note recognition. A local principal component analysis (PCA) method is applied to remove non-linear dependencies among variables and extract the main principal features of data. At first the data space is partitioned into regions by using a self-organizing map (SOM) model and then the PCA is performed in each region. A learning vector quantization (LVQ) network is employed as the main classifier of the system. By defining a new algorithm for rating the reliability and using a set of test data, we estimate the reliability of the system. The experimental results taken from 1,200 samples of US dollar bills show that the reliability is increased up to 100% when the number of regions as well as the number of codebook vectors in the LVQ classifier are taken properly.

A Hierarchical Approach for Banknote Image Processing Using Homogeneity and FFD Model

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This letter presents a novel banknote image processing system that includes banknote recognition, general attrition evaluation, and feature identification, in which the phenomenon of banknote deterioration is discussed in detail for the first time. To compare the sensed image with its reference, a banknote image registration algorithm based on the free-form deformations model (FFD) is proposed, in which a homogeneity-based banknote deterioration energy (BDE) is used as the cost function. The proposed algorithms lead to a high capacity for low-quality banknote processing and greatly decrease the false reject rate. </para>

Bank note recognition for the vision impaired

Blind Australians find great difficulty in recognising bank notes. Each note has the same feel, with no Braille markings, irregular edges or other tangible features. In Australia, there is only one device available that can assist blind people recognise their notes. Internationally, there are devices available; however they are expensive, complex and have not been developed to cater for Australian currency. This paper discusses a new device, the MoneyTalker that takes advantage of the largely different colours and patterns on each Australian bank note and recognises the notes electronically, using the reflection and transmission properties of light. Different coloured lights are transmitted through the inserted note and the corresponding sensors detect distinct ranges of values depending on the colour of the note. Various classification algorithms were studied and the final algorithm was chosen based on accuracy and speed of recognition. The MoneyTalker has shown an accuracy of more than 99%. A blind subject has tested the device and believes that it is usable, compact and affordable. Based on the devices that are available currently in Australia, the MoneyTalker is an effective alternative in terms of accuracy and usability.

A reliable method for classification of bank notes using artificial neural networks

We present a method based on principal component analysis (PCA) for increasing the reliability of bank note recognition machines. The system is intended for classifying any kind of currency, but in this paper we examine only US dollars (six different bill types). The data was acquired through an advanced line sensor, and after preprocessing, the PCA algorithm was used to extract the main features of data and to reduce the data size. A linear vector quantization (LVQ) network was applied as the main classifier of the system. By defining a new method for validating the reliability, we evaluated the reliability of the system for 1200 test samples. The results show that the reliability is increased up to 95% when the number of PCA components as well as the number of LVQ codebook vectors are taken properly. In order to compare the results of classification, we also applied hidden Markov models (HMMs) as an alternative classifier.

Reliability improvement of bank note classification

This paper addresses the reliability of neuro-classifiers for bank note recognition. A local principal component analysis (PCA) method is applied to remove non-linear dependencies among variables and extract the main principal features of data. At first the data space is partitioned into regions by using a self-organizing map (SOM) model and then the PCA is performed in each region. A learning vector quantization (LVQ) network is employed as the main classifier of the system. By defining a new algorithm for rating the reliability and using a set of test data, we estimate the reliability of the system. The experimental results taken from 1,200 samples of US dollar bills show that the reliability is increased up to 100% when the number of regions as well as the number of codebook vectors in the LVQ classifier are taken properly.

Banknote recognition by means of optimized masks, neural networks and genetic algorithms

Previous work by the authors has proposed a banknote recognition system using a neural network (NN) to develop new types of banknote recognition machines. This system is constructed by means of some core techniques. One is a small-scale neural recognition technique using masks. The second is a mask-optimization technique using a genetic algorithm (GA). The last is a neural hardware technique using a digital signal processor (DSP). This paper focuses on and discusses the mask optimization by the GA, which is the second core technique in the neural recognition system. This technique enables the selection of good masks, that can effectively generate the characteristic values of the input image. Further, the effectiveness of this technique is shown not only by the generalization of the NN, but also by a statistical analysis, using the Italian banknotes. Finally, the feasibility and effectiveness of the neural recognition system is shown by using worldwide banknotes.

Spatial logic algorithms using basic morphological analogic CNN operations

The CNN implementation of basic scale-, rotation- and translation-invariant morphological functions and novel types of analogic CNN algorithms using spatial logic are introduced for object recognition (detection) purposes. The power of the technique is illustrated on bank-note recognition tasks.