Classification Of Coins Research Articles

A CNN-ASSISTED DECISION SUPPORT SYSTEM FOR ANCIENT WORLD COIN CLASSIFICATION

The work is devoted to solving the problem of automating the classification of coins from the ancient world. The purpose of the work is to create a neural network model and a system for the classification of ancient coins. The object of research is photographs of coins from ancient cities in the polis of the northern Black Sea region. The subject of research is the process of coin classification. A system architecture, a neural network architecture, and an application for the classification of ancient coins are proposed. The results of the system's operation are demonstrated, and the quality of network training is evaluated. The models were trained using self-generated data samples consisting of sets of color images of coins (200 by 200 resolution) of several types and images of coins that play the role of all other coins and should be classified as not belonging to a given class. The relationship between the ratio of class coins to other coins was also found. For obverse sample 783-7831, 100% accuracy in ten epochs was achieved when the ratio between samples was 1:1, with ratios of 1:4 and 1:7, 30 epochs were required to achieve 100% accuracy. The following technologies were used to implement the Web system: a framework for Python – Django for writing the server part; a JavaScript programming language for writing the user part of the system; and a jQuery library to improve the interaction of the user part with the user. For interaction between the user and the server part of the applications, the AJAX request technology was used, which allows data to be transferred to the server part imperceptibly for the user without reloading the page. Sqlite3 was used as the main application database.

Corrections to “A Deep Learning Framework for the Classification of Brazilian Coins”

Corrections to “A Deep Learning Framework for the Classification of Brazilian Coins”

Chemical and physical studies of metallic alloy-based old Indian coins with LIBS coupled with multivariate analysis

The present work aims to demonstrate the capabilities of Laser-induced Breakdown Spectroscopy (LIBS) coupled with a multivariate technique for rapid quantification and classification of old Indian coins made of various alloys. Thirteen old Indian coins in different years of circulation, (1922–1986) were selected for the study. The concentrations were determined by Calibration free LIBS (CF-LIBS) method. The concentration of cuprum (Cu) is negligible, and aluminum (Al) is maximum in the first five coins, and vice-versa in the remaining eight coins. Two different multivariate methods, Principal Component Analysis (PCA) and Soft Independent Modelling of Class Analogy (SIMCA) have been used to classify and identify the coins. PCA classified all thirteen samples into four main alloy categories. The discernment of unknown samples to their probable class membership of alloy was performed using SIMCA. The surface hardness (Brinell hardness number) is linearly correlated with the plasma temperature and LIBS intensity ratios. The sample surface of the first and fifth coin belongs to Al-alloy, having the least surface hardness, and it became harder for Cu–Ni alloy, Ni-brass alloy, and bronze alloy. The hardness of the surface is more for bronze sample twelve. It is also observed that the plasma temperature increases monotonically with the Brinell hardness number. This analysis provides valuable information on fabrication methodology and explains large diversification in the elementary composition of old coins.

BI-DIRECTIONAL CLASSIFICATION OF ROMAN PERIOD COINS BY DEEP LEARNING METHODS

In this study, the problem of classification of coins, which have historical importance and can only be distinguished by experts, is discussed with pre-learning deep learning algorithms. In the solution of the problem, the RRC-60 dataset, which consists of the images of the coins used in the Roman Republic period, was used. In this study, pre-learning Xception, MobileNetV3-L, EfficientNetB0 and DenseNet201 models were trained using the images on both sides of the coins in the data set. As a result of the training, the best values, Precision, Recall and F1-Score metrics in the MobileNetV3-L model were 98.2%, 96.8%, 97.5%, respectively, and the test accuracy was 95.2%

A Deep Learning Framework for the Classification of Brazilian Coins

A Deep Learning Framework for the Classification of Brazilian Coins

CLASSIFICATION OF THE OLBIAN COINS OF THE SECOND HALF OF THE 4TH CENTURY BC.

Since the beginning of the XXI century, the amount of available for the researchers numismatic material has increased significantly, so introducing a new types of coins into the scientific circulation has become an especially relevant in modern numismatics, even when the archaeological context of most of these finds is almost lost. The study of ancient numismatics of Olbia is rapidly gaining in modern Ukraine. At the beginning of the XX century, ancient numismatics already had some significant achievements, but the accumulated material required urgent cataloging and systematization. During last 10 years since the publication of the most important and thorough catalog of ancient coins by Vladlen Opanasovich Anokhin, as well as the results of cataloging Olbia coins by other researchers - Valery Nechitaylo and Grigory Makandarov, numismatics has been enriched by new previously unknown coin types.
 The aim of the study. The main purpose of the article is to introduce into the scientific circulation new varieties of Olbia coins and to compile the most complete classification of Olbia coins of the IV century BC. Research methodology. In the process of scientific elaboration of the topic general scientific methods were used: analytical, chronological, and topographical, as well as source methods: critical, metrological and iconographic. A systematic approach to the processing of modern finds from private collections and access to the collections of foreign museums was the impetus for writing an expanded classification work. The scientific novelty. The value of the processed materials is that they not only complement this group of coins, but also refine previously published types in unsatisfactory condition, where incorrect reading of the names and trinkets has led to inaccuracies.
 The Conclusions. The so-called «obol series» covers the period of the Olbia minting around 350-330 BC. The monetary system consists of four denominations: obol (on the coin field depicts Demeter and the eagle on the dolphin), dikhalk (on the coin field depicts Demeter and the eagle on the dolphin), hulk (on the coin field depicts Demeter and the ear, dolphin) and hemihalk (depicts Demeter and dolphin). The die analysis allowed to divide the coins of Olbia of the IV century BC senior denomination for two stylistic groups. According to the results of our own research, we were able to determine the following number of varieties of each of these denominations: obols – 24 types, dikhalks - 6 types, hulks - 6 types, hemihalks - 2 types.
 We see the prospect of further research in the introduction into scientific circulation of new previously undiscovered varieties of Olbian coins from little-studied sources - materials of museum collections in Ukraine and abroad, among numismatic rarities sold at numismatic auctions and private collections.

Coins as decoration and element of the Tatar traditional costume in the XIX – XX centuries

This article discusses the historical-culturological component of coins in jewelry and women's costume of the Volga Tatars in the XIX – XX centuries. The subject of this research is the coins of the tsarist, Soviet and modern Russian periods, which in one way or another were used as a decorative element in the Tatar national costume and jewelry. Research methodology is comprised of the general scientific and private scientific, such as culturological analysis, empirical experience of the author in jewelry restoration, and interview. The article relies on iconographic materials, jewelry, as well as essays and testimonies of the eyewitnesses. The scientific novelty lies in the thematic selection of sources and information, analysis and comparison of the facts. The author touches upon previously unstudied technical and technological aspects in preparation and processing of coins for their use as decoration. The article reveals the specificity of using coins for decorative purposes, provides information and hypotheses based on the sources that describe the use of coins in costume decoration. The author is first to carry out the classification of coins depending on the method of fixation, perforation and elements of the costume. The article describes the method of historical dating based on the technical and technological methods of processing of coins for application in jewelry.

Klassifikation af mønter fra Valdemartiden

Classification of coins from the Valdemar eraThoughts prompted by a coin from Gudme church
 Coin dates are often considered to be accurate by archaeologists and historians. Indeed, many coin types can be dated to within a short period, often because of date inscriptions. But when dealing with anonymous coin types, we must rely on the archaeological toolbox: classification, typology and contextual evidence. In particular, the definition of types, subtypes and variations contains elements of subjectivity. Peter Hauberg published his fundamental typology for the period 1157-1241 in 1906, but only 4 years later the enormous hoard from Grenaa, most likely deposited in 1214-1234, multiplied both the known number of coins and the number of coin types from Jutland. Since then, new finds have been relatively rare, and these are mainly single finds with no datable context.The article takes as its starting point a coin found in Gudme church, with a royal portrait on the obverse and a Golgata depiction on the reverse. It reviews several coin types from the late 12th and early 13th century with the same combination of motifs. It concludes that types present in the Grenaa hoard, such as that represented by the coin from Gudme, are most likely from the first third of the 13th century, but we cannot exclude the possibility that some may be a little earlier. The dating of other types with related motifs is less certain; they may be a little earlier or even a little later, given that the overall design (king/symbol) of these types continued in use well into the mid-13th century. The types reviewed here can be divided into two groups based on their size and weight. The smaller/lighter types have mainly been found in Jutland (figs. 9, 15-18, 22-24). Many are represented in the Grenaa hoard and some specimens derive from the Bokel hoard in Germany. The larger/heavier types have a more eastern distribution, concentrated on the island of Funen, with only a single specimen in the Grenaa hoard. It is suggested that this group (figs. 1-14 and 19-21), including the Gudme coin (fig. 14), were actually struck on Funen (probably at the episcopal seat in Odense). They can be related to other rare and near-contemporary coin types with a similar concentration of finds on Funen.

Deep ancient Roman Republican coin classification via feature fusion and attention

We perform the classification of ancient Roman Republican coins via recognizing their reverse motifs where various objects, faces, scenes, animals, and buildings are minted along with legends. Most of these coins are eroded due to their age and varying degrees of preservation, thereby affecting their informative attributes for visual recognition. Changes in the positions of principal symbols on the reverse motifs also cause huge variations among the coin types. Lastly, in-plane orientations, uneven illumination, and a moderate background clutter further make the classification task non-trivial and challenging.To this end, we present a novel network model, CoinNet, that employs compact bilinear pooling, residual groups, and feature attention layers. Furthermore, we gathered the largest and most diverse image dataset of the Roman Republican coins that contains more than 18,000 images belonging to 228 different reverse motifs. On this dataset, our model achieves a classification accuracy of more than 98% and outperforms the conventional bag-of-visual-words based approaches and more recent state-of-the-art deep learning methods. We also provide a detailed ablation study of our network and its generalization capability.

Multifrequency Inductive Sensor System for Classification of Bimetallic Coins

The reliable classification of coin sets from different countries and counterfeit coins is an essential means of securing cash circulation. Especially bimetallic coins, such as 2-Euro coins, are often subjected to counterfeit by mixing them with coins of other countries or by imitations. In this article, a real-time embedded sensor system is proposed, based on inductance spectroscopy to characterize and identify bimetallic coins having similar geometric properties and looking similar at a first view. The system is based on inductance spectroscopy varying the penetration depth of the magnetic field in the bimetallic structure of the coin, which generally contains buried layers of other metals. The experimental evaluation shows that the bimetallic coins from different countries can be identified and classified by the use of the support vector machine, a machine learning algorithm. Experimental results showed that the system reached a classification accuracy up to 100% within a response rate of 36.62 ms per five bimetallic coins.

Complete classification of trapping coins for quantum walks on the two-dimensional square lattice

One of the unique features of discrete-time quantum walks is called trapping, meaning the inability of the quantum walker to completely escape from its initial position, albeit the system is translationally invariant. The effect is dependent on the dimension and the explicit form of the local coin. A four state discrete-time quantum walk on a square lattice is defined by its unitary coin operator, acting on the four dimensional coin Hilbert space. The well known example of the Grover coin leads to a partial trapping, i.e., there exists some escaping initial state for which the probability of staying at the initial position vanishes. On the other hand, some other coins are known to exhibit strong trapping, where such escaping state does not exist. We present a systematic study of coins leading to trapping, explicitly construct all such coins for discrete-time quantum walks on the 2D square lattice, and classify them according to the structure of the operator and the manifestation of the trapping effect. We distinguish three types of trapping coins exhibiting distinct dynamical properties, as exemplified by the existence or non-existence of the escaping state and the area covered by the spreading wave-packet.

Classification of Ancient Roman Coins by Denomination Using Colour, a Forgotten Feature in Automatic Ancient Coin Analysis

Ancient numismatics, that is, the study of ancient currencies (predominantly coins), is an interesting domain for the application of computer vision and machine learning, and has been receiving an increasing amount of attention in recent years. Notwithstanding the number of articles published on the topic, the variety of different methodological approaches described, and the mounting realisation that the relevant problems in the field are most challenging indeed, all research to date has entirely ignored one specific, readily accessible modality: colour. Invariably, colour is discarded and images of coins treated as being greyscale. The present article is the first one to question this decision (and indeed, it is a decision). We discuss the reasons behind the said choice, present a case why it ought to be reexamined, and in turn investigate the issue for the first time in the published literature. Specifically, we propose two new colour-based representations specifically designed with the aim of being applied to ancient coin analysis, and argue why it is sensible to employ them in the first stages of the classification process as a means of drastically reducing the initially enormous number of classes involved in type matching ancient coins (tens of thousands, just for Ancient Roman Imperial coins). Furthermore, we introduce a new data set collected with the specific aim of denomination-based categorisation of ancient coins, where we hypothesised colour could be of potential use, and evaluate the proposed representations. Lastly, we report surprisingly successful performances which goes further than confirming our hypothesis—rather, they convincingly demonstrate a much higher relevant information content carried by colour than even we expected. Thus we trust that our findings will be noted by others in the field and that more attention and further research will be devoted to the use of colour in automatic ancient coin analysis.

Classification of Ancient Roman Coins by Denomination Using Colour, a Forgotten Feature in Automatic Ancient Coin Analysis

Ancient numismatics, that is, the study of ancient currencies (predominantly coins), is an interesting domain for the application of computer vision and machine learning, and has been receiving an increasing amount of attention in recent years. Notwithstanding the number of articles published on the topic, the variety of different methodological approaches described, and the mounting realisation that the relevant problems in the field are most challenging indeed, all research to date has entirely ignored one specific, readily accessible modality: colour. Invariably, colour is discarded and images of coins treated as being greyscale. The present article is the first one to question this decision (and indeed, it is a decision). We discuss the reasons behind the said choice, present a case why it ought to be reexamined, and in turn investigate the issue for the first time in the published literature. Specifically, we propose two new colour-based representations specifically designed with the aim of being applied to ancient coin analysis, and argue why it is sensible to employ them in the first stages of the classification process as a means of drastically reducing the initially enormous number of classes involved in type matching ancient coins (tens of thousands, just for Ancient Roman Imperial coins). Furthermore, we introduce a new data set collected with the specific aim of denomination-based categorisation of ancient coins, where we hypothesised colour could be of potential use, and evaluate the proposed representations. Lastly, we report surprisingly successful performances which goes further than confirming our hypothesis—rather, they convincingly demonstrate a much higher relevant information content carried by colour than even we expected. Thus we trust that our findings will be noted by others in the field and that more attention and further research will be devoted to the use of colour in automatic ancient coin analysis.

Classification of Historical Anatolian Coins with Machine Learning Algorithms

To find out which period the historical coins belong to requires a number of scientific procedures that archaeologists or experts can do. These operations can often be time-consuming and demanding operations. From this point on, in this study, the automatically classification of historical coins by using machine learning methods is discussed.Being able to use machine learning methods to classify historical coins can help experts and can become an analysis tool without the need for scientific tests for non-experts. For this purpose, some physical properties of different coins used in Anatolian geography were collected and classified by various machine learning methods named SVM, Random Forest, Bagging, and Decision Trees. Also, two different missing values strategies are deployed in conjunction with each chosen method. Based on our findings, random forest method together with imputing missing values with mean gives an acceptable results with the accuracy rate of %71, although there are some limitations such as high rate of missing values and working with a small dataset.

Brazilian Coins Recognition Using Histogram of Oriented Gradients Features

This paper tends to the issue of coin recognition when dealing with shading and reflection variations under the same lighting conditions. In order to approach the problem, a database containing Brazilian coin images (both front and reverse side of the coin) consisting of five different denominations have been used which is provided by the kaggle-diverse and largest data community in the world. This work focuses on an automatic image classification process for Brazilian coins. The imagebased classification of coins primarily incorporates three stages where the initial step is Region of Interest (ROI) extraction; the subsequent advance is extraction of features and classification. The first step of ROI extraction is accomplished by segmenting the coin region using the proposed segmentation method. In the second step i.e., feature extraction; Histogram of Oriented Gradients (HOG) features are extracted from the image. The image is converted to a vector containing feature values. The third step is where the extracted features are mapped to the class and are known as classification. Three classification algorithms i.e., Support Vector Machine (SVM), Artificial Neural Network (ANN) and K-Nearest Neighbour are compared for classification of five coin denominations. With the proposed segmentation methodology, the best classification accuracy of 92% is achieved in the case of ANN classifier.

Classifying Medieval Bracteates

In the Middle Ages, tens of thousands of uni-faced bracteate coins were struck in the period 1140−1520. The existence of hundreds of small independent currency areas with their own mints in central, eastern and northern Europe and the strong link between bracteates and periodic re-coinage explain the large number of bracteate types. The classification and dating of bracteates and other coins can provide insight into economic and monetary development when studying coin hoards and cumulative finds. A central problem when classifying bracteates is that most of them are anonymous, i.e., there are seldom any legends or letters on the coins. In this study, four methods for dating and classifying medieval bracteates are presented: 1) legends and letters; 2) coin finds; 3) regional monetary standards; and 4) social attributes. In most cases, a combination of methods must be used to achieve accurate classification. The last two methods are especially important when legends disappear after the 1230s or when the find information of the coin is lacking.

Inaccuracies enrooted in the attribution and classification of coins of the Cilician Armenian Kingdom Part II Revisiting the copper coinage of Levon IV

At present, seven groups of copper coins are attributed to Levon IV (1320-1342), the king of Cilician Armenia. However, iconographic, stylistic and metrological differences have been observed in these coins that make the possibility of attributing them all to the same king doubtful. A comparative study shows that only two of these groups can be attributed with confidence to Levon IV. These are the small copper coins (Group VI, Figure 22 and Group VII, Figure 23), which are a coherent continuations of Oshin’s copper coinage. The minting of such small copper coins continued under the two kings who followed Levon IV: Ki (Guy) and Kostandin III (Figure 35).As for the other groups, two of them (Groups I and II, Figures 17 and 18) belong to Levon III as they are closely linked to Kostandin I’s coins by iconography and style. Preliminary observations were made on the other three groups. Issues of their dating and attribution will be further examined in one of the following articles in this series.

Classification of cryptocurrency coins and tokens by the dynamics of their market capitalizations.

We empirically verify that the market capitalizations of coins and tokens in the cryptocurrency universe follow power-law distributions with significantly different values for the tail exponent falling between 0.5 and 0.7 for coins, and between 1.0 and 1.3 for tokens. We provide a rationale for this, based on a simple proportional growth with birth and death model previously employed to describe the size distribution of firms, cities, webpages, etc. We empirically validate the model and its main predictions, in terms of proportional growth (Gibrat's Law) of the coins and tokens. Estimating the main parameters of the model, the theoretical predictions for the power-law exponents of coin and token distributions are in remarkable agreement with the empirical estimations, given the simplicity of the model. Our results clearly characterize coins as being ‘entrenched incumbents’ and tokens as an ‘explosive immature ecosystem’, largely due to massive and exuberant Initial Coin Offering activity in the token space. The theory predicts that the exponent for tokens should converge to 1 in the future, reflecting a more reasonable rate of new entrants associated with genuine technological innovations.

Corrections to deep-rooted errors in the attribution and classification of coins of the Cilician Armenian kingdom

A cursory overview of the coinage of the Cilician Armenian kings clearly shows that most of the coins of the early and middle periods are of better quality and artistic design, struck with more care, and have higher weights and silver contents. These characteristics began to deteriorate over the course of the last decades of the kingdom’s existence. This general trend in the process of Cilician coin minting has been mentioned and discussed by practically all the scholars who studied this series. According to the current classification, the entire numismatic output of that kingdom is divided between fourteen kings, beginning with Levon I (1198-1219) and ending with Levon V (1374-1375), each of them being attributed certain groups of coins.

Coarse-grained correspondence-based ancient Sasanian coin classification by fusion of local features and sparse representation-based classifier

Numismatics sorts out historical aspects of money. Identification and classification of coins, as a part of their duties, need years of experience. This research aims at using the knowledge of numismatics for developing an image-based classification of ancient Sassanian dynasty coins. A straightforward method is to take coins observe and reverse-side motifs into account, just like numismatics does. To this aim, three feature descriptors, Cosine transform, Wavelet transform and Bi-Directional Principal Component Analysis, are separately applied to the extracted motifs' areas to form the feature space. To cope with the `curse of dimensionality' and increase the `discrimination power', feature space is enriched with spatial information achieved by applying a feature selection method. Indeed, the best feature subset, which maximizes the mutual information between the joint distribution of the selected features and the classification variable, is selected using the minimum Redundancy Maximum Relevance (mRMR) method to a trade-off between thousands of features and a few hundreds of samples. One fold of our contribution dedicates to decrease the over-fitting probability of the learning model by making the Sparse Representation-based Classifier kernelized. We evaluate our method on a dataset of 573 coin images. The experimental results show that our proposed image representation is more discriminative than the competitive ones in which the system achieves a mean classification rate of 96.51 %.