An Image-Based Class Retrieval System for Roman Republican Coins

Abstract

We propose an image-based class retrieval system for ancient Roman Republican coins that can be instrumental in various archaeological applications such as museums, Numismatics study, and even online auctions websites. For such applications, the aim is not only classification of a given coin, but also the retrieval of its information from standard reference book. Such classification and information retrieval is performed by our proposed system via a user friendly graphical user interface (GUI). The query coin image gets matched with exemplar images of each coin class stored in the database. The retrieved coin classes are then displayed in the GUI along with their descriptions from a reference book. However, it is highly impractical to match a query image with each of the class exemplar images as there are 10 exemplar images for each of the 60 coin classes. Similarly, displaying all the retrieved coin classes and their respective information in the GUI will cause user inconvenience. Consequently, to avoid such brute-force matching, we incrementally vary the number of matches per class to find the least matches attaining the maximum classification accuracy. In a similar manner, we also extend the search space for coin class to find the minimal number of retrieved classes that achieve maximum classification accuracy. On the current dataset, our system successfully attains a classification accuracy of 99% for five matches per class such that the top ten retrieved classes are considered. As a result, the computational complexity is reduced by matching the query image with only half of the exemplar images per class. In addition, displaying the top 10 retrieved classes is far more convenient than displaying all 60 classes.

Bi-Directional Classification of Roman Period Coins by Deep Learning Methods

“…Anwar et al illustrated a graphical user interface by classifying Roman coins into 60 classes and 600 images. In this study, a 98% classification success rate was obtained by using the reverse side of the coins [6]. Ma and Arandjelović reached an average classification performance of 74.25% with a tone-based random forest classifier in a study using 400 Roman coins used for four different denominations during the reign of the Roman emperor Dominican [7].…”

“…[6] and Aslan et al[4]. Anwar et al[6] studied only 600 images and one face, while Aslan et al[4] used 6000 images, one face and one classification algorithm.…”

“…[6] and Aslan et al[4]. Anwar et al[6] studied only 600 images and one face, while Aslan et al[4] used 6000 images, one face and one classification algorithm. In the study, 12000 images, bidirectional and four different classification algorithms were used.…”

Information Entropy Algorithms for Image, Video, and Signal Processing

“…In the contribution by Anwar et al [9], "An Image-Based Class Retrieval System for Roman Republican Coins," authors propose an image-based class retrieval system for ancient Roman Republican coins that can be instrumental in various archaeological applications such as museums, numismatics study, and even online auction websites. For such applications, the aim is not only classification of a given coin, but also the retrieval of its information from a standard reference book.…”