Improving Ancient Roman Coin Classification by Fusing Exemplar-Based Classification and Legend Recognition

Zambanini, Sebastian; Kavelar, Albert; Kampel, Martin

doi:10.1007/978-3-642-41190-8_17

Cited by 9 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each patch R, a distance dP to patch Q is calculated where both patches share a patch position. Similar to [21], dP is transformed to a pseudo probability ρ(dP ) where the shortest distance is mapped to the highest probability and vice versa.…”

Section: ) Find Best Patch Combination Using Markov Randommentioning

confidence: 99%

Multi-image morphing: Summarizing visual information from similar ancient coin image regions

Hodlmoser

Zambanini

Kampel

2014

2014 International Conference on Virtual Systems &Amp; Multimedia (VSMM)

Self Cite

View full text Add to dashboard Cite

The process of synthetically producing an image illustrating merged parts of multiple source images is usually known as image morphing. In this work a system is presented which morphs more than two source images to one output image. Its focus lies on using ancient coin images belonging to a common coin type. Nowadays, these coins can be worn or damaged. The goal of the presented morphing framework is the automatic detection and summarization of visual data of common regions by which outliers like wear marks of coins are removed. Since image registration forms the basis of the morphing system, SIFT flow functionalities are used. The selection of possible regioncandidates is inferred by means of a Markov Random Field in order to find the best combination of visual content. Finally, solving the Poisson equation smooths the morphed image. An evaluation is carried out in which the system is applied to three different data sets in order to demonstrate visually aesthetic results. A second evaluation is done by investigating a classification task of ancient coin images. It is shown that substituting a morphed image as training image in the classification task improves the representation of a coin type compared to a single image.

show abstract

Section: ) Find Best Patch Combination Using Markov Randommentioning

confidence: 99%

Multi-image morphing: Summarizing visual information from similar ancient coin image regions

Hodlmoser

Zambanini

Kampel

2014

2014 International Conference on Virtual Systems &Amp; Multimedia (VSMM)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A database of 180 Roman Republican coins divided into 60 classes was published by Zambanini and Kampel (2013). To our knowledge, it is the first database used to read characters on coins.…”

Section: Roman Republican Coinsmentioning

confidence: 99%

“…Arandjelovic (2012) describes the character appearance by using a HoG-like descriptor, but this step is implemented in the whole coin recognition pipeline and he neither reported individually his character recognition results nor published the database of the extracted characters. Kavelar et al (2012) and Zambanini and Kampel (2013) used a single SIFT descriptor to describe the patch that contains the character, and they reported a recognition rate of 25% to 68% on 18 classes using different training sizes per class (15-50). But, once again, the authors did not publish the databases of characters extracted from coins.…”

mentioning

confidence: 99%

A New Database of Digits Extracted from Coins with Hard-to-Segment Foreground for Optical Character Recognition Evaluation

Pan

Tougne

2017

Front. ICT

View full text Add to dashboard Cite

Since the release date struck on a coin is important information of its monetary type, recognition of extracted digits may assist in identification of monetary types. However, digit images extracted from coins are challenging for conventional optical character recognition methods because the foreground of such digits has very often the same color as their background. In addition, other noises, including the wear of coin metal, make it more difficult to obtain a correct segmentation of the character shape. To address those challenges, this article presents the CoinNUMS database for automatic digit recognition. The database CoinNUMS, containing 3,006 digit images, is divided into three subsets. The first subset CoinNUMS_geni consists of 606 digit images manually cropped from high-resolution photographs of well-conserved coins from GENI coin photographs; the second subset CoinNUMS_pcgs_a consists of 1,200 digit images automatically extracted from a subset of the USA_Grading numismatic database containing coins in different quality; the last subset CoinNUMS_pcgs_m consists of 1,200 digit images manually extracted from the same coin photographs as CoinNUMS_pcgs_a. In CoinNUMS_pcgs_a and CoinNUMS_pcgs_m, the digit images are extracted from the release date. In CoinNUMS_geni, the digit images can come from the cropped date, the face value, or any other legends containing digits in the coin. To show the difficulty of these databases, we have tested recognition algorithms of the literature. The database and the results of the tested algorithms will be freely available on a dedicated website.

show abstract

“…With such a large number of categories, the ancient coins further face an additional challenge of "rarity" where the worldwide count of specimen for some classes is considerably low. Consequently, there is clear interest in automatically extracting information about an unknown coin, and several works in the past [2,3,4,5,6,7,8,9,10,11] have attempted to address this problem. As being a visual recognition task, recent state-of-the-art convolutional neural network (CNN) based models [12,13,14] have also been applied, albeit their strong dependency on comprehensive and annotated image datasets.…”

Section: Introductionmentioning

confidence: 99%

Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention

Anwar¹,

Anwar²,

Zambanini³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

We perform 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 task of classification 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 re-

show abstract

Improving Ancient Roman Coin Classification by Fusing Exemplar-Based Classification and Legend Recognition

Cited by 9 publications

References 18 publications

Multi-image morphing: Summarizing visual information from similar ancient coin image regions

Multi-image morphing: Summarizing visual information from similar ancient coin image regions

A New Database of Digits Extracted from Coins with Hard-to-Segment Foreground for Optical Character Recognition Evaluation

Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention

Contact Info

Product

Resources

About