Word detection applied to images of ancient Roman coins

2014 IEEE International Conference on Image Processing (ICIP)

2014

Self Cite

We propose to perform image-based ancient coin classification by recognizing symbols minted on the reverse side of coins. Dense sampling based bag-of-visual-words model is used for symbol recognition. The lack of spatial information in the bag-of-visual-words model degrades symbol recognition rate as the symbols have specific geometric structures. Furthermore, coins can be imaged under various rotations resulting in severely rotated symbols. Therefore we propose a novel bag-of-visual-words model for symbol-based coin classification which accounts for the spatial arrangement of the visual words in a rotation invariant manner. We perform our experiments on images collected from three different sources thus making our dataset more challenging. To evaluate our proposed model for robustness to rotations, we synthetically generated severely rotated coin images. In the presence of rotation differences between coins, our model outperforms the conventional bag-of-visual-words model as well as recently proposed angles histograms of pair-wise identical visual words model.

Section: Fig 1: Variations In Symbolsmentioning

confidence: 99%

A rotation-invariant bag of visual words model for symbols based ancient coin classification

Anwar

2014 IEEE International Conference on Image Processing (ICIP)

2014

Self Cite

“…Since the individual character locations are known for a specific word hypothesis, the respective character orientations are known as well and can be used to compute SIFT descriptors aligned accordingly. This increases the confidence in the hypothesis since orientationally fixed SIFT descriptors lead to a better character recognition rate [12]. In the end, the output of the legend recognition pipeline is a list of words ordered by their scores.…”

Section: Coin Classification By Legend Recognitionmentioning

confidence: 99%

“…In the past, promising approaches for recognizing ancient Roman coins including image matching [20] and the recognition of the coin legends [12] have been proposed. The former measures the visual similarity of coin images by the energy needed to establish a dense correspondence between them.…”

Section: Introductionmentioning

confidence: 99%

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

Kavelar

New Trends in Image Analysis and Processing – ICIAP 2013

2013

Self Cite

In this paper we present an image-based classification method for ancient Roman Republican coins that uses multiple sources of information. Exemplar-based classification, which estimates the coins' visual similarity by means of a dense correspondence field, and lexiconbased legend recognition are unified to a common classification approach. Classification scores from both coin sides are further integrated to an overall score determining the final classification decision. Experiments carried out on a dataset of 60 different classes comprising 464 coin images show that the combination of methods leads to higher classification rate than using them separately.

“…The legend recognition method (Kavelar et al, 2012) uses object recognition techniques rather than standard OCR methods, since OCR relies on successful binarization for the separation of text and background. Coin legends have the same color as the rest of the coin, thus intensity changes result only from the coin surface relief structure.…”

Section: Legend Recognitionmentioning

confidence: 99%

The Ilac-Project: Supporting Ancient Coin Classification by Means of Image Analysis

Kavelar

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

et al. 2013

ABSTRACT:This paper presents the ILAC project, which aims at the development of an automated image-based classification system for ancient Roman Republican coins. The benefits of such a system are manifold: operating at the suture between computer vision and numismatics, ILAC can reduce the day-to-day workload of numismatists by assisting them in classification tasks and providing a preselection of suitable coin classes. This is especially helpful for large coin hoard findings comprising several thousands of coins. Furthermore, this system could be implemented in an online platform for hobby numismatists, allowing them to access background information about their coin collection by simply uploading a photo of obverse and reverse for the coin of interest. ILAC explores different computer vision techniques and their combinations for the use of image-based coin recognition. Some of these methods, such as image matching, use the entire coin image in the classification process, while symbol or legend recognition exploit certain characteristics of the coin imagery. An overview of the methods explored so far and the respective experiments is given as well as an outlook on the next steps of the project.