Dan HURGOIU, Vasile Tompa, Calin Neamtu, Daniela Popescu


       The Kosons are ancient gold coins categorized as treasury coins which were not exchanged in commercial trades. This specific particularity of the Kosons enables scientists to use image processing techniques in the classification and authentication work. Because this type of coins have no signs of wear specific to a long time of circulation, it is now possible, by a rigorous inventory, to establish the number of molds used in the minting process. The only viable method for the identification and classification of an important amount of coins is a semi-automated or automated process. This paper presents the working algorithm and concepts implemented by the authors for Koson coins inventory, and also presents the hardware and software platforms designed for this application. The algorithm used to develop the software application is based on the Fast Fourier Transform (FFT) and Discrete Fourier Transform (DFT) applied in a correlation filter.

Keywords:  image processing, cross-correlation, gold Kosons, Dacian treasury

Full Text:



L Morovič, P. Pokorný, Optical 3D Scanning of Small Parts, Advanced Materials Research, Volumes: 468-471 pp. 2269-2273, Trans Tech Publications, Switzerland; 2012.

M. Zaharieva, M. Kampel, S. Zambanini, Image based recognition of ancient coins, 12th International Conference on Computer Analysis of Images and Patterns (CAIP'07), pp. 547–554, 2007.

Zambanini S., Kampel M., Coarse-to-Fine Correspondence Search for Classifying Ancient Coins, 2nd ACCV Workshop on e-Heritage, Daejeon, South Korea, 2012.

***, NI Vision Concepts Manual, PN: 372916J-01, National Instruments, 2010.

R. Huber, H. Ramoser, K. Mayer, Harald Penz, Michael Rubik, Classification of coins using an eigenspace approach, Pattern Recognition Letters, Volume 26, Issue 1, Pages 61-75, ISSN: 0167-8655, 2005

Chih-Cheng Lu, Wen-Liu Chang, Chih-Chen Wang, Sheng-Fong Yu, Jen-Tzong Jeng, A statistical pattern analysis approach for rapid coin identification based on Eddy-current sensors, Procedia Engineering, Vol. 15, pp. 5579-5583, ISSN 1877-7058, 2011.

A. Dehghani, H. Moghaddam and M.S. Moin, Optic disc localization in retinal images using histogram matching, Eurasip Journal, DOI: 10.1186/1687-5281-2012-19

A. Poursaberi, H. Noubari, M. Gavrilova, S. Yanushkevich, Gauss–Laguerre wavelet textural feature fusion with geometrical information for facial expression identification EURASIP Journal, 2012.

Ghanem T.M, Moustafa M.N, Shahein H.I, Gabor wavelet based automatic coin classsification, 16th IEEE International conference on image processing, ISBN: 978-1-4244-5653-6, pp. 305-308, 2009.


  • There are currently no refbacks.