What can artificial intelligence and image processing tell us about coins? Zachary Taylor of the American Numismatic Society gave a walkthrough in April of 'CADS'.
I was intrigued by the ideas of calibrating feature extraction by sizing a circle and throwing away everything outside the circle. I hadn’t thought of it myself — the die study I am attempting is on a series where the die is larger than the coins. It seems like an ingenious hack given how feature extraction works. Taylor also suggested that the images should be cleaned up — I think he mentioned removing backgrounds — but if the software removes everything except the center there is no need to remove backgrounds at all.
Greek coins, and many Roman coins, suffer from dies that degrade faster near the edges than the center. Only using the middle of the coin may help to keep degrading dies "together" in the tree (dendrogram) view later.
Taylor next showed setting the “blur radius” until the image looks “cartoonish”. He called the CADS kind of blurring “median blur”. This seems like a good idea. I suspect it could be done automatically with a small bit of work rather than requiring a human operator. Taylor said this was to remove circulation wear. I suspect this also makes the analysis more resistant to photographic and lighting concerns.
The next thing is what he calls “feature detection”. CADS uses OpenCV, which has been under development for a couple of decades. Taylor says using feature detection came from Huapeng Su’s earlier ANS CADS prototype. A 'feature' is just a contrast pattern of light and color, not something a human would call a 'feature' like a helmet decoration or nose shape. OpenCV tutorials suggest features represent “corners” — small regions on the image where the contrast changes a lot, and changes differently from nearby regions.
The coins CADS has been tested on seemed to be all VF-XF condition. I will be curious to see how it does with coins with a wider range of conditions. I was wondering if the blur could be different for each coin, with less blur being applied to lower grade coins.
The next step is calculating the “distance metric” between all coins. I suspect the computational complexity is N^2 to the number of coin images. He described this as “brute force Hamming method”, with the “20 best matches condensed into 1”, “agglomerative nesting” with “no risk of overfitting”. Taylor said CADS uses Oriented FAST and Rotated BRIEF (not SIFT). I am not a computer vision guy and only know the meaning of some of those terms … but OpenCV provides a library for all of these things: https://docs.opencv.org/master/d1/d89/tutorial_py_orb.html . Taylor’s work seems to be choosing to use that library and tuning the parameters rather than implementing a distance calculation from scratch.
Taylor said the algorithm to compute the distance metric takes “a few hours” for 3000 owls and he showed it taking less than a minute for about 100 Paphos tests. This also suggests the performance is N^2.
The next piece is the dendrogram graph, which looks nice. (It might just be the dendrogram feature of the Javascript library D3 https://www.d3-graph-gallery.com/dendrogram ?)
Taylor described the dendrogram sub-trees as representing dies if tuned correctly. I suspect his algorithm will also group coins from the same die by “die state”.
The “card view” letting the user quickly flip between all the children at a point in the dendrogram looked good. I suspect the card view would be greatly improved if the images were rotated and scaled so that the matched features of all coins on the card line up as close as possible.
After Taylor's demo, Alan Stahl showed Princeton’s work on the topic. He had previously shown this work at the New York Numismatic Club. Princeton’s approach has at least two key differences.
Stahl’s team used a complex physical technique to get the 3D height of the object. It is a great technique but it may not get traction because of the difficulty performing it and getting access to the coins. Yet it is worth pointing out that the CADS approach has only been tested on (over?)-cleaned silver coins. Bronze coins and coins with a lot of toning may not work directly with CADS — photographs of plaster casts may needed to get good results from CADS if patina variations overwhelm “feature detection”. If that is true then the Princeton approach not look so difficult compared to CADS for those series.
Stahl was concerned about the file size of his images. I suspect he could just use the calculated “height” as a greyscale pixel values and store his images as black-and-white JPEGs. That would reduce the image size to normal and I suspect it would let him use Taylor’s workflow directly.
Princeton had humans annotate manually some interesting points on the coins. This is labor intensive! Yet manual annotation might have some merit being used in conjunction with the Taylor approach. It might be that the CADS approach has a hard time “connecting” worn coins, partly reworked dies, or lighting techniques. Perhaps after CADS has reduced the 3000 obverses to a hundred “dies” the Princeton approach of manually marking points could be used on CADS-identified dies to find further matches that CADS missed.
I was disappointed that after all of these years the ANS and Mr. Taylor only managed to look at two series of ancient coin types. Taylor said this isn’t a problem because the “learning” is unsupervised.
The obverse of this medal depicts the bronze statue of former dictator António de Oliveira Salazar of Portugal. The statue was beheaded with dynamite during the 1974 “Carnation Revolution”. The revolution, a military-led coup d'état, started on April 25, 1974, and replaced the dictatorship with a democracy after a two-year transitional period.
The reverse shows rubble on the pedastal after the explosion, with an a question mark in the shape of Salazar's profile in the shape of a question mark.
The statue’s head has been stored for over 30 years in the attic of City Hall in Salazar’s city of birth, Santa Comba Dao, Portugal. There is current discussion that the statue be restored and placed in a newly planned Salazar museum.
"Forgery" would mean he made it himself. He was accused of passing a forgery, knowingly or unknowingly. Most people don't even look at their change, they just spend it at the next place.
According to August 2019 article, the U.S. Secret Service is working with [Minnesota] retailers to stop the flow of counterfeit money coming into the Twin Cities. If cashiers, who work with money all day long, need education to spot fake notes why should anyone expect that a regular citizen would recognize it? I have the skills to detect counterfeit currency, but since the pandemic I have been touching the bills I receive as little as possible. https://minnesota.cbslocal.com/2019/08/13/trying-to-be-very-aware-twin-cities-retailers-on-lookout-for-counterfeit-cash/
Here is a January story on $900,000 of counterfeit US currency seized by Customs and Border Patrol in Minnsota. https://www.kare11.com/article/news/local/counterfeit-bills-seized-at-minnesota-border-international-falls-china/89-920a8623-b78c-4d52-a735-6eb913ffd98d
The obverse Greek inscription: ΒΑΣΙΛΕΩΣ ΣΩΤΗΡΟΣ ΜΕΝΑΝΔΡΟΥ (Basileos Soteros Menandrou; of King Menander, the Savior)
The reverse Kharosthi inscription: 𐨨𐨂𐨱𐨪𐨗𐨯 𐨟𐨟𐨪𐨯 𐨨𐨅𐨣𐨪𐨯
The reverse inscription usually appears in coin catalogs as Maharajasa tratarasa Menamdrasa; “The Savior King Menander”. The Kharosthi might appear in a table at the end. It's real text here. (You may need a font to see it.) You can cut and paste it to other documents.
One of my hobbies is trying to put coin inscriptions into computer format. Hopefully I came close. Step one was glancing at the Unicode Kharoṣṭhī proposal, especially the table at the end.
This is what I came up with:
Ma-u-ha-ra-ja-sa 𐨨𐨂𐨱𐨪𐨗𐨯 𐨨𐨂𐨱𐨪𐨗𐨯
ta-ta-ra-sa 𐨟𐨟𐨪𐨯 𐨟𐨟𐨪𐨯
Ma-e-na-d-ra-sa 𐨨𐨅𐨣𐨪𐨯 (using a zero-width space to help position; using ra instead of the compound dr) 𐨨𐨅​𐨣𐨪𐨯
I blogged about this in in 2016.
The presentation will be Saturday May 30th 1pm EDT. To attend please RSVP Ed Snible. This presentation is hosted by the Bronx Coin Club and the Ancient Numismatic Society of Washington DC.
Dr. Jonas Emmanuel Flueck created a computer system that uses digital image recognition to match coin images to an extensive database of sales catalogs. Five years ago he founded Ex-Numis, a provenance rediscovery service for ancient coin collectors and dealers.
Dr. Flueck will tell us about the importance of provenance for both legal and scholarly reasons, his technology and database of almost one million ancient coins, and what he has learned about provenance in today’s ancient coin market.
Dr. Jonas Emmanuel Flueck is the executive director of the auction house “Lugdunum GmbH” (Switzerland); a former treasurer at the IAPN; the general secretary of the Association of Swiss Professional Numismatists; and the founder of Ex-Numis.
They believe the global pandemic justifies their action. (They give their legal and moral justification here.)
The National Emergency Library is not just medical books. It is everything they have. For the duration of the emergency you can download all kinds of amazing things. Here is a list of their numismatic holdings by decade. It includes some very rare auction catalogs and club journals.
I encourage everyone looking for an at-home project to consider finishing your own numismatic works and prepare them for publication. Stay home. Use this library for research during the pandemic.
