Photo Open Access

Anti-Counterfeiting for Polymer Banknotes Based on Polymer Substrate Fingerprinting ( datasets archive part 1/2)

Shen Wang; Ehsan Toreini; Feng Hao

Including the datasets of benchmark, rotation, scribbling, folding and soaking.

*Please notice the raw images of folding and soaking datasets have been lost during an unpredictable computer malfunction. The attached files in folding dataset.zip and soaking dataset.zip are the processed images, which will be used to extract the fingerprints in the following stage.

Abstract—Polymer banknotes are the trend for printed currency and have been adopted by more than fifty countries worldwide. However, over the past years, the quantity of polymer counterfeits has been increasing, so has the quality of counterfeits. This shows that the initial advantage of bringing a new polymer technology to fight against counterfeiting is reducing. To maintain one step ahead of counterfeiters, we propose a novel anti-counterfeiting technique called Polymer Substrate Fingerprinting (PSF). Our technique is built based on the observation that the opacity coating, a critical step during the production of polymer notes, is a stochastic manufacturing process, leaving uneven thickness in the coating layer and the random dispersion of impurities from the ink. The imperfections in the coating layer result in random translucent patterns when a polymer banknote is back-lit by a light source. We show these patterns can be reliably captured by a commodity negative-film scanner and processed into a compact fingerprint to uniquely identify each banknote. Using an extensive dataset of 6,200 sample images collected from 340 UK banknotes, we show that our method can reliably authenticate banknotes, and is robust against rough daily handling of banknotes. Furthermore, we show the extracted fingerprints contain around 900 bits of entropy, which makes it extremely scalable to identify every polymer note circulated globally. As compared with previous or existing anti-counterfeiting mechanisms for banknotes, our method has a distinctive advantage: it ensures that even in the extreme case when counterfeiters have procured the same printing equipment and ink as used by a legitimate government, counterfeiting banknotes remains infeasible because of the difficulty to replicate a stochastic manufacturing process.

Files (44.8 GB)
Name Size
benchmark dataset_split.z01
md5:c3f121c7a4ee1f9ddb32ed835e3d8430
1.6 GB Download
benchmark dataset_split.z02
md5:55bf2f986797b5caaacacc9e5b276cf9
1.6 GB Download
benchmark dataset_split.z03
md5:d98a13c9a10a01ec5fb3505e3e2c1245
1.6 GB Download
benchmark dataset_split.z04
md5:6cc26fd215960fa4e800417ec234049c
1.6 GB Download
benchmark dataset_split.z05
md5:62c75135a79f2861134f3c7e6413159a
1.6 GB Download
benchmark dataset_split.z06
md5:002c1bb39449fba413f1d6c86f24e66a
1.6 GB Download
benchmark dataset_split.z07
md5:2c55349398454149ae3e53fca61fc4dc
1.6 GB Download
benchmark dataset_split.z08
md5:cd79f3aedb6c3eda7b8e5132ab73cba6
1.6 GB Download
benchmark dataset_split.z09
md5:fdc56d31c0761064aa43ce9222a4be73
1.6 GB Download
benchmark dataset_split.zip
md5:24e9c3dcd74a6d3199ebfeceaecca330
1.1 GB Download
folding dataset.zip
md5:d0a9434bba331c79d0569a4a0ea105e5
155.9 MB Download
rotation dataset_split.z01
md5:dbcc989cdb7a26ef193a32cf3b935b7d
1.6 GB Download
rotation dataset_split.z02
md5:e63c526ce4656b9077a39ca1fb06a453
1.6 GB Download
rotation dataset_split.z03
md5:77cda0eb5eb730f8050de627ee9c98dc
1.6 GB Download
rotation dataset_split.z04
md5:142c63420d284405e26ecf7c8c1a57c7
1.6 GB Download
rotation dataset_split.z05
md5:cceca8858f2966c4fdcc11705af33e1e
1.6 GB Download
rotation dataset_split.z06
md5:cb6b18fe93746082c5a8c39fb3f74b9a
1.6 GB Download
rotation dataset_split.z07
md5:eeed9e57e7cc4609124ba99e33e6e99a
1.6 GB Download
rotation dataset_split.z08
md5:d0d62be01d9fcbf0652e1484b63a180c
1.6 GB Download
rotation dataset_split.z09
md5:7735b205a1b6e8341c25d6e2d149a50f
1.6 GB Download
rotation dataset_split.z10
md5:c9b0f40cd30c6d8ee7aa58790d69790b
1.6 GB Download
rotation dataset_split.zip
md5:027ab412a6d4b62f99b9c33dfd1000c0
152.1 MB Download
scribbling dataset_split.z01
md5:8258ca563bdbdf1d7e36e227fd343478
1.6 GB Download
scribbling dataset_split.z02
md5:4531d8d51806a80d1477ef8ec8a49ce8
1.6 GB Download
scribbling dataset_split.z03
md5:ed8ec432f059536898a445c83b3d51f7
1.6 GB Download
scribbling dataset_split.z04
md5:c543c88110f7145f325998b3c082c914
1.6 GB Download
scribbling dataset_split.z05
md5:5b2e5e09a90ffa9b51658b055a3a36c5
1.6 GB Download
scribbling dataset_split.z06
md5:277ed74b090d1b64984f1f299c9fc505
1.6 GB Download
scribbling dataset_split.z07
md5:9073f8bb3158912b475aa136df4fbb5a
1.6 GB Download
scribbling dataset_split.z08
md5:11f345b2db1d87155a5faed88a5a1503
1.6 GB Download
scribbling dataset_split.zip
md5:91dbcc7bb4f3f5960d8e5cf963de64f9
757.7 MB Download
soaking dataset.zip
md5:12ebbbe51e2eb13a9492760f9126cba9
155.1 MB Download
28
180
views
downloads
Views 28
Downloads 180
Data volume 251.3 GB
Unique views 24
Unique downloads 44

Share

Cite as