Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together

Johannes Schuiki; Christof Kauba; Heinz Hofbauer; Andreas Uhl

doi:10.1109/IWBF57495.2023.10157739

Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together

Johannes Schuiki, Christof Kauba, Heinz Hofbauer, Andreas Uhl

Artificial Intelligence and Human Interfaces

Research output: Contribution to conference › Paper › peer-review

Abstract

Intrinsic, non-invasive product authentication is still
an important topic as it does not generate additional costs
during the production process. This topic is of specific interest
for medical products as non-genuine products can directly
effect the patients’ health. This work investigates micro-texture
classification as a mean of proving the authenticity of zircon
oxide blocks (for dental implants). Samples of three different
manufacturers were acquired using four smartphone devices with
a clip-on macro lens. In addition, an existing drug packaging
material database was utilized. While the intra-sensor micro-
texture classification worked well, the cross-sensor classification
results were less promising. In an attempt to track down the
limiting factors, intrinsic sensor features usually used in device
identification were investigated as well.

Original language	English
Pages	1-6
DOIs	https://doi.org/10.1109/IWBF57495.2023.10157739
Publication status	Published - 2023
Event	11th International Workshop on Biometrics and Forensics (IWBF'23) - , Spain Duration: 20 Apr 2023 → 21 Apr 2023

Workshop

Workshop	11th International Workshop on Biometrics and Forensics (IWBF'23)
Country/Territory	Spain
Period	20/04/23 → 21/04/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

micro texture
texture classification
smartphone imaging
cross sensor
material classification
product authentication

Fields of Science and Technology Classification 2012

102 Computer Sciences

Access to Document

10.1109/IWBF57495.2023.10157739

Cite this

@conference{f9a5af821ad8483faf009c877c2f8a24,

title = "Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together",

abstract = "Intrinsic, non-invasive product authentication is stillan important topic as it does not generate additional costsduring the production process. This topic is of specific interestfor medical products as non-genuine products can directlyeffect the patients{\textquoteright} health. This work investigates micro-textureclassification as a mean of proving the authenticity of zirconoxide blocks (for dental implants). Samples of three differentmanufacturers were acquired using four smartphone devices witha clip-on macro lens. In addition, an existing drug packagingmaterial database was utilized. While the intra-sensor micro-texture classification worked well, the cross-sensor classificationresults were less promising. In an attempt to track down thelimiting factors, intrinsic sensor features usually used in deviceidentification were investigated as well.",

keywords = "micro texture, texture classification, smartphone imaging, cross sensor, material classification, product authentication",

author = "Johannes Schuiki and Christof Kauba and Heinz Hofbauer and Andreas Uhl",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 11th International Workshop on Biometrics and Forensics (IWBF'23) ; Conference date: 20-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1109/IWBF57495.2023.10157739",

language = "English",

pages = "1--6",

}

TY - CONF

T1 - Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together

AU - Schuiki, Johannes

AU - Kauba, Christof

AU - Hofbauer, Heinz

AU - Uhl, Andreas

PY - 2023

Y1 - 2023

N2 - Intrinsic, non-invasive product authentication is stillan important topic as it does not generate additional costsduring the production process. This topic is of specific interestfor medical products as non-genuine products can directlyeffect the patients’ health. This work investigates micro-textureclassification as a mean of proving the authenticity of zirconoxide blocks (for dental implants). Samples of three differentmanufacturers were acquired using four smartphone devices witha clip-on macro lens. In addition, an existing drug packagingmaterial database was utilized. While the intra-sensor micro-texture classification worked well, the cross-sensor classificationresults were less promising. In an attempt to track down thelimiting factors, intrinsic sensor features usually used in deviceidentification were investigated as well.

AB - Intrinsic, non-invasive product authentication is stillan important topic as it does not generate additional costsduring the production process. This topic is of specific interestfor medical products as non-genuine products can directlyeffect the patients’ health. This work investigates micro-textureclassification as a mean of proving the authenticity of zirconoxide blocks (for dental implants). Samples of three differentmanufacturers were acquired using four smartphone devices witha clip-on macro lens. In addition, an existing drug packagingmaterial database was utilized. While the intra-sensor micro-texture classification worked well, the cross-sensor classificationresults were less promising. In an attempt to track down thelimiting factors, intrinsic sensor features usually used in deviceidentification were investigated as well.

KW - micro texture

KW - texture classification

KW - smartphone imaging

KW - cross sensor

KW - material classification

KW - product authentication

UR - http://www.scopus.com/inward/record.url?scp=85165670018&partnerID=8YFLogxK

U2 - 10.1109/IWBF57495.2023.10157739

DO - 10.1109/IWBF57495.2023.10157739

M3 - Paper

SP - 1

EP - 6

T2 - 11th International Workshop on Biometrics and Forensics (IWBF'23)

Y2 - 20 April 2023 through 21 April 2023

ER -

Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together

Abstract

Workshop

Bibliographical note

Keywords

Fields of Science and Technology Classification 2012

Access to Document

Other files and links

AIIVSalzburg: Artificial Intelligence in Industrial Vision: A Salzburg Perspective

Cite this

Cross-Sensor Micro-Texture Material Classification and Smartphone Acquisition do not go well together

Abstract

Workshop

Bibliographical note

Keywords

Fields of Science and Technology Classification 2012

Access to Document

Other files and links

Projects

AIIVSalzburg: Artificial Intelligence in Industrial Vision: A Salzburg Perspective

Cite this