An evaluation framework for spectral filter array cameras to optimize skin diagnosis

Jacob Renzo Bauer, Jean Baptiste Thomas, Jon Yngve Hardeberg, Rudolf M. Verdaasdonk

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Comparing and selecting an adequate spectral filter array (SFA) camera is application-specific and usually requires extensive prior measurements. An evaluation framework for SFA cameras is proposed and three cameras are tested in the context of skin analysis. The proposed framework does not require application-specific measurements and spectral sensitivities together with the number of bands are the main focus. An optical model of skin is used to generate a specialized training set to improve spectral reconstruction. The quantitative comparison of the cameras is based on reconstruction of measured skin spectra, colorimetric accuracy, and oxygenation level estimation differences. Specific spectral sensitivity shapes influence the results directly and a 9-channel camera performed best regarding the spectral reconstruction metrics. Sensitivities at key wavelengths influence the performance of oxygenation level estimation the strongest. The proposed framework allows to compare spectral filter array cameras and can guide their application-specific development.

Original languageEnglish
Article number4805
JournalSensors (Switzerland)
Volume19
Issue number21
DOIs
Publication statusPublished - 1 Nov 2019

Fingerprint

Skin
Cameras
cameras
filters
evaluation
Oxygenation
oxygenation
spectral sensitivity
sensitivity
education
Wavelength
wavelengths

Keywords

  • Biomedical optics
  • Image quality
  • Multispectral imaging
  • Oxygenation
  • Reflectance spectroscopy
  • Spectral filter array
  • Tissue optics

Cite this

Bauer, J. R., Thomas, J. B., Hardeberg, J. Y., & Verdaasdonk, R. M. (2019). An evaluation framework for spectral filter array cameras to optimize skin diagnosis. Sensors (Switzerland), 19(21), [4805]. https://doi.org/10.3390/s19214805
Bauer, Jacob Renzo ; Thomas, Jean Baptiste ; Hardeberg, Jon Yngve ; Verdaasdonk, Rudolf M. / An evaluation framework for spectral filter array cameras to optimize skin diagnosis. In: Sensors (Switzerland). 2019 ; Vol. 19, No. 21.
@article{c3b5992dffe3447082dd7f9e69e047a3,
title = "An evaluation framework for spectral filter array cameras to optimize skin diagnosis",
abstract = "Comparing and selecting an adequate spectral filter array (SFA) camera is application-specific and usually requires extensive prior measurements. An evaluation framework for SFA cameras is proposed and three cameras are tested in the context of skin analysis. The proposed framework does not require application-specific measurements and spectral sensitivities together with the number of bands are the main focus. An optical model of skin is used to generate a specialized training set to improve spectral reconstruction. The quantitative comparison of the cameras is based on reconstruction of measured skin spectra, colorimetric accuracy, and oxygenation level estimation differences. Specific spectral sensitivity shapes influence the results directly and a 9-channel camera performed best regarding the spectral reconstruction metrics. Sensitivities at key wavelengths influence the performance of oxygenation level estimation the strongest. The proposed framework allows to compare spectral filter array cameras and can guide their application-specific development.",
keywords = "Biomedical optics, Image quality, Multispectral imaging, Oxygenation, Reflectance spectroscopy, Spectral filter array, Tissue optics",
author = "Bauer, {Jacob Renzo} and Thomas, {Jean Baptiste} and Hardeberg, {Jon Yngve} and Verdaasdonk, {Rudolf M.}",
year = "2019",
month = "11",
day = "1",
doi = "10.3390/s19214805",
language = "English",
volume = "19",
journal = "Sensors (Switserland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "21",

}

An evaluation framework for spectral filter array cameras to optimize skin diagnosis. / Bauer, Jacob Renzo; Thomas, Jean Baptiste; Hardeberg, Jon Yngve; Verdaasdonk, Rudolf M.

In: Sensors (Switzerland), Vol. 19, No. 21, 4805, 01.11.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - An evaluation framework for spectral filter array cameras to optimize skin diagnosis

AU - Bauer, Jacob Renzo

AU - Thomas, Jean Baptiste

AU - Hardeberg, Jon Yngve

AU - Verdaasdonk, Rudolf M.

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Comparing and selecting an adequate spectral filter array (SFA) camera is application-specific and usually requires extensive prior measurements. An evaluation framework for SFA cameras is proposed and three cameras are tested in the context of skin analysis. The proposed framework does not require application-specific measurements and spectral sensitivities together with the number of bands are the main focus. An optical model of skin is used to generate a specialized training set to improve spectral reconstruction. The quantitative comparison of the cameras is based on reconstruction of measured skin spectra, colorimetric accuracy, and oxygenation level estimation differences. Specific spectral sensitivity shapes influence the results directly and a 9-channel camera performed best regarding the spectral reconstruction metrics. Sensitivities at key wavelengths influence the performance of oxygenation level estimation the strongest. The proposed framework allows to compare spectral filter array cameras and can guide their application-specific development.

AB - Comparing and selecting an adequate spectral filter array (SFA) camera is application-specific and usually requires extensive prior measurements. An evaluation framework for SFA cameras is proposed and three cameras are tested in the context of skin analysis. The proposed framework does not require application-specific measurements and spectral sensitivities together with the number of bands are the main focus. An optical model of skin is used to generate a specialized training set to improve spectral reconstruction. The quantitative comparison of the cameras is based on reconstruction of measured skin spectra, colorimetric accuracy, and oxygenation level estimation differences. Specific spectral sensitivity shapes influence the results directly and a 9-channel camera performed best regarding the spectral reconstruction metrics. Sensitivities at key wavelengths influence the performance of oxygenation level estimation the strongest. The proposed framework allows to compare spectral filter array cameras and can guide their application-specific development.

KW - Biomedical optics

KW - Image quality

KW - Multispectral imaging

KW - Oxygenation

KW - Reflectance spectroscopy

KW - Spectral filter array

KW - Tissue optics

U2 - 10.3390/s19214805

DO - 10.3390/s19214805

M3 - Article

VL - 19

JO - Sensors (Switserland)

JF - Sensors (Switserland)

SN - 1424-8220

IS - 21

M1 - 4805

ER -