Skin color correction via convolutional neural networks in 3D fringe projection profilometry
Fringe Projection Profilometry (FPP) with Digital Light Projector technology is one of the most reliable 3D sensing techniques for biomedical applications. However, besides the fringe pattern images,often a color texture image is needed for an accurate medical documentation. This image may be acquir...
- Autores:
-
Barrios, Erik
Pineda, Jesus
Romero, Lenny A
Millán, María S
Marrugo, Andrés G.
- Tipo de recurso:
- Fecha de publicación:
- 2021
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12114
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12114
- Palabra clave:
- Color constancy
Convolutional neural network
Image color processing
Machine learning
Skin color correction
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| id |
UTB2_bc022bd1b3cd28422f76b7e23da40f49 |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12114 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| title |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| spellingShingle |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry Color constancy Convolutional neural network Image color processing Machine learning Skin color correction |
| title_short |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| title_full |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| title_fullStr |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| title_full_unstemmed |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| title_sort |
Skin color correction via convolutional neural networks in 3D fringe projection profilometry |
| dc.creator.fl_str_mv |
Barrios, Erik Pineda, Jesus Romero, Lenny A Millán, María S Marrugo, Andrés G. |
| dc.contributor.author.none.fl_str_mv |
Barrios, Erik Pineda, Jesus Romero, Lenny A Millán, María S Marrugo, Andrés G. |
| dc.subject.keywords.spa.fl_str_mv |
Color constancy Convolutional neural network Image color processing Machine learning Skin color correction |
| topic |
Color constancy Convolutional neural network Image color processing Machine learning Skin color correction |
| description |
Fringe Projection Profilometry (FPP) with Digital Light Projector technology is one of the most reliable 3D sensing techniques for biomedical applications. However, besides the fringe pattern images,often a color texture image is needed for an accurate medical documentation. This image may be acquired either by projecting a white image or a black image and relying on ambient light. Color Constancy is essential for a faithful digital record, although the optical properties of biological tissue make color reproducibility challenging. Furthermore, color perception is highly dependent on the illuminant. Here, we describe a deep learning-based method for skin color correction in FPP. We trained a convolutional neural network using a skin tone color palette acquired under different illumination conditions to learn the mapping relationship between the input color image and its counterpart in the sRGB color space. Preliminary experimental results demonstrate the potential for this approach. |
| publishDate |
2021 |
| dc.date.issued.none.fl_str_mv |
2021-09-02 |
| dc.date.accessioned.none.fl_str_mv |
2023-07-18T19:17:34Z |
| dc.date.available.none.fl_str_mv |
2023-07-18T19:17:34Z |
| dc.date.submitted.none.fl_str_mv |
2023-07 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_b1a7d7d4d402bcce |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/draft |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
draft |
| dc.identifier.citation.spa.fl_str_mv |
Barrios, E., Pineda, J., Romero, L.A., Millán, M.S., Marrugo, A.G. Skin color correction via convolutional neural networks in 3D fringe projection profilometry (2021) Proceedings of SPIE - The International Society for Optical Engineering, 11804, art. no. 118041P, . DOI: 10.1117/12.2594331 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12114 |
| dc.identifier.doi.none.fl_str_mv |
10.1117/12.2594331 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
Barrios, E., Pineda, J., Romero, L.A., Millán, M.S., Marrugo, A.G. Skin color correction via convolutional neural networks in 3D fringe projection profilometry (2021) Proceedings of SPIE - The International Society for Optical Engineering, 11804, art. no. 118041P, . DOI: 10.1117/12.2594331 10.1117/12.2594331 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12114 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.cc.*.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.source.spa.fl_str_mv |
Proceedings of SPIE - The International Society for Optical Engineering - Vol. 11804 (2021) |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/1/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/2/license_rdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/3/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/4/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/5/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf.jpg |
| bitstream.checksum.fl_str_mv |
371445ffec1c488df1ca8d8baff9ecf2 4460e5956bc1d1639be9ae6146a50347 e20ad307a1c5f3f25af9304a7a7c86b6 de64508af7ca8531e38f3d1456767488 efa6309ff7a70d54388d2d35aac4b3d0 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021614683029504 |
| spelling |
Barrios, Erikbb277699-e10e-4f85-982c-9a3b98acb515Pineda, Jesusa6827c4e-c14f-4dc1-ba8e-4c5b1cd055ebRomero, Lenny A4e34aa8a-f981-4e1d-ae32-d45acb6abcf9Millán, María S9fe60bec-aad5-4e2e-99bd-db4b5e8f4a1bMarrugo, Andrés G.00746131-f46c-4d8c-9c02-514385d7b36e2023-07-18T19:17:34Z2023-07-18T19:17:34Z2021-09-022023-07Barrios, E., Pineda, J., Romero, L.A., Millán, M.S., Marrugo, A.G. Skin color correction via convolutional neural networks in 3D fringe projection profilometry (2021) Proceedings of SPIE - The International Society for Optical Engineering, 11804, art. no. 118041P, . DOI: 10.1117/12.2594331https://hdl.handle.net/20.500.12585/1211410.1117/12.2594331Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarFringe Projection Profilometry (FPP) with Digital Light Projector technology is one of the most reliable 3D sensing techniques for biomedical applications. However, besides the fringe pattern images,often a color texture image is needed for an accurate medical documentation. This image may be acquired either by projecting a white image or a black image and relying on ambient light. Color Constancy is essential for a faithful digital record, although the optical properties of biological tissue make color reproducibility challenging. Furthermore, color perception is highly dependent on the illuminant. Here, we describe a deep learning-based method for skin color correction in FPP. We trained a convolutional neural network using a skin tone color palette acquired under different illumination conditions to learn the mapping relationship between the input color image and its counterpart in the sRGB color space. Preliminary experimental results demonstrate the potential for this approach.application/pdfenghttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://purl.org/coar/access_right/c_abf2Proceedings of SPIE - The International Society for Optical Engineering - Vol. 11804 (2021)Skin color correction via convolutional neural networks in 3D fringe projection profilometryinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/drafthttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/version/c_b1a7d7d4d402bccehttp://purl.org/coar/resource_type/c_2df8fbb1Color constancyConvolutional neural networkImage color processingMachine learningSkin color correctionCartagena de IndiasMarrugo, A.G., Gao, F., Zhang, S. State-of-the-art active optical techniques for three-dimensional surface metrology: a review [Invited] (2020) Journal of the Optical Society of America A: Optics and Image Science, and Vision, 37 (9), pp. B60-B77. Cited 102 times. https://www.osapublishing.org/abstract.cfm?URI=josaa-37-9-B60 doi: 10.1364/JOSAA.398644Meza, J., Contreras-Ortiz, S.H., Romero, L.A., Marrugo, A.G. Three-dimensional multimodal medical imaging system based on freehand ultrasound and structured light (2021) Optical Engineering, 60 (5), art. no. 054106. Cited 7 times. http://www.spie.org/x867.xml doi: 10.1117/1.OE.60.5.054106Laloš, J., Mrak, M., Pavlovčič, U., Jezeršek, M. Handheld optical system for skin topography measurement using fourier transform profilometry (2015) Strojniski Vestnik/Journal of Mechanical Engineering, 61 (5), pp. 285-291. Cited 4 times. http://en.sv-jme.eu/data/upload/2015/05/01_2015_2424_Lalos_04.pdf doi: 10.5545/sv-jme.2015.2424Pineda, J., Vargas, R., Romero, L.A., Marrugo, J., Meneses, J., Marrugo, A.G. Robust automated reading of the skin prick test via 3D imaging and parametric surface fitting (2019) PLoS ONE, 14 (10), art. no. e0223623. Cited 7 times. https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0223623&type=printable doi: 10.1371/journal.pone.0223623Rey-Barroso, L., Burgos-Fernández, F.J., Ares, M., Royo, S., Puig, S., Malvehy, J., Pellacani, G., (...), Ricart, M.V. Morphological study of skin cancer lesions through a 3D scanner based on fringe projection and machine learning (2019) Biomedical Optics Express, 10 (7), pp. 3404-3409. Cited 6 times. https://www.osapublishing.org/boe/viewmedia.cfm?uri=boe-10-7-3404&seq=0 doi: 10.1364/BOE.10.003404Xu, J., Zhang, S. Status, challenges, and future perspectives of fringe projection profilometry (2020) Optics and Lasers in Engineering, 135, art. no. 106193. Cited 121 times. https://www.journals.elsevier.com/optics-and-lasers-in-engineering doi: 10.1016/j.optlaseng.2020.106193Wannous, H., Treuillet, S., Lucas, Y. Robust tissue classification for reproducible wound assessment in telemedicine environments (2010) Journal of Electronic Imaging, 19 (2), art. no. 023002. Cited 43 times. doi: 10.1117/1.3378149Wannous, H., Lucas, Y., Treuillet, S., Mansouri, A., Voisin, Y. Improving color correction across camera and illumination changes by contextual sample selection (2012) Journal of Electronic Imaging, 21 (2), art. no. 023015. Cited 23 times. http://www.spie.org/x868.xml doi: 10.1117/1.JEI.21.2.023015Tanaka, S., Kakinuma, A., Kamijo, N., Takahashi, H., Tsumura, N. Auto white balance method using a pigmentation separation technique for human skin color (Open Access) (2017) Optical Review, 24 (1), pp. 17-26. Cited 3 times. http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-40109-70-1126859-0,00.html doi: 10.1007/s10043-016-0290-yCorbalán, M., Millán, M.S., Yzuel, M.J. Color measurement in standard CIELAB coordinates using a 3CCD camera: correction for the influence of the light source (2000) Optical Engineering, 39 (6), pp. 1470-1476. Cited 30 times. doi: 10.1117/1.602519Mahmoud, A. (2018) Semantic white balance: Semantic color constancy using convolutional neural network. Cited 15 times. arXiv preprint arXiv:1802.00153Lou, Z., Gevers, T., Hu, N., Lucassen, M. P. Color constancy by deep learning (2015) , pp. 76-1. Cited 67 times. [BMVC]Qian, Y. (2020) Computational color constancy: From pixel to video with a stop at convolutional neural networkBuchsbaum, G. A spatial processor model for object colour perception (Open Access) (1980) Journal of the Franklin Institute, 310 (1), pp. 1-26. Cited 1251 times. doi: 10.1016/0016-0032(80)90058-7Vaezi Joze, H.R., Drew, M.S. White patch gamut mapping colour constancy (Open Access) (2012) Proceedings - International Conference on Image Processing, ICIP, art. no. 6466981, pp. 801-804. Cited 15 times. ISBN: 978-146732533-2 doi: 10.1109/ICIP.2012.6466981Choi, H.-H., Yun, B.-J. Deep learning-based computational color constancy with convoluted mixture of deep experts (CMODe) fusion technique (2020) IEEE Access, 8, pp. 188309-188320. Cited 10 times. http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 doi: 10.1109/ACCESS.2020.3030912Oh, S.W., Kim, S.J. Approaching the computational color constancy as a classification problem through deep learning (2017) Pattern Recognition, 61, pp. 405-416. Cited 75 times. www.elsevier.com/inca/publications/store/3/2/8/ doi: 10.1016/j.patcog.2016.08.013Hu, Y., Wang, B., Lin, S. FC4: Fully convolutional color constancy with confidence-weighted pooling (Open Access) (2017) Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-January, pp. 330-339. Cited 151 times. ISBN: 978-153860457-1 doi: 10.1109/CVPR.2017.43Cooksey, C.C., Allen, D.W., Tsai, B.K. Reference data set of human skin reflectance (Open Access) (2017) Journal of Research of the National Institute of Standards and Technology, 122, art. no. 26. Cited 15 times. https://nvlpubs.nist.gov/nistpubs/jres/122/jres.122.026.pdf doi: 10.6028/jres.122.026Cooksey, C., Allen, D., Tsai, B. Reectance data set and variability study for human skin reectance (2019) Proceedings of the CIE 2019 29th Session Washington, DC (2019-07-01)McCamy, C.S., Marcus, H., Davidson, J.G. COLOR-RENDITION CHART. (Open Access) (1976) J Appl Photogr Eng, 2 (3), pp. 95-99. Cited 382 times.Kingma, D. P., Ba, J. (2014) Adam: A method for stochastic optimization. Cited 51871 times. arXiv preprint arXiv:1412.6980Helgadottir, S., Argun, A., Volpe, G. Digital video microscopy enhanced by deep learning (Open Access) (2019) Optica, 6 (4), pp. 506-513. Cited 42 times. https://www.osapublishing.org/optica/viewmedia.cfm?uri=optica-6-4-506&seq=0 doi: 10.1364/OPTICA.6.000506Midtvedt, B., Helgadottir, S., Argun, A., Midtvedt, D., Volpe, G. (2020) Deeptrack: A comprehensive deep learning framework for digital microscopy. Cited 2 times. https://github.com/softmatterlab/DeepTrack-2.0.gitGaurav, S. (2003) Digital color imaging handbook. Cited 660 times. CRC Presshttp://purl.org/coar/resource_type/c_2df8fbb1ORIGINALSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdfSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdfapplication/pdf142922https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/1/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf371445ffec1c488df1ca8d8baff9ecf2MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/3/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD53TEXTSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdf.txtSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdf.txtExtracted texttext/plain6655https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/4/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf.txtde64508af7ca8531e38f3d1456767488MD54THUMBNAILSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdf.jpgSkin color correction via convolutional neural networks in 3D fringe projection profilometry.pdf.jpgGenerated Thumbnailimage/jpeg8606https://repositorio.utb.edu.co/bitstream/20.500.12585/12114/5/Skin%20color%20correction%20via%20convolutional%20neural%20networks%20in%203D%20fringe%20projection%20profilometry.pdf.jpgefa6309ff7a70d54388d2d35aac4b3d0MD5520.500.12585/12114oai:repositorio.utb.edu.co:20.500.12585/121142023-07-19 00:19:22.157Repositorio Institucional UTBrepositorioutb@utb.edu.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 |