A Data-Driven Approach for Fibres Recognition via Spectrophotometry

Megan Robinson; Saikat Ghosh; Chenyu Du; Parikshit  Goswami; Mauro Vallati

doi:10.5220/0014286800004052

A Data-Driven Approach for Fibres Recognition via Spectrophotometry

Megan Robinson, Saikat Ghosh, Chenyu Du, Parikshit Goswami, Mauro Vallati

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The increasing volume of textile waste presents significant environmental and economic challenges, necessitating the development of efficient automated sorting techniques to support a more effective textile waste recycling. Automated sorting is a notoriously complex task, due to deployment constraints and to the variability of textiles. To advance the work on automated textile sorting, this study investigates the use of data-driven approaches on spectrophotometer-based reflectance measurements for recognising fibres. Spectrophotometry offers significant advantages in terms of operational simplicity and reliability, making it a promising choice for use in textile sorting facilities where environmental conditions are difficult to control. Considering an extensive dataset of specifically acquired pure textile samples, in this work we leverage on AutoML solutions to determine the best architecture to discriminate between cotton and polyethylene terephthalate (PET) fibres.

Original language	English
Title of host publication	Proceedings of the 18th International Conference on Agents and Artificial Intelligence
Subtitle of host publication	Volume 3: ICAART
Editors	Ana Paula Rocha, Mattias Wahde, H. Jaap van den Herik
Publisher	SciTePress
Pages	2507-2514
Number of pages	8
Volume	3
ISBN (Print)	9789897587962
DOIs	https://doi.org/10.5220/0014286800004052
Publication status	Published - 5 Mar 2026
Event	18th International Conference on Agents and Artificial Intelligence - Marbella, Spain Duration: 5 Mar 2026 → 7 Mar 2026 https://icaart.scitevents.org/

Publication series

Name	Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)
Publisher	SciTePress
ISSN (Print)	2184-433X
ISSN (Electronic)	2184-3589

Conference

Conference	18th International Conference on Agents and Artificial Intelligence
Abbreviated title	ICAART 2026
Country/Territory	Spain
City	Marbella
Period	5/03/26 → 7/03/26
Internet address	https://icaart.scitevents.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 12 Responsible Consumption and Production

Access to Document

10.5220/0014286800004052Licence: CC BY-NC-ND

Cite this

Robinson, M., Ghosh, S., Du, C., Goswami, P., & Vallati, M. (2026). A Data-Driven Approach for Fibres Recognition via Spectrophotometry. In A. P. Rocha, M. Wahde, & H. J. van den Herik (Eds.), Proceedings of the 18th International Conference on Agents and Artificial Intelligence: Volume 3: ICAART (Vol. 3, pp. 2507-2514). (Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)). SciTePress. https://doi.org/10.5220/0014286800004052

Robinson, Megan ; Ghosh, Saikat ; Du, Chenyu et al. / A Data-Driven Approach for Fibres Recognition via Spectrophotometry. Proceedings of the 18th International Conference on Agents and Artificial Intelligence: Volume 3: ICAART. editor / Ana Paula Rocha ; Mattias Wahde ; H. Jaap van den Herik. Vol. 3 SciTePress, 2026. pp. 2507-2514 (Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)).

@inproceedings{2c58ce4d01a44ce4a43b51c6909d9428,

title = "A Data-Driven Approach for Fibres Recognition via Spectrophotometry",

abstract = "The increasing volume of textile waste presents significant environmental and economic challenges, necessitating the development of efficient automated sorting techniques to support a more effective textile waste recycling. Automated sorting is a notoriously complex task, due to deployment constraints and to the variability of textiles. To advance the work on automated textile sorting, this study investigates the use of data-driven approaches on spectrophotometer-based reflectance measurements for recognising fibres. Spectrophotometry offers significant advantages in terms of operational simplicity and reliability, making it a promising choice for use in textile sorting facilities where environmental conditions are difficult to control. Considering an extensive dataset of specifically acquired pure textile samples, in this work we leverage on AutoML solutions to determine the best architecture to discriminate between cotton and polyethylene terephthalate (PET) fibres.",

keywords = "Textile Recognition, Machine Learning, Spectrophotometry",

author = "Megan Robinson and Saikat Ghosh and Chenyu Du and Parikshit Goswami and Mauro Vallati",

year = "2026",

month = mar,

day = "5",

doi = "10.5220/0014286800004052",

language = "English",

isbn = "9789897587962",

volume = "3",

series = "Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)",

publisher = "SciTePress",

pages = "2507--2514",

editor = "Rocha, \{Ana Paula\} and Mattias Wahde and \{van den Herik\}, \{H. Jaap\}",

booktitle = "Proceedings of the 18th International Conference on Agents and Artificial Intelligence",

address = "Portugal",

note = "18th International Conference on Agents and Artificial Intelligence, ICAART 2026 ; Conference date: 05-03-2026 Through 07-03-2026",

url = "https://icaart.scitevents.org/",

}

Robinson, M , Ghosh, S , Du, C , Goswami, P & Vallati, M 2026, A Data-Driven Approach for Fibres Recognition via Spectrophotometry. in AP Rocha, M Wahde & HJ van den Herik (eds), Proceedings of the 18th International Conference on Agents and Artificial Intelligence: Volume 3: ICAART. vol. 3, Proceedings of International Conference on Agents and Artificial Intelligence (ICAART), SciTePress, pp. 2507-2514, 18th International Conference on Agents and Artificial Intelligence, Marbella, Spain, 5/03/26. https://doi.org/10.5220/0014286800004052

A Data-Driven Approach for Fibres Recognition via Spectrophotometry. / Robinson, Megan ; Ghosh, Saikat ; Du, Chenyu et al.
Proceedings of the 18th International Conference on Agents and Artificial Intelligence: Volume 3: ICAART. ed. / Ana Paula Rocha; Mattias Wahde; H. Jaap van den Herik. Vol. 3 SciTePress, 2026. p. 2507-2514 (Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Data-Driven Approach for Fibres Recognition via Spectrophotometry

AU - Robinson, Megan

AU - Ghosh, Saikat

AU - Du, Chenyu

AU - Goswami, Parikshit

AU - Vallati, Mauro

PY - 2026/3/5

Y1 - 2026/3/5

N2 - The increasing volume of textile waste presents significant environmental and economic challenges, necessitating the development of efficient automated sorting techniques to support a more effective textile waste recycling. Automated sorting is a notoriously complex task, due to deployment constraints and to the variability of textiles. To advance the work on automated textile sorting, this study investigates the use of data-driven approaches on spectrophotometer-based reflectance measurements for recognising fibres. Spectrophotometry offers significant advantages in terms of operational simplicity and reliability, making it a promising choice for use in textile sorting facilities where environmental conditions are difficult to control. Considering an extensive dataset of specifically acquired pure textile samples, in this work we leverage on AutoML solutions to determine the best architecture to discriminate between cotton and polyethylene terephthalate (PET) fibres.

AB - The increasing volume of textile waste presents significant environmental and economic challenges, necessitating the development of efficient automated sorting techniques to support a more effective textile waste recycling. Automated sorting is a notoriously complex task, due to deployment constraints and to the variability of textiles. To advance the work on automated textile sorting, this study investigates the use of data-driven approaches on spectrophotometer-based reflectance measurements for recognising fibres. Spectrophotometry offers significant advantages in terms of operational simplicity and reliability, making it a promising choice for use in textile sorting facilities where environmental conditions are difficult to control. Considering an extensive dataset of specifically acquired pure textile samples, in this work we leverage on AutoML solutions to determine the best architecture to discriminate between cotton and polyethylene terephthalate (PET) fibres.

KW - Textile Recognition

KW - Machine Learning

KW - Spectrophotometry

UR - https://www.scitepress.org/ProceedingsDetails.aspx?ID=58XSX+TeehI=&t=1

UR - https://www.scopus.com/pages/publications/105041730637

U2 - 10.5220/0014286800004052

DO - 10.5220/0014286800004052

M3 - Conference contribution

SN - 9789897587962

VL - 3

T3 - Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)

SP - 2507

EP - 2514

BT - Proceedings of the 18th International Conference on Agents and Artificial Intelligence

A2 - Rocha, Ana Paula

A2 - Wahde, Mattias

A2 - van den Herik, H. Jaap

PB - SciTePress

T2 - 18th International Conference on Agents and Artificial Intelligence

Y2 - 5 March 2026 through 7 March 2026

ER -

Robinson M , Ghosh S , Du C , Goswami P , Vallati M. A Data-Driven Approach for Fibres Recognition via Spectrophotometry. In Rocha AP, Wahde M, van den Herik HJ, editors, Proceedings of the 18th International Conference on Agents and Artificial Intelligence: Volume 3: ICAART. Vol. 3. SciTePress. 2026. p. 2507-2514. (Proceedings of International Conference on Agents and Artificial Intelligence (ICAART)). doi: 10.5220/0014286800004052

A Data-Driven Approach for Fibres Recognition via Spectrophotometry

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Textile waste refinery for the production of recycled plastic, cellulose and dye

Cite this

A Data-Driven Approach for Fibres Recognition via Spectrophotometry

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

Textile waste refinery for the production of recycled plastic, cellulose and dye

Cite this