Logo des Repositoriums
 
Konferenzbeitrag
Full Review

Hyperspectral band selection using segmented autoencoders for visual quality assessment of food products

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2025

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

In the food industry, natural products that fail to meet quality standards must be removed during processing. To automate this resource-intensive and error-prone process, this work presents a system for AI-supported quality detection of natural products based on hyperspectral images. The implemented system consists of three components: background filter, dimension reduction using autoencoders, and CNN classifier for quality assessment. By training multiple autoencoders for different spectral segments, the proposed architecture can extract the essential spectral information from a given input image, selecting the most informative spectral bands. The system was evaluated on datasets containing chicken legs and potatoes, recorded by a hyperspectral sensor with 224 spectral bands. The results show that the system enables efficient processing of relatively large hyperspectral datasets. Furthermore, the dimension reduction carried out is suitable for the robust classification of defective natural products.

Beschreibung

Schwarze, Jan-Philipp; Herrmann, Lena; Igelbrink, Felix; Hertzberg, Joachim (2025): Hyperspectral band selection using segmented autoencoders for visual quality assessment of food products. 45. GIL-Jahrestagung, Digitale Infrastrukturen für eine nachhaltige Land-, Forst- und Ernährungswirtschaft. DOI: 10.18420/giljt2025_46. Bonn: Gesellschaft für Informatik e.V.. PISSN: 2944-7682. EISSN: 2944-7682. ISBN: 978-3-88579-802-6. pp. 381-386. Wieselburg, Austria. 25/26. Februar 2025

Zitierform

Tags