Hyperspectral imaging LED and incandescent light source comparison for food quality inspection
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43210%2F21%3A43921619" target="_blank" >RIV/62156489:43210/21:43921619 - isvavai.cz</a>
Alternative codes found
RIV/62156489:43110/21:43921619
Result on the web
<a href="https://mendelnet.cz/media/mnet_2021_full.pdf" target="_blank" >https://mendelnet.cz/media/mnet_2021_full.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hyperspectral imaging LED and incandescent light source comparison for food quality inspection
Original language description
Incandescent light sources are typical lighting types for Vis-NIR hyperspectral imaging. New broadband LED-based lights start to appear as a possible substitute for incandescent light sources due to the development of new LED dye types. Two light sources (Tungsten-halogen lamp and hyperspectral LED Effilux EFFI-Flex-HSI-100-SD-P2) for the Vis-NIR (400-1000 nm) hyperspectral imaging were compared on 15 samples of Gothajsky cooked salami slices. The goal was to compare these two light source technologies (old incandescent and new LED-based) in the matter of image quality. Images were scored using no-reference quality metrics (BRISQUE, NIQE, PIQE). There was a strong correlation between the mean values of the scoring metrics (BRISQUE R=0.9245, NIQE R=0.8933, PIQE R=0.9779). Results show the main advantage of the LED light is no heat stress of the samples resulting in more stable results with less glare. The main disadvantage of LED light was a lower illumination power resulting in higher exposition time needed.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
MendelNet 2021: Proceedings of International PhD Students Conference
ISBN
978-80-7509-821-4
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
424-429
Publisher name
Mendelova univerzita v Brně
Place of publication
Brno
Event location
Brno
Event date
Nov 10, 2021
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—