New raw material discrimination system based on a spatial optical spectroscopy technique
New raw material discrimination system based on a spatial optical spectroscopy technique
A non-intrusive and non-contact system for real-time detection of spurious elements in raw material processing chains for industrial environments is presented. Observation line spectrographs, based on the visible.near infrared (Vis.NIR) reflectance of the material under study, are obtained using a dual spatial-spectroscopic imaging technique. To attain a representative spectral fingerprint, the large amount of data is compressed using a principal component analysis (PCA) fast algorithm prior to the classification made by a neural network. The technique has been successfully tested on the tobacco industry. However, the technique is not limited to tobacco leaves, but other materials can be discriminated or classified instead.
optical system, non-contact, imaging spectroscopy, neural networks, material classification
605-612
García-Allende, P.B.
b48e1be3-30b3-47e0-a917-3068c773479c
Conde, O.M.
0ec97d1c-778e-487a-b486-3bae32a4bf44
Cubillas, A.M.
333991f8-a83a-4edf-a79a-38ce16a29450
Jáuregui, C.
1fc691e2-b7a2-4344-9f6d-dbc478499e3a
López-Higuera, J.M.
acf3b7bd-9a4e-44b1-b0d9-f8d944dc30d4
15 April 2007
García-Allende, P.B.
b48e1be3-30b3-47e0-a917-3068c773479c
Conde, O.M.
0ec97d1c-778e-487a-b486-3bae32a4bf44
Cubillas, A.M.
333991f8-a83a-4edf-a79a-38ce16a29450
Jáuregui, C.
1fc691e2-b7a2-4344-9f6d-dbc478499e3a
López-Higuera, J.M.
acf3b7bd-9a4e-44b1-b0d9-f8d944dc30d4
García-Allende, P.B., Conde, O.M., Cubillas, A.M., Jáuregui, C. and López-Higuera, J.M.
(2007)
New raw material discrimination system based on a spatial optical spectroscopy technique.
Sensors and Actuators A: Physical, 135 (2), .
(doi:10.1016/j.sna.2006.08.024).
Abstract
A non-intrusive and non-contact system for real-time detection of spurious elements in raw material processing chains for industrial environments is presented. Observation line spectrographs, based on the visible.near infrared (Vis.NIR) reflectance of the material under study, are obtained using a dual spatial-spectroscopic imaging technique. To attain a representative spectral fingerprint, the large amount of data is compressed using a principal component analysis (PCA) fast algorithm prior to the classification made by a neural network. The technique has been successfully tested on the tobacco industry. However, the technique is not limited to tobacco leaves, but other materials can be discriminated or classified instead.
This record has no associated files available for download.
More information
Published date: 15 April 2007
Keywords:
optical system, non-contact, imaging spectroscopy, neural networks, material classification
Identifiers
Local EPrints ID: 49792
URI: http://eprints.soton.ac.uk/id/eprint/49792
ISSN: 0924-4247
PURE UUID: 0e20018d-6497-4b76-835a-32364e645718
Catalogue record
Date deposited: 03 Dec 2007
Last modified: 15 Mar 2024 09:59
Export record
Altmetrics
Contributors
Author:
P.B. García-Allende
Author:
O.M. Conde
Author:
A.M. Cubillas
Author:
C. Jáuregui
Author:
J.M. López-Higuera
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics