Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis

Gudmundur Einarsson, Janus Nørtoft Jensen, Rasmus Reinhold Paulsen, Hildur Einarsdottir, Bjarne Kjær Ersbøll, Anders Bjorholm Dahl, Lars Bager Christensen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Non-invasive food inspection and quality assurance are becoming viable techniques in food production due to the introduction of fast and accessible multispectral X-ray scanners. However, the novel devices produce massive amount of data and there is a need for fast and accurate algorithms for processing it. We apply a sparse classifier for foreign object detection and segmentation in multispectral X-ray. Using sparse methods makes it possible to potentially use fewer variables than traditional methods and thereby reduce acquisition time, data volume and classification speed. We report our results on two datasets with foreign objects, one set with spring rolls and one with minced meat. Our results indicate that it is possible to limit the amount of data stored to 50% of the original size without affecting classification accuracy of materials used for training. The method has attractive computational properties, which allows for fast classification of items in new images.
Original languageEnglish
Title of host publicationSCIA 2017
Volume10269
PublisherSpringer
Publication date2017
Pages350-361
ISBN (Print)9783319591254
DOIs
Publication statusPublished - 2017
Event20th Scandinavian Conference on Image Analysis - Tromsø, Norway
Duration: 12 Jun 201714 Jun 2017

Conference

Conference20th Scandinavian Conference on Image Analysis
CountryNorway
CityTromsø
Period12/06/201714/06/2017
SeriesLecture Notes in Computer Science
Volume10269
ISSN0302-9743

Keywords

  • Theoretical Computer Science
  • Computer Science (all)
  • Foreign object detection
  • Multispectral
  • Sparse classification
  • X-ray
  • Discriminant analysis
  • Image analysis
  • Object recognition
  • Quality assurance
  • X rays
  • Acquisition time
  • Classification accuracy
  • Computational properties
  • Fast and accurate algorithms
  • Fast classification
  • Multi-spectral
  • Sparse classifiers
  • Object detection

Cite this

Einarsson, G., Jensen, J. N., Paulsen, R. R., Einarsdottir, H., Ersbøll, B. K., Dahl, A. B., & Christensen, L. B. (2017). Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis. In SCIA 2017 (Vol. 10269, pp. 350-361). Springer. Lecture Notes in Computer Science, Vol.. 10269 https://doi.org/10.1007/978-3-319-59126-1_29
Einarsson, Gudmundur ; Jensen, Janus Nørtoft ; Paulsen, Rasmus Reinhold ; Einarsdottir, Hildur ; Ersbøll, Bjarne Kjær ; Dahl, Anders Bjorholm ; Christensen, Lars Bager. / Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis. SCIA 2017. Vol. 10269 Springer, 2017. pp. 350-361 (Lecture Notes in Computer Science, Vol. 10269).
@inproceedings{ac40d145d5fd4c398aadb9841d7a4e34,
title = "Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis",
abstract = "Non-invasive food inspection and quality assurance are becoming viable techniques in food production due to the introduction of fast and accessible multispectral X-ray scanners. However, the novel devices produce massive amount of data and there is a need for fast and accurate algorithms for processing it. We apply a sparse classifier for foreign object detection and segmentation in multispectral X-ray. Using sparse methods makes it possible to potentially use fewer variables than traditional methods and thereby reduce acquisition time, data volume and classification speed. We report our results on two datasets with foreign objects, one set with spring rolls and one with minced meat. Our results indicate that it is possible to limit the amount of data stored to 50{\%} of the original size without affecting classification accuracy of materials used for training. The method has attractive computational properties, which allows for fast classification of items in new images.",
keywords = "Theoretical Computer Science, Computer Science (all), Foreign object detection, Multispectral, Sparse classification, X-ray, Discriminant analysis, Image analysis, Object recognition, Quality assurance, X rays, Acquisition time, Classification accuracy, Computational properties, Fast and accurate algorithms, Fast classification, Multi-spectral, Sparse classifiers, Object detection",
author = "Gudmundur Einarsson and Jensen, {Janus N{\o}rtoft} and Paulsen, {Rasmus Reinhold} and Hildur Einarsdottir and Ersb{\o}ll, {Bjarne Kj{\ae}r} and Dahl, {Anders Bjorholm} and Christensen, {Lars Bager}",
year = "2017",
doi = "10.1007/978-3-319-59126-1_29",
language = "English",
isbn = "9783319591254",
volume = "10269",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "350--361",
booktitle = "SCIA 2017",

}

Einarsson, G, Jensen, JN, Paulsen, RR, Einarsdottir, H, Ersbøll, BK, Dahl, AB & Christensen, LB 2017, Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis. in SCIA 2017. vol. 10269, Springer, Lecture Notes in Computer Science, vol. 10269, pp. 350-361, 20th Scandinavian Conference on Image Analysis, Tromsø, Norway, 12/06/2017. https://doi.org/10.1007/978-3-319-59126-1_29

Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis. / Einarsson, Gudmundur; Jensen, Janus Nørtoft; Paulsen, Rasmus Reinhold; Einarsdottir, Hildur; Ersbøll, Bjarne Kjær; Dahl, Anders Bjorholm; Christensen, Lars Bager.

SCIA 2017. Vol. 10269 Springer, 2017. p. 350-361 (Lecture Notes in Computer Science, Vol. 10269).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis

AU - Einarsson, Gudmundur

AU - Jensen, Janus Nørtoft

AU - Paulsen, Rasmus Reinhold

AU - Einarsdottir, Hildur

AU - Ersbøll, Bjarne Kjær

AU - Dahl, Anders Bjorholm

AU - Christensen, Lars Bager

PY - 2017

Y1 - 2017

N2 - Non-invasive food inspection and quality assurance are becoming viable techniques in food production due to the introduction of fast and accessible multispectral X-ray scanners. However, the novel devices produce massive amount of data and there is a need for fast and accurate algorithms for processing it. We apply a sparse classifier for foreign object detection and segmentation in multispectral X-ray. Using sparse methods makes it possible to potentially use fewer variables than traditional methods and thereby reduce acquisition time, data volume and classification speed. We report our results on two datasets with foreign objects, one set with spring rolls and one with minced meat. Our results indicate that it is possible to limit the amount of data stored to 50% of the original size without affecting classification accuracy of materials used for training. The method has attractive computational properties, which allows for fast classification of items in new images.

AB - Non-invasive food inspection and quality assurance are becoming viable techniques in food production due to the introduction of fast and accessible multispectral X-ray scanners. However, the novel devices produce massive amount of data and there is a need for fast and accurate algorithms for processing it. We apply a sparse classifier for foreign object detection and segmentation in multispectral X-ray. Using sparse methods makes it possible to potentially use fewer variables than traditional methods and thereby reduce acquisition time, data volume and classification speed. We report our results on two datasets with foreign objects, one set with spring rolls and one with minced meat. Our results indicate that it is possible to limit the amount of data stored to 50% of the original size without affecting classification accuracy of materials used for training. The method has attractive computational properties, which allows for fast classification of items in new images.

KW - Theoretical Computer Science

KW - Computer Science (all)

KW - Foreign object detection

KW - Multispectral

KW - Sparse classification

KW - X-ray

KW - Discriminant analysis

KW - Image analysis

KW - Object recognition

KW - Quality assurance

KW - X rays

KW - Acquisition time

KW - Classification accuracy

KW - Computational properties

KW - Fast and accurate algorithms

KW - Fast classification

KW - Multi-spectral

KW - Sparse classifiers

KW - Object detection

U2 - 10.1007/978-3-319-59126-1_29

DO - 10.1007/978-3-319-59126-1_29

M3 - Article in proceedings

SN - 9783319591254

VL - 10269

T3 - Lecture Notes in Computer Science

SP - 350

EP - 361

BT - SCIA 2017

PB - Springer

ER -

Einarsson G, Jensen JN, Paulsen RR, Einarsdottir H, Ersbøll BK, Dahl AB et al. Foreign object detection in multispectral X-ray images of food items using sparse discriminant analysis. In SCIA 2017. Vol. 10269. Springer. 2017. p. 350-361. (Lecture Notes in Computer Science, Vol. 10269). https://doi.org/10.1007/978-3-319-59126-1_29