Multi-spectral Image Analysis for Astaxanthin Coating Classification

Martin Georg Ljungqvist, Bjarne Kjær Ersbøll, Michael Engelbrecht Nielsen, Stina Frosch

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

279 Downloads (Pure)

Abstract

Industrial quality inspection using image analysis on astaxanthin coating in aquaculture feed pellets is of great importance for automatic production control. In this study multi-spectral image analysis of pellets was performed using LDA, QDA, SNV and PCA on pixel level and mean value of pixels for each pellet. Classication using LDA or QDA on pellet mean or median values showed better results than using the pixel values or PCA.
Original languageEnglish
Title of host publicationScandinavian Workshop on Imaging Food Quality 2011 : Ystad, May 27, 2011 - Proceedings
Number of pages98
Place of PublicationKgs. Lyngby, Denmark
PublisherTechnical University of Denmark
Publication date2011
Pages63-68
Publication statusPublished - 2011
EventScandinavian Workshop on Imaging Food Quality 2011 - Ystad, Sweden
Duration: 27 May 201127 May 2011
http://www2.imm.dtu.dk/projects/SWIFQ/

Workshop

WorkshopScandinavian Workshop on Imaging Food Quality 2011
CountrySweden
CityYstad
Period27/05/201127/05/2011
OtherHeld in conjunction with the Scandinavian Conference on Image Analysis (SCIA 2011)
Internet address
SeriesD T U Compute. Technical Report
Number2011-15
ISSN1601-2321

Keywords

  • Astaxanthin
  • Image analysis
  • Multi-spectral

Cite this

Ljungqvist, M. G., Ersbøll, B. K., Nielsen, M. E., & Frosch, S. (2011). Multi-spectral Image Analysis for Astaxanthin Coating Classification. In Scandinavian Workshop on Imaging Food Quality 2011: Ystad, May 27, 2011 - Proceedings (pp. 63-68). Technical University of Denmark. D T U Compute. Technical Report, No. 2011-15 http://www2.imm.dtu.dk/projects/SWIFQ/