An explorative study on pork loin recognition

Anders Boesen Lindbo Larsen, Marchen Sonja Hviid, Rasmus Larsen, Anders Lindbjerg Dahl

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

254 Downloads (Pure)

Abstract

Bag-of-words (BoW) image description has shown good performance for a large variety of image recognition scenarios. We investigate approaches to alleviating a standard BoW image description pipeline representations for the specific task of recognizing pork loins. Specifically, we extend the BoW description to include depth maps, perform non-rigid image registration to align the images, and apply PCA dimensionality reduction on the BoW descriptors. Our results show that the combination of image registration and PCA yields a more distinctive recognition.
Original languageEnglish
Title of host publicationWorkshop on Farm Animal and Food Quality Imaging 2013 : Espoo, Finland, June 17, 2013, Proceedings
Place of PublicationKgs. Lyngby
PublisherTechnical University of Denmark
Publication date2013
Pages49-54
Publication statusPublished - 2013
EventWorkshop on Farm Animal and Food Quality Imaging 2013 - Espoo, Finland
Duration: 17 Jun 201317 Jun 2013
http://www2.imm.dtu.dk/projects/WFAFQI/

Workshop

WorkshopWorkshop on Farm Animal and Food Quality Imaging 2013
CountryFinland
CityEspoo
Period17/06/201317/06/2013
Internet address
SeriesDTU Compute-Technical Report-2013
Number12
ISSN1601-2321

Cite this

Larsen, A. B. L., Hviid, M. S., Larsen, R., & Dahl, A. L. (2013). An explorative study on pork loin recognition. In Workshop on Farm Animal and Food Quality Imaging 2013: Espoo, Finland, June 17, 2013, Proceedings (pp. 49-54). Technical University of Denmark. DTU Compute-Technical Report-2013, No. 12