An explorative study on pork loin recognition

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

An explorative study on pork loin recognition

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

Danish Meat Research Institute
Technical University of Denmark

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

467 Downloads (Orbit)

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 language	English
Title of host publication	Workshop on Farm Animal and Food Quality Imaging 2013 : Espoo, Finland, June 17, 2013, Proceedings
Place of Publication	Kgs. Lyngby
Publisher	Technical University of Denmark
Publication date	2013
Pages	49-54
Publication status	Published - 2013
Event	Workshop on Farm Animal and Food Quality Imaging 2013 - Espoo, Finland Duration: 17 Jun 2013 → 17 Jun 2013 http://www2.imm.dtu.dk/projects/WFAFQI/

Workshop

Workshop	Workshop on Farm Animal and Food Quality Imaging 2013
Country/Territory	Finland
City	Espoo
Period	17/06/2013 → 17/06/2013
Internet address	http://www2.imm.dtu.dk/projects/WFAFQI/

Series	DTU Compute Technical Report-2013
Number	12
ISSN	1601-2321

Access to Document

Pages from tr13 12 Clemmensen L 5Final published version, 3.05 MB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{7f589a28b27148aeaf4c28baabfd7885,

title = "An explorative study on pork loin recognition",

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.",

author = "Larsen, \{Anders Boesen Lindbo\} and Hviid, \{Marchen Sonja\} and Rasmus Larsen and Dahl, \{Anders Lindbjerg\}",

year = "2013",

language = "English",

series = "DTU Compute Technical Report-2013",

publisher = "Technical University of Denmark",

number = "12",

pages = "49--54",

booktitle = "Workshop on Farm Animal and Food Quality Imaging 2013",

note = "Workshop on Farm Animal and Food Quality Imaging 2013, WFAFQI ; Conference date: 17-06-2013 Through 17-06-2013",

url = "http://www2.imm.dtu.dk/projects/WFAFQI/",

}

Larsen, ABL, Hviid, MS, Larsen, R & Dahl, AL 2013, An explorative study on pork loin recognition. in Workshop on Farm Animal and Food Quality Imaging 2013: Espoo, Finland, June 17, 2013, Proceedings. Technical University of Denmark, Kgs. Lyngby, DTU Compute Technical Report-2013, no. 12, pp. 49-54, Workshop on Farm Animal and Food Quality Imaging 2013, Espoo, Finland, 17/06/2013.

An explorative study on pork loin recognition. / Larsen, Anders Boesen Lindbo; Hviid, Marchen Sonja; Larsen, Rasmus et al.
Workshop on Farm Animal and Food Quality Imaging 2013: Espoo, Finland, June 17, 2013, Proceedings. Kgs. Lyngby: Technical University of Denmark, 2013. p. 49-54 (DTU Compute Technical Report-2013; No. 12).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - An explorative study on pork loin recognition

AU - Larsen, Anders Boesen Lindbo

AU - Hviid, Marchen Sonja

AU - Larsen, Rasmus

AU - Dahl, Anders Lindbjerg

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

M3 - Article in proceedings

T3 - DTU Compute Technical Report-2013

SP - 49

EP - 54

BT - Workshop on Farm Animal and Food Quality Imaging 2013

PB - Technical University of Denmark

CY - Kgs. Lyngby

T2 - Workshop on Farm Animal and Food Quality Imaging 2013

Y2 - 17 June 2013 through 17 June 2013

ER -

An explorative study on pork loin recognition

Abstract

Workshop

Access to Document

OpenUrl availability

Fingerprint

Cite this