Diagnosis of Broiler Livers by Classifying Image Patches

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

3 Citations (Scopus)

Abstract

The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps with probabilities of the three most common diseases. A Random Forest classifier combines the maps to a single diagnosis. The method classifies 77.6% livers correctly in a problem that is far from trivial.
Original languageEnglish
Title of host publicationImage Analysis : 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I
PublisherSpringer
Publication date19 May 2017
Pages374-385
ISBN (Print)978-3-319-59125-4
ISBN (Electronic)978-3-319-59126-1
DOIs
Publication statusPublished - 19 May 2017
EventScandinavian Conference on Image Analysis - Tromsø, Norway
Duration: 12 Jun 201714 Jun 2017
Conference number: 20
http://scia2017.org

Conference

ConferenceScandinavian Conference on Image Analysis
Number20
CountryNorway
CityTromsø
Period12/06/201714/06/2017
Internet address
SeriesLecture Notes in Computer Science
Volume10269
ISSN0302-9743

Fingerprint

broiler chickens
liver
meat processing plants
computer vision
neural networks
methodology

Cite this

Jørgensen, A., Fagertun, J., & Moeslund, T. B. (2017). Diagnosis of Broiler Livers by Classifying Image Patches. In Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I (pp. 374-385). Springer. Lecture Notes in Computer Science, Vol.. 10269 https://doi.org/10.1007/978-3-319-59126-1_31
Jørgensen, Anders ; Fagertun, Jens ; Moeslund, Thomas B. / Diagnosis of Broiler Livers by Classifying Image Patches. Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I. Springer, 2017. pp. 374-385 (Lecture Notes in Computer Science, Vol. 10269).
@inproceedings{8db249acfbe34b3894ccbaf33488939d,
title = "Diagnosis of Broiler Livers by Classifying Image Patches",
abstract = "The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps with probabilities of the three most common diseases. A Random Forest classifier combines the maps to a single diagnosis. The method classifies 77.6{\%} livers correctly in a problem that is far from trivial.",
author = "Anders J{\o}rgensen and Jens Fagertun and Moeslund, {Thomas B.}",
year = "2017",
month = "5",
day = "19",
doi = "10.1007/978-3-319-59126-1_31",
language = "English",
isbn = "978-3-319-59125-4",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "374--385",
booktitle = "Image Analysis",
address = "Germany",

}

Jørgensen, A, Fagertun, J & Moeslund, TB 2017, Diagnosis of Broiler Livers by Classifying Image Patches. in Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I. Springer, Lecture Notes in Computer Science, vol. 10269, pp. 374-385, Scandinavian Conference on Image Analysis, Tromsø, Norway, 12/06/2017. https://doi.org/10.1007/978-3-319-59126-1_31

Diagnosis of Broiler Livers by Classifying Image Patches. / Jørgensen, Anders; Fagertun, Jens; Moeslund, Thomas B.

Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I. Springer, 2017. p. 374-385 (Lecture Notes in Computer Science, Vol. 10269).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Diagnosis of Broiler Livers by Classifying Image Patches

AU - Jørgensen, Anders

AU - Fagertun, Jens

AU - Moeslund, Thomas B.

PY - 2017/5/19

Y1 - 2017/5/19

N2 - The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps with probabilities of the three most common diseases. A Random Forest classifier combines the maps to a single diagnosis. The method classifies 77.6% livers correctly in a problem that is far from trivial.

AB - The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps with probabilities of the three most common diseases. A Random Forest classifier combines the maps to a single diagnosis. The method classifies 77.6% livers correctly in a problem that is far from trivial.

U2 - 10.1007/978-3-319-59126-1_31

DO - 10.1007/978-3-319-59126-1_31

M3 - Article in proceeding

SN - 978-3-319-59125-4

T3 - Lecture Notes in Computer Science

SP - 374

EP - 385

BT - Image Analysis

PB - Springer

ER -

Jørgensen A, Fagertun J, Moeslund TB. Diagnosis of Broiler Livers by Classifying Image Patches. In Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I. Springer. 2017. p. 374-385. (Lecture Notes in Computer Science, Vol. 10269). https://doi.org/10.1007/978-3-319-59126-1_31