Diagnosis of Broiler Livers by Classifying Image Patches

Anders Jørgensen; Jens Fagertun; Thomas B. Moeslund

doi:10.1007/978-3-319-59126-1_31

Diagnosis of Broiler Livers by Classifying Image Patches

Anders Jørgensen, Jens Fagertun, Thomas B. Moeslund

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

6 Citationer (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.

Originalsprog	Engelsk
Titel	Image Analysis : 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I
Forlag	Springer
Publikationsdato	19 maj 2017
Sider	374-385
ISBN (Trykt)	978-3-319-59125-4
ISBN (Elektronisk)	978-3-319-59126-1
DOI	https://doi.org/10.1007/978-3-319-59126-1_31
Status	Udgivet - 19 maj 2017
Begivenhed	Scandinavian Conference on Image Analysis, SCIA - Tromsø, Norge Varighed: 12 jun. 2017 → 14 jun. 2017 Konferencens nummer: 20 http://scia2017.org

Konference

Konference	Scandinavian Conference on Image Analysis, SCIA
Nummer	20
Land/Område	Norge
By	Tromsø
Periode	12/06/2017 → 14/06/2017
Internetadresse	http://scia2017.org

Navn	Lecture Notes in Computer Science
Vol/bind	10269
ISSN	0302-9743

Adgang til dokumentet

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

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@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 = may,

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",

note = "Scandinavian Conference on Image Analysis, SCIA ; Conference date: 12-06-2017 Through 14-06-2017",

url = "http://scia2017.org",

}

Jørgensen, A, Fagertun, J & Moeslund, TB 2017, Diagnosis of Broiler Livers by Classifying Image Patches. i Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I. Springer, Lecture Notes in Computer Science, bind 10269, s. 374-385, Scandinavian Conference on Image Analysis, SCIA, Tromsø, Norge, 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. s. 374-385 (Lecture Notes in Computer Science, Bind 10269).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Diagnosis of Broiler Livers by Classifying Image Patches

AU - Jørgensen, Anders

AU - Fagertun, Jens

AU - Moeslund, Thomas B.

N1 - Conference code: 20

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

T2 - Scandinavian Conference on Image Analysis

Y2 - 12 June 2017 through 14 June 2017

ER -

Diagnosis of Broiler Livers by Classifying Image Patches

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater