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