Organ Segmentation in Poultry Viscera Using RGB-D
Philipsen, Mark Philip (Media Technology, Aalborg University)
Dueholm, Jacob Velling (Media Technology, Aalborg University)
Jørgensen, Anders (IHFood, Copenhagen)
Escalera, Sergio (Centre de Visió per Computador (Bellaterra, Catalunya))
Moeslund, Thomas Baltzer (Media Technology, Aalborg University)
Universitat Autònoma de Barcelona

Fecha:	2018
Resumen:	We present a pattern recognition framework for semantic segmentation of visual structures, that is, multi-class labelling at pixel level, and apply it to the task of segmenting organs in the eviscerated viscera from slaughtered poultry in RGB-D images. This is a step towards replacing the current strenuous manual inspection at poultry processing plants. Features are extracted from feature maps such as activation maps from a convolutional neural network (CNN). A random forest classifier assigns class probabilities, which are further refined by utilizing context in a conditional random field. The presented method is compatible with both 2D and 3D features, which allows us to explore the value of adding 3D and CNN-derived features. The dataset consists of 604 RGB-D images showing 151 unique sets of eviscerated viscera from four different perspectives. A mean Jaccard index of is achieved across the four classes of organs by using features derived from 2D, 3D and a CNN, compared to using only basic 2D image features.
Ayudas:	Ministerio de Economía y Competitividad TIN2016-74946-P
Nota:	Altres ajuts: The authors would like to thank the Green Development and Demonstration Programme (GUDP) of the Danish Ministry of Food for financial support and Danpo for providing access to their facilities. This work has been partially supported by [...] and CERCA Programme/Generalitat de Catalunya.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Semantic segmentation ; RGB-D ; Random forest ; Conditional random field ; 2D ; 3D ; CNN
Publicado en:	Sensors (Basel, Switzerland), Vol. 18 (january 2018) , ISSN 1424-8220

DOI: 10.3390/s18010117
PMID: 29301337

15 p, 2.5 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados