Please use this identifier to cite or link to this item:
https://hdl.handle.net/2445/122953
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Philipsen, Mark Philip | - |
dc.contributor.author | Velling Dueholm, Jacob | - |
dc.contributor.author | Jørgensen, Anders | - |
dc.contributor.author | Escalera Guerrero, Sergio | - |
dc.contributor.author | Moeslund, Thomas Baltzer | - |
dc.date.accessioned | 2018-06-14T11:46:52Z | - |
dc.date.available | 2018-06-14T11:46:52Z | - |
dc.date.issued | 2018-01-03 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.uri | https://hdl.handle.net/2445/122953 | - |
dc.description.abstract | 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 78.11% is achieved across the four classes of organs by using features derived from 2D, 3D and a CNN, compared to 74.28% using only basic 2D image features. | - |
dc.format.extent | 15 p. | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | - |
dc.publisher | MDPI | - |
dc.relation.isformatof | Reproducció del document publicat a: https://doi.org/10.3390/s18010117 | - |
dc.relation.ispartof | Sensors, 2018, vol. 18(1), num. 117 | - |
dc.relation.uri | https://doi.org/10.3390/s18010117 | - |
dc.rights | cc-by (c) Philipsen, Mark Philip et al., 2018 | - |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es | - |
dc.source | Articles publicats en revistes (Matemàtiques i Informàtica) | - |
dc.subject.classification | Ocells | - |
dc.subject.classification | Xarxes neuronals (Neurobiologia) | - |
dc.subject.other | Birds | - |
dc.subject.other | Neural networks (Neurobiology) | - |
dc.title | Organ Segmentation in Poultry Viscera Using RGB-D | - |
dc.type | info:eu-repo/semantics/article | - |
dc.type | info:eu-repo/semantics/publishedVersion | - |
dc.identifier.idgrec | 675064 | - |
dc.date.updated | 2018-06-14T11:46:53Z | - |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | - |
dc.identifier.pmid | 29301337 | - |
Appears in Collections: | Articles publicats en revistes (Matemàtiques i Informàtica) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
675064.pdf | 2.55 MB | Adobe PDF | View/Open |
This item is licensed under a
Creative Commons License