%0 Journal Article
%T Organ Segmentation in Poultry Viscera Using RGB-D
%A Mark Philip Philipsen
%A Jacob Velling Dueholm
%A Anders Jorgensen
%A Sergio Escalera
%A Thomas B. Moeslund
%J Sensors
%D 2018
%V 18
%N 1
%F Mark Philip Philipsen2018
%O HUPBA; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3072), last updated on Thu, 17 Jan 2019 13:38:00 +0100
%X 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.
%K semantic segmentation
%K RGB-D
%K random forest
%K conditional random field
%K 2D
%K 3D
%K CNN
%U http://dx.doi.org/10.3390/s18010117
%P 117