PT Journal
AU Mark Philip Philipsen
   Jacob Velling Dueholm
   Anders Jorgensen
   Sergio Escalera
   Thomas B. Moeslund
TI Organ Segmentation in Poultry Viscera Using RGB-D
SO Sensors
JI SENS
PY 2018
BP 117
VL 18
IS 1
DI 10.3390/s18010117
DE semantic segmentation; RGB-D; random forest; conditional random field; 2D; 3D; CNN
AB 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.
ER