Contextual Analysis of CT Scanned Pig Carcasses

Allan Lyckegaard, Rasmus Larsen, Lars Bager Christensen, Martin Vester Christensen, Eli V. Olsen

AbstractKnowledge of the weight of tissue types in pig carcasses is generally only available after manual dissection. The use of computed tomography (CT) has demonstrated to be a promising approach to gain knowledge on the lean meat weight (Romvari, 2005), but less effort has been put into gaining knowledge about the weight of other tissue types from CT. Knowing the weight of individual tissue types will directly give access to other measures such as the weight of the carcass and the Lean Meat Percentage (LMP).
Until now, most analyses of CT scans have been based on the Hounsfield spectra that does not consider the spatial context in CT scan. Applying contextual methods from the field of image analysis we hope to make a virtual dissection of pig carcasses.
KeywordsContextual analysis, tissue classification, virtual dissection, computed tomography, weight prediction
TypeConference paper [With referee]
Conference52nd International Congress of Meat Science and Technology (ICoMST),
Year2006    pp. 207-208
PublisherInformatics and Mathematical Modelling, Technical University of Denmark, DTU
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics