1 Department of Informatics and Mathematical Modeling, Technical University of Denmark2 Image Analysis and Computer Graphics, Department of Informatics and Mathematical Modeling, Technical University of Denmark3 Department of Photonics Engineering, Technical University of Denmark4 Department of Applied Mathematics and Computer Science, Technical University of Denmark
This thesis presents the development and application of algorithms for the analysis of pig carcasses. Focus is on the simulation and quality estimation of meat products produced in a Danish slaughterhouse. Computed Tomography scans of pig carcasses provide the data used in the application. Image analysis is applied in order to imitate some of the cutting processes found in a slaughterhouse but also to give a quantitative measure of the composition of each carcass. The basis of the algorithms is non-linear image registration. This method finds the anatomical correspondence between a reference carcass and a template carcass. By iteratively comparing the transformed template with the reference a resulting dense deformation field is found. Propagating a set of landmarks from the reference coordinate system onto the template enables the simulation of slaughtering processes. Non-invasively estimating the quality of the slaughtering products provides a very valuable tool for use in the slaughterhouse in the future.