Data from Mri and Computer Vision Techniques

This paper aims to predict quality features of Iberian hams by using non-destructive methods of analysis and data mining. Iberian hams were analyzed by Magnetic Resonance Imaging (MRI) and Computer Vision Techniques (CVT) throughout their ripening process and physico-chemical parameters from them were also measured. The obtained data were used to create an initial database. Deductive techniques of data mining (multiple linear regression) were used to estimate new data, allowing the insertion of new records in the database. Predictive techniques of data mining were applied (multiple linear regression) on MRI-CVT data, achieving prediction equations of weight, moisture and lipid content. Finally, data from prediction equations were compared to data determined by physical-chemical analysis, obtaining high correlation coefficients in most cases. Therefore, data mining, MRI and CVT are suitable tools to estimate quality traits of Iberian hams. This would improve the control of the ham processing in a non-destructive way.