Evaluation of scanning electron microscopy images of a model dressing using image feature extraction techniques and principal component analysis

Twelve dressing systems made by varying protein type, oil level, CaCl2, NaC l, and sucrose, were examined using scanning electron microscopy. Images fr om the 12 systems were quantitatively analysed using methods of feature ext raction. These methods were based on vectorisations of the images followed by principal component analysis on the extracted vectors. These techniques were used to examine the reproducibility of the acquired images as well as to relate the images to theologic and sensory texture parameters. Two featu re extraction methods were used: the angle measure technique (AMT) and the absolute difference method (ABDF). The ABDF method used fewer principal com ponents to extract information from images relevant to the complex modulus/ sensory viscosity of the system, but the information seemed equally well pr eserved by the two-feature extraction methods. The AMT was more efficient i n classifying the images with respect to protein type. A fair correlation b etween images and complex modulus was obtained (R=0.73). It is suggested th at a better correlation might be obtained by adding more systems, increasin g the number of areas imaged for each system as well as avoiding systems of low viscosity.