Quality control of the yarns is a fundamental aspect for the textile industry. In particular, in the last two decades there have been several attempts of defining an automatic classifier able to evaluate the composition of animal yarns (e.g. wool and cashmere). A promising approach is based on the morphological analysis of the individual fibers composing the yarn, whose images are acquired by high resolution electron microscope, using a combination of image processing techniques, neural networks and advanced statistical tools.