Textiles made from noble animal hair are very expensive and often affected by counterfeiting, as there is no method so far to identify animal hair objectively and flawlessly even after chemical treatments. Therefore, a standard method for counterfeit-resistant identification of animal hair based on automated analysis of light or scanning electron microscopic (SEM) images will be developed. A toolbox extracts, based on existing animal hair definitions, the parameters for animal hair type identification and tests their suitability using machine learning. This approach is contrasted with a Deep Learning method that does not require the explicit extraction of the mentioned features from the images. Users are medium-sized companies in the field of yarn, knit and fabric manufacturing, finishing, ready-to-wear and retail involved in high-value and -priced wool and cashmere textiles from the fashion, apparel and home textile sectors. Successful, counterfeit-resistant animal hair identification will uncover counterfeits and thus make them rarer in the future. The associated loss of image and downstream costs when counterfeits are only detected retrospectively can be avoided. The project is being carried out in close cooperation with associations and companies from these industries.