An essential task in almost any Pattern Recognition System is the extraction of features vectors, which are then used to perform a classification. Depending on the context of this classification, these feature vectors are expected to present invariance under basic transformations such as translations, scaling or rotations. Thus, every problem needs a careful selection of feature variables, which so far is mostly done by hand (i.e. not automatically). Neural networks have been used successfully as classifiers for a long time, but only recently, they have begun to be employed for automatic selection of feature variables. The ASSOM, ASGCS and ASGFC neural models are able to automatically select feature variables (filters) for the segmentation of textures. In this paper three different texture segmentation architectures TEXSOM, TEXGFC and TEXSGFC, which are based on the mentioned neural models, are described.