This paper presents an autoassociator neural network for texture feature extraction. Texture features are extracted through the hidden layer of an autoassociator. The Resilient Propagation (RP) algorithm was employed to train the autoassociator with the texture input and output patterns. The performance of the feature extractor was evaluated on Brodatz benchmark database. A detail analysis of the results is included. The results and analysis showed that the autoassociator is capable of extracting texture features better than the other traditional techniques. © 2001 IEEE.