A self-organizing neural system for learning to recognize textured scenes

A self-organizing ARTEX model is developed to categorize and classify textu red image regions. ARTEX specializes the FACADE model of how the visual cor tex sees, and the ART model of how temporal and prefrontal cortices interac t with the hippocampal system to learn visual recognition categories and th eir names. FACADE processing generates a vector of boundary and surface pro perties, notably texture and brightness properties, by utilizing multi-scal e filtering, competition, and diffusive filling-in. Its context-sensitive l ocal measures of textured scenes can be used to recognize scenic properties that gradually change across space, as well as abrupt texture boundaries. ART incrementally learns recognition categories that classify FACADE output vectors, class names of these categories, and their probabilities. Top-dow n expectations within ART encode learned prototypes that pay attention to e xpected visual features. When novel visual information creates a poor match with the best existing category prototype, a memory search selects a new c ategory with which classify the novel data. ARTEX is compared with psychoph ysical data, and is bench marked on classification of natural textures and synthetic aperture radar images. It outperforms state-of-the-art systems th at use rule-based, backpropagation, and K-nearest neighbor classifiers. (C) 1999 Elsevier Science Ltd. All rights reserved.