Geometry Module

The ALISA Geometry Module classifies geometric structures in images by extracting categorical features from the texture class maps generated by the Texture Module. In one mode, the Geometry Module learns to recognize and classify a set of simple “canonical” geometric concepts, such as horizontal, vertical, slanted, curved, intersecting, and the like. Alternatively, the Geometry Module can be used to learn and classify “secular” geometric concepts, such as signatures of different persons, text and graphics in manuscripts (pictured below), different kinds of coins, and different brands of batteries. Unlike artificial neural-networks, very few training exemplars, each presented only once to ALISA, are required to learn each concept.

All Rights Reserved :: Last Updated on September 30, 2005