About ALISA
Based on collective learning systems theory developed by Professor Peter Bock, a network of adaptive learning cells has been applied to a difficult image processing task: the detection and classification of structures and objects in images. Known as ALISA (Adaptive Learning Image and Signal Analysis), this image and signal processing engine was first designed at the Research Institute for Applied Knowledge Processing in Ulm, Germany, and then extended and refined at The George Washington University in Washington DC with major funding from the German industrial firm Robert Bosch over the last 15 years. Currently, Project ALISA is hosted at the George Washington University in Washington DC, funded by the Defense Threat Reduction Agency (DoD) at about $300,000 annually. The design of the parallel-processing ALISA system was motivated by the multi-path cortical-column architecture and adaptive functions of the primate visual cortex. The current ALISA system uses four modules: the Texture Module, the Geometry Module, the Vector Module, and the Shape Module. Two additional modules are currently under development: the Component Module for the analysis of the internal structure of objects, and the Lexical Module for the language-independent analysis of textual information.
The long-term research focuese upon the extension of ALISA to successively higher adaptive levels of cognition: textures -> geometries -> shapes -> components -> objects -> scenes, using feedback from the higher to lower levels for disambiguation and the assignment of symbolic value. In the meantime, the texture, geometry, and shape class maps generated by ALISA can provide symbolic information for classical rule-based systems to classify more complex concepts.
Click here to download a PowerPoint presentation about the ALISA classifier (17.1 MB).
All Rights Reserved :: Last Updated on November 1, 2007