A general model for an optical recognition system capable of simultaneous recognition of patterns at different resolution levels is outlined. The model is based on two hierarchic stages of processing networks and presents interesting analogies with the human visual system. Illustrative applications and preliminary experimental results are also briefly discussed.

A model for spoken dialogue between an operator and a mobile robot in the procedural network formalism is described. The model is used to improve speech recognition by the robot and aid in the design of the robot's language generation component. Some probabilistic language models for understanding dialogue, which may be generally applicable to a variety of systems, are described.>

A general pattern-recognition procedure for application to unconstrained alphanumeric characters is presented. The procedure is designed to allow hierarchical redescription of the input images in terms of significant elements only, and formal developments are given within the framework of elementary phrase-structure grammars. The extraction of the primitives associated with the terminal vocabularies of the grammars is always deterministic, and the productions of the parsers are characterized by a significant degree of topological fidelity. Preliminary experimental results indicate recognition rates comparable to the state of the art, but with a considerable reduction in computing time.>

EMMA (1) is a multiprocessor system designed and built by ELSAG of Genoa, Italy, to solve problems of pattern recognition arising in automatic mail sorting. The resulting architecture is modular, organizable around several levels, and offers a theoretically unlimited possibility of increasing the processor power. EMMA runs under a simple distributed operating system, supplying process communication, synchronization primitives and some diagnostic functions that complement analysis and reconfiguration modules residing in the supervisor.