Generalized contextual recognition of hand-printed documents using semantic trees with lazy evaluation

Abstract

Describes a new general-purpose contextual architecture which provides a unified framework for efficiently combining all types and levels of context in hand-print recognition applications. The architecture has been designed and built as a C++ class library and utilised within an initial demonstrator which implements full contextual constraints for a combination of postcode and corresponding postal address. Preliminary evaluation of the demonstrator suggests the system has the potential to achieve genuinely remarkable performance compared with previous context systems: its memory requirements are an order of magnitude less than an equivalent trie-based dictionary; its search speed is at least an order of magnitude faster than the trie, and actually gets faster as the dictionary size increases(!); and its error rate is virtually zero if suitable contextual constraints can be applied. Using this architecture, it appears to be possible to build real-time solutions to large-scale heterogeneous contextual problems.