Hierarchical representation of reference database for an on-line chinese

Abstract

A hierarchical database system for on-line Chinese character recognition is disclosed. The hierarchical database system comprises: (1) the database of character description; (b) the database of stroke correspondence rules of components; (3) the database of character structures; (4) the database of standard component patterns; and (5) the database of spatial relationships between strokes of components. The database of character description stores the rule code(s) of the constituent component(s) and the character structure for all the characters included in the vocabulary. The database of stroke correspondence rules of components stores stroke correspondence rules for all the components denoted by the above mentioned rule codes. The database of character structure stores the synthesis rules of character patterns, the decomposition rules of character structures, and the spatial relationships between components, for all the 208 character structures utilized in a preferred embodiment. The database of standard component patterns stores the coordinates of extreme points of line segments constituting the standard patterns of components. And the database of spatial relationships between strokes of components stores the spatial relationships between strokes of each component. When an input script is matched against a template character, the input script is decomposed into constituent component(s) according to the decomposition rule of that character described as a rule code (stored in the database of character description). Then, the stroke correspondence rules are retrieved from the database of stroke correspondence rules of components via the rule code(s) of that template character. After the matching is completed at the stroke level, the character distance is computed using the database of spatial relationships between strokes of components and the character pattern, which can be synthesized using the database of standard component patterns and the database of character structures. The present invention also discloses a method of finding the best decomposition rule of components for each character, by which various 'geometric features' of strokes and possible decomposition sequences are taken into consideration to thereby derive the best rule for each character for minimizing the number of erroneously decomposed strokes.