Abstract: An apparatus for recognizing shapes characterized by a stroke grouper receptive to a plurality of strokes formed on a screen of a pen-based computer system; a shape recognition engine receptive to a stroke group produced by the stroke grouper; and a knowledge base coupled to the shape recognition engine, where the knowledge base includes, at a minimum, knowledge concerning closed polygons and closed curves. Preferably, the closed curves of the knowledge base include both circles and ellipses. A method for recognizing digitized shapes in a computer system includes the steps of receiving at least one user-initiated stroke; grouping the user initiated stroke with related strokes to form a stroke group; and analyzing the stroke group to make a best-guess shape represented by the stroke group. Preferably, the method also looks for other shapes which are related to the best-guess shape and modifying at least one of the location, size, or shape of the best-guess shape to conform with the other shapes.

Abstract: A technique for analyzing and interpreting user inputs to a computer, such as strokes, key depressions, or voice signals to a hand-held, pen-based computer system. Inputs to the system are received at a user interface, such as a dual function display/input screen from users in the form of pen strokes or gestures. A database stores the input data strokes and hypotheses regarding possible interpretations of the strokes. Recognition of the input strokes and recognition of higher level combinations of strokes (forming characters and words, etc.) is performed using recognizers, or recognition domains, each of which performs a particular recognition task. A controller is provided for controlling the hypotheses database and for scheduling the recognition tasks in the recognition domains. Arbitration resolves conflicts among competing hypotheses associated with each interpretation. The recognition domains, or recognizers generate two or more competing interpretations for the same input.

Abstract: An apparatus for recognizing shapes characterized by a stroke grouper receptive to a plurality of strokes formed on a screen of a pen-based computer system; a shape recognition engine receptive to a stroke group produced by the stroke grouper; and a knowledge base coupled to the shape recognition engine, where the knowledge base includes, at a minimum, knowledge concerning closed polygons and closed curves. Preferably, the closed curves of the knowledge base include both circles and ellipses. A method for recognizing digitized shapes in a computer system includes the steps of receiving at least one user-initiated stroke; grouping the user-initiated stroke with related strokes to form a stroke group; and analyzing the stroke group to make a best-guess shape represented by the stroke group. Preferably, the method also looks for other shapes which are related to the best-guess shape and modifying at least one of the location, size, or shape of the best-guess shape to conform with the other shapes.

Abstract: A method for defining and identifying valid patterns for used in a pattern recognition system. The method is particularly well suited for defining and recognizing patterns comprised of subpatterns which have multi-dimensional relationships. The definition portion is embodied in a constrained attribute grammar. The constrained attribute grammar includes nonterminal, keyword and non-keyword symbols, attribute definitions corresponding to each symbol, a set of production rules, and a relevance measure for each of the key symbols. Each of the symbols represents a subpattern. The production rules includes syntactic, semantic, constraints and action portions. It is the production rules which define the dimensional relationships between the various subpatterns. An instantiation of a constrained attribute grammar is called a language. The verification portion is comprised of a parsing scheme that determines validity of a pattern.