Handwriting and character recognition system
First Claim
1. A system for encoding and recognizing an oriental language character which has N character strokes drawn in a generally accepted predetermined sequence, comprising:
- a direction code and means therefor to be used for direction coding a first character stroke based on the direction of travel of said stroke relative to said stroke'"'"'s starting point, to give said stroke a two-digit direction code comprising first and second types of coding symbols, said direction code and means therefor being used to obtain for each of said N character strokes a two-digit direction code consisting of at least one coding symbol;
a position code and means therefor to be used for position coding the location of the starting point of a subsequent character stroke relative to the location of the ending point of the stroke immediately previous thereto, and wherein said starting point is not constrained to coincide with said ending point, to give said subsequent character stroke a two-digit position code comprising first and second types of coding symbols, said position code and means therefor being used to obtain for each of said N character strokes except the first character stroke a two-digit direction code consisting of at least one coding symbol;
means for accumulating a first string of 4N-2 digits of coding after all said N character strokes are encoded in said predetermined sequence;
storing means for storing said first string of 4N-2 digits;
means for receiving and encoding a hand written oriental language character intended to have N character strokes using said direction code and said position code to produce a new string of coding digits; and
means for comparing said new string with said first string, whereby a handwritten character is recognized when a matching exists between said new string and said first string, and wherein said first string is stored in said storing means when a match does not exist.
0 Assignments
0 Petitions
Accused Products
Abstract
A method and system for multistroked oriental-language character-recognition by codifying sequential character strokes, uses a direction code (using two digits and representing four directions) for each stroke'"'"'s travel direction, and a position code (using two digits and representing four positions) for each stroke'"'"'s relative position of its starting point relative to the ending point of its previous stroke. Strokes which might have more than one direction at different instants of handwriting are codified by substituting one or two digits in their direction code with one or two replacement digits, for e.g., `x`. Similarly, strokes which might have more than one relative position at different instants of handwriting are codified by substituting one or two digits in their position code with one or two replacement digits, for e.g., `x`. A code, for a character, which consists of a sequence of the direction code and the relative position code is called a DXWC. A database which consists of DXWCs can be established by training the computer system using the described method for a big set of characters. A new particular DXWC (called NewC), which may not have any replacement code symbols because of having only a single sample, can be compared with any existing DXWC (called OldC) in the database to achieve a recognition of a new handwritten character. OldCs which might have an `x` type codes symbols or digits are compared ignoring the `x` digits.
44 Citations
7 Claims
-
1. A system for encoding and recognizing an oriental language character which has N character strokes drawn in a generally accepted predetermined sequence, comprising:
-
a direction code and means therefor to be used for direction coding a first character stroke based on the direction of travel of said stroke relative to said stroke'"'"'s starting point, to give said stroke a two-digit direction code comprising first and second types of coding symbols, said direction code and means therefor being used to obtain for each of said N character strokes a two-digit direction code consisting of at least one coding symbol; a position code and means therefor to be used for position coding the location of the starting point of a subsequent character stroke relative to the location of the ending point of the stroke immediately previous thereto, and wherein said starting point is not constrained to coincide with said ending point, to give said subsequent character stroke a two-digit position code comprising first and second types of coding symbols, said position code and means therefor being used to obtain for each of said N character strokes except the first character stroke a two-digit direction code consisting of at least one coding symbol; means for accumulating a first string of 4N-2 digits of coding after all said N character strokes are encoded in said predetermined sequence; storing means for storing said first string of 4N-2 digits; means for receiving and encoding a hand written oriental language character intended to have N character strokes using said direction code and said position code to produce a new string of coding digits; and means for comparing said new string with said first string, whereby a handwritten character is recognized when a matching exists between said new string and said first string, and wherein said first string is stored in said storing means when a match does not exist. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
Specification