Patent US5121441A successfully refreshed from Google Patents.
US5121441A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Robust prototype establishment in an on-line handwriting recognition system
Assignee: International Business Machines Corp
•
Filing: 1990-09-21
•
Granted: 1992-06-09
•
Expires: 2010-09-21
Abstract
Abstract For use in a handwriting recognition system a method, and apparatus for accomplishing same, that includes the steps of (a) inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols to be recognized by the system; (b) forming from the inputted strokes a first set (CHR) comprised of one or more symbols; and (c) averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set (AVG) comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared. The method further includes the steps of (d) identifying a symbol or symbols of the second set that corresponds to only a single symbol of the first set; and (e) deleting the identified symbol or symbols from the second set. The method further includes the steps of (f) decomposing into constituent strokes the prototype symbols of the second set; and (g) forming a third set (STK) comprised of the constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Inventors
- 👤 Thomas E. Chefalas
- 👤 Tetsunosuke Fujisaki
- 👤 Joonki Kim
- 👤 Charles C. Tappert
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 19:11
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/32; G06V30/36; G06V30/373; G06F; G06F18/00; G06F18/20; G06F18/28; G06V30/19; G06V30/191; G06V30/1914
Claims Analysis
Total Claims: 28
Claim 1
Independent Claim
127 words
A method of generating a set of prototype symbols for use in a handwriting recognition system, comprising the steps of: inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared; decomposing the prototype symbols of the second set into constituent strokes; and forming a third set comprised of the constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Claim 2
Independent Claim
127 words
A method of generating a set of prototype symbols for use in a handwriting recognition system, comprising the steps of: inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared; decomposing the prototype symbols of the second set into constituent strokes; and forming a third set comprised of the constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Claim 3
Dependent Claim
37 words
A method as set forth in claim 1 wherein the step of forming a third set includes a step of averaging at least one characteristic of similarly formed constituent strokes of the second set of prototype symbols.
Claim 4
Dependent Claim
48 words
A method as set forth in claim 1 wherein the step of decomposing includes the initial steps of: identifying a symbol or symbols of the second set that correspond to a maverick symbol of the first set; and deleting the identified symbol or symbols from the second set.
Claim 5
Dependent Claim
29 words
A method as set forth in claim 1 wherein the step of inputting includes a step of generating strokes by the movement of a stylus relative to a tablet.
Claim 6
Dependent Claim
55 words
A method as set forth in claim 1 wherein the step of inputting includes an initial step of generating a data structure comprised of a plurality of strokes having predetermined shapes for defining a predetermined number of symbols, and wherein the step of inputting further includes a step of providing the data structure for input.
Claim 7
Dependent Claim
49 words
A method as set forth in claim 1 wherein the step of averaging includes a step of globally averaging at least x-axis and y-axis coordinate data of points that make up constituent strokes of all similarly shaped symbols of the first set that also have a same symbol label.
Claim 8
Dependent Claim
53 words
A method as set forth in claim 1 wherein the step of averaging includes a step of incrementally averaging at least x-axis and y-axis coordinate data of points that make up constituent strokes of a single symbol of the first set with a member of the second set having a same symbol label.
Claim 9
Dependent Claim
56 words
A method as set forth in claim 1 wherein the step of averaging includes an initial step of determining if a symbol to be averaged has a shape that is within a predetermined threshold of the shapes of other symbol having a same symbol label, the step of determining being accomplished by an elastic matching technique.
Claim 10
Dependent Claim
29 words
A method as set forth in claim 1 wherein the steps of averaging, decomposing and forming are initiated in response to a command from a user of the system.
Claim 11
Independent Claim
248 words
A method of generating a set of prototype symbols and prototype strokes for use in a handwriting recognition system, comprising the steps of: providing a user of the system with means for interacting with a prototype manager function of the system; responsive to input from the user, inputting a plurality of strokes each of which is a constituent stroke of a system training symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; responsive to a command from the user activating the prototype manager function averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared; responsive to further commands from the user activating the prototype manager function identifying a symbol or symbols of the second set that correspond to a maverick symbol of the first set; displaying to the user the maverick symbol or symbols; and deleting specified ones of the identified symbol or symbols from the second set; and responsive to a further command from the user activating the prototype manager function decomposing the remaining prototype symbols of the second set into constituent strokes; averaging at least one characteristic of similarly formed constituent strokes; and forming a third set comprised of the average constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Claim 12
Independent Claim
248 words
A method of generating a set of prototype symbols and prototype strokes for use in a handwriting recognition system, comprising the steps of: providing a user of the system with means for interacting with a prototype manager function of the system; responsive to input from the user, inputting a plurality of strokes each of which is a constituent stroke of a system training symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; responsive to a command from the user activating the prototype manager function averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared; responsive to further commands from the user activating the prototype manager function identifying a symbol or symbols of the second set that correspond to a maverick symbol of the first set; displaying to the user the maverick symbol or symbols; and deleting specified ones of the identified symbol or symbols from the second set; and responsive to a further command from the user activating the prototype manager function decomposing the remaining prototype symbols of the second set into constituent strokes; averaging at least one characteristic of similarly formed constituent strokes; and forming a third set comprised of the average constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Claim 13
Dependent Claim
39 words
A method as set forth in claim 10 and responsive to a further command from the user activating the prototype manager function for storing at least the second and the third prototype sets for subsequent use by the system.
Claim 14
Dependent Claim
75 words
A method as set forth in claim 10 and responsive to a further command from the user activating the prototype manager function to display to the user any members of the second set having characteristics that are similar to one another to within a predetermined threshold; and, responsive to further input from the user, modifying one of the displayed members of the second set to unequivocally distinguish the two displayed members one from the other.
Claim 15
Dependent Claim
127 words
Handwritten character recognition apparatus comprising: means for inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols selected for training the system; means for forming from the inputted strokes a first set comprised of one or more symbols; means for averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the apparatus, assemblages of input strokes are compared; means for decomposing the prototype symbols of the second set into constituent strokes; and means for forming a third set comprised of the constituent strokes of the second set to which, during the use of the apparatus, input strokes are compared.
Claim 16
Dependent Claim
127 words
Handwritten character recognition apparatus comprising: means for inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols selected for training the system; means for forming from the inputted strokes a first set comprised of one or more symbols; means for averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the apparatus, assemblages of input strokes are compared; means for decomposing the prototype symbols of the second set into constituent strokes; and means for forming a third set comprised of the constituent strokes of the second set to which, during the use of the apparatus, input strokes are compared.
Claim 17
Dependent Claim
35 words
Apparatus as set forth in claim 13 wherein the means for forming a third set includes means for averaging at least one characteristic of similarly formed constituent strokes of the second set of prototype symbols.
Claim 18
Dependent Claim
57 words
Apparatus as set forth in claim 13 wherein the means for decomposing includes: means for identifying a symbol or symbols of the second set that correspond to a maverick symbol of the first set; and means, responsive to an command from a user of the system, for deleting the identified symbol or symbols from the second set.
Claim 19
Dependent Claim
47 words
Apparatus as set forth in claim 13 wherein the means for averaging includes means for globally averaging at least x-axis and y-axis coordinate data of points that make up constituent strokes of all similarly shaped symbols of the first set that also have a same symbol label.
Claim 20
Dependent Claim
51 words
Apparatus as set forth in claim 13 wherein the means for averaging includes means for incrementally averaging at least x-axis and y-axis coordinate data of points that make up constituent strokes of a single symbol of the first set with a member of the second set having a same symbol label.
Claim 21
Dependent Claim
37 words
Apparatus as set forth in claim 13 wherein the averaging means includes means for comparing symbols by an elastic averaging technique to determine if two symbols having a same symbol label are shaped in a similar manner.
Claim 22
Dependent Claim
35 words
Apparatus as set forth in claim 13 wherein the averaging means, the decomposing means and the forming means are all coupled to and responsive to means for inputting commands from a user of the system.
Claim 23
Dependent Claim
29 words
Apparatus as set forth in claim 13 and further including means for storing and retrieving at least the second and the third sets for subsequent use by the apparatus.
Claim 24
Dependent Claim
41 words
Apparatus as set forth in claim 13 wherein the means for inputting is coupled to means for providing data expressive of predetermined symbols comprised of strokes having shapes selected for emphasizing differences between the symbols while de-emphasizing similarities between the symbols.
Claim 25
Independent Claim
91 words
A method of generating a set of prototype symbols for use in a handwriting recognition system, comprising the steps of: inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; and averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared.
Claim 26
Independent Claim
91 words
A method of generating a set of prototype symbols for use in a handwriting recognition system, comprising the steps of: inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols; forming from the inputted strokes a first set comprised of one or more symbols; and averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared.
Claim 27
Dependent Claim
51 words
A method as set forth in claim 22 and further including the steps of: decomposing the prototype symbols of the second set into constituent strokes; and forming a third set comprised of the constituent strokes of the second set to which, during the use of the system, input strokes are compared.
Claim 28
Dependent Claim
37 words
A method as set forth in claim 23 wherein the step of forming a third set includes a step of averaging at least one characteristic of similarly formed constituent strokes of the second set of prototype symbols.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1995-06-09 | 1995-12-09 | 1996-06-09 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1999-06-09 | 1999-12-09 | 2000-06-09 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2003-06-09 | 2003-12-09 | 2004-06-09 | $7700.00 | Window Closed / Lapsed |