US5729629A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Handwritten symbol recognizer
Assignee: Microsoft Technology Licensing LLC
•
Filing: 1996-11-18
•
Granted: 1998-03-17
•
Expires: 2016-11-18
Abstract
Abstract A handwritten symbol recognizer adapted to automatically recognize various handwritten symbols including Kanji character is disclosed. The symbol recognizer includes a data processor coupled to a user interface that receives handwritten input symbols from a user and displays reference symbols determined by the symbol recognizer to correspond to the handwritten symbols. The data processor includes a memory unit which temporarily stores coordinate information representing features of the input symbols as received from the user interface. The data processor includes a symbol analyzer that retrieves the coordinate information from the memory unit and translates the coordinate information for each written feature into a feature code representing one of a predetermined number of feature models stored in the memory. The symbol analyzer also creates a geometric representation of the input symbol for comparison with one or more geometric models stored in the memory unit. The data processor also includes a label comparator adapted to compare the feature codes for the input symbol with feature codes of reference symbols stored in the memory unit and to identify the reference symbol or symbols having feature codes that most closely match the feature codes of the input symbol. The data processor also includes a geometric comparator that compares stored geometric models corresponding to the reference symbols most closely matching the input label with the geometric representation of the input symbol. The geometric comparator uses its comparison to identify the reference symbols whose geometric model or models most closely match the geometric representation of the input symbol. The reference symbol that most closely matches the handwritten input symbol, as determined by the label and geometric comparators, is sent to the user interface which displays the reference symbol to the user.
Inventors
- 👤 Xiwei Dai
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:22
CPC Classifications
B; B01; B01D; B01D61/00; B01D61/02; B01D61/10; F; F01; F01L; F01L25/00; F01L25/02; F01L25/04; F01L25/06; F01L25/063; F04; F04B; F04B5/00; F04B9/00; F04B9/08; F04B9/10; F04B9/109; F04B9/111; F04B9/1115; G; G06; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/142; G06V30/1423; G06V30/24; G06V30/248; G06V30/2504; G06V30/32; G06V30/333; G06V30/347; G06V30/36; G06V30/373
Claims Analysis
Total Claims: 70
Claim 1
Independent Claim
297 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having sequential features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the sequential features of the input symbol according to the time sequential order in which the sequential features were written, translates the coordinate information for each written sequential feature into a feature code representing one of a predetermined number of feature models, and produces an input label of feature codes ordered according to the time sequential order in which the features were written, the symbol analyzer also creates a geometric representation of the input symbol, the geometric representation including data representing positions of the features of the input symbol; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a plurality of feature codes in a predetermined order and corresponding to one of the geometric models, each geometric model storing data representing positions of features of a reference symbol represented by the geometric model; a label comparator that compares the input label with the label models without regard for positions of the features represented by the feature codes of the input label and identifies a most closely matching subset of the stored label models by identifying the label model or models that most closely match the input label regardless of the positions of the features represented by the feature codes of the input label; and a geometric comparator that compares only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 2
Dependent Claim
297 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having sequential features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the sequential features of the input symbol according to the time sequential order in which the sequential features were written, translates the coordinate information for each written sequential feature into a feature code representing one of a predetermined number of feature models, and produces an input label of feature codes ordered according to the time sequential order in which the features were written, the symbol analyzer also creates a geometric representation of the input symbol, the geometric representation including data representing positions of the features of the input symbol; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a plurality of feature codes in a predetermined order and corresponding to one of the geometric models, each geometric model storing data representing positions of features of a reference symbol represented by the geometric model; a label comparator that compares the input label with the label models without regard for positions of the features represented by the feature codes of the input label and identifies a most closely matching subset of the stored label models by identifying the label model or models that most closely match the input label regardless of the positions of the features represented by the feature codes of the input label; and a geometric comparator that compares only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 3
Dependent Claim
31 words
The handwriting recognizer of claim 1 wherein the symbol analyzer is adapted to translate the coordinate information for each written feature into a feature code representing one of thirteen feature models.
Claim 4
Dependent Claim
30 words
The handwriting recognizer of claim 1 wherein the symbol analyzer includes means for vectorizing the coordinate information into a time sequence of vector codes representing vector information of the features.
Claim 5
Dependent Claim
19 words
The handwriting recognizer of claim 3 wherein the symbol analyzer includes a filter adapted to smooth anomalous vector codes.
Claim 6
Dependent Claim
26 words
The handwriting recognizer of claim 3 wherein the symbol analyzer includes means for translating a portion of the vector codes into one of the feature codes.
Claim 7
Dependent Claim
37 words
The handwriting recognizer of claim 1 wherein the symbol analyzer includes a hook filter adapted to determine whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook.
Claim 8
Dependent Claim
74 words
The handwriting recognizer of claim 6 wherein the symbol analyzer includes means for vectorizing the coordinate information into a plurality of vector codes representing vector information of the features and wherein the hook filter is adapted to identify an unintended hook if the number of vector codes created for the end portion of the pen stroke is less than a predetermined fraction of the number of vector codes created for the entire pen stroke.
Claim 9
Dependent Claim
41 words
The handwriting recognizer of claim 1 wherein the symbol analyzer includes means for creating the geometric representation of the input symbol by saving a subset of the coordinate points of each feature and discarding the remaining coordinate points of the features.
Claim 10
Dependent Claim
33 words
The handwriting recognizer of claim 8 wherein the subset saved is limited to two coordinate points for each feature with one of the two coordinate points being an end point of the feature.
Claim 11
Dependent Claim
54 words
The handwriting recognizer of claim 1 wherein the label comparator includes: means for rearranging the order of the feature codes of the input label after the geometric representation of the input symbol corresponding to the input label is compared by the geometric comparator and for comparing the rearranged input label to the label models.
Claim 12
Dependent Claim
36 words
The handwriting recognizer of claim 1 wherein the label comparator includes means for comparing the input label only with label models having the same number of feature codes as the input label during a first pass.
Claim 13
Dependent Claim
41 words
The handwriting recognizer of claim 1 wherein the label comparator includes means for identifying a score for each comparison of the input label with one of the label models and means for saving the scores that satisfy a predetermined label threshold.
Claim 14
Dependent Claim
40 words
The handwriting recognizer of claim 1 wherein the geometric comparator includes means for computing a Euclidean vector distance for each geometric model, the Euclidean vector distance representing how closely the geometric model matches the geometric representation of the input symbol.
Claim 15
Dependent Claim
65 words
The handwriting recognizer of claim 13 wherein the geometric representation of the input symbol is limited to two coordinate points for each feature and the means for computing a Euclidean vector distance computes the Euclidean vector distance for a selected geometric model by determining a distance between each of the two coordinates points for each feature and corresponding coordinate points for the selected geometric model.
Claim 16
Dependent Claim
28 words
The handwriting recognizer of claim 13, further including output means for causing to be displayed one of the geometric models whose Euclidean vector distance satisfies a geometric threshold.
Claim 17
Dependent Claim
281 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having sequential features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the sequential features of the input symbol according to the time sequential order in which the sequential features were written, translates the coordinate information for each written sequential feature into a feature code representing one of a predetermined number of feature models, and produces an input label of feature codes ordered according to the time sequential order in which the features were written, the symbol analyzer also creates a geometric representation of the input symbol; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a plurality of feature codes in a predetermined order and corresponding to one of the geometric models; a label comparator that compares the input label with the label models and identifies the label model or models that most closely match the input label, wherein the label comparator includes means for comparing the input label only with label models having the same number of feature codes as the input label during a first pass and wherein the label comparator includes means for comparing the input label with label models having one more or one less feature code than the input label during a second pass; and a geometric comparator that compares the geometric models corresponding to the label models most closely matching the input label with the geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 18
Dependent Claim
281 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having sequential features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the sequential features of the input symbol according to the time sequential order in which the sequential features were written, translates the coordinate information for each written sequential feature into a feature code representing one of a predetermined number of feature models, and produces an input label of feature codes ordered according to the time sequential order in which the features were written, the symbol analyzer also creates a geometric representation of the input symbol; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a plurality of feature codes in a predetermined order and corresponding to one of the geometric models; a label comparator that compares the input label with the label models and identifies the label model or models that most closely match the input label, wherein the label comparator includes means for comparing the input label only with label models having the same number of feature codes as the input label during a first pass and wherein the label comparator includes means for comparing the input label with label models having one more or one less feature code than the input label during a second pass; and a geometric comparator that compares the geometric models corresponding to the label models most closely matching the input label with the geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 19
Dependent Claim
253 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models without regard for positions of the features represented by the feature codes of the input label, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, each geometric model including data representing positions of features of a reference symbol represented by the geometric model; identifying a most closely matching subset of the stored label models by identifying the label model or models most closely matching the input label regardless of the positions of the features represented by the feature codes of the input label; creating a geometric representation of the input symbol, the geometric representation including data representing positions of features of the input symbol; comparing only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 20
Dependent Claim
253 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models without regard for positions of the features represented by the feature codes of the input label, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, each geometric model including data representing positions of features of a reference symbol represented by the geometric model; identifying a most closely matching subset of the stored label models by identifying the label model or models most closely matching the input label regardless of the positions of the features represented by the feature codes of the input label; creating a geometric representation of the input symbol, the geometric representation including data representing positions of features of the input symbol; comparing only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 21
Dependent Claim
28 words
The method of claim 17 wherein the translating step includes translating the coordinate information for each written feature into a feature code representing one of thirteen feature models.
Claim 22
Dependent Claim
27 words
The method of claim 17 wherein the translating step includes vectorizing the coordinate information into a time sequence of vector codes representing vector information of the features.
Claim 23
Dependent Claim
14 words
The method of claim 19 wherein the translating step includes smoothing anomalous vector codes.
Claim 24
Dependent Claim
23 words
The method of claim 19 wherein the translating step includes translating a portion of the vector codes into one of the feature codes.
Claim 25
Dependent Claim
45 words
The method of claim 17 wherein the translating step includes determining whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook and ignoring the end portion if it is determined to be an unintended hook.
Claim 26
Dependent Claim
64 words
The method of claim 22 wherein the determining step includes: vectorizing the coordinate information into a plurality of vector codes representing vector information of the features; and identifying an unintended hook if the number of vector codes created for the end portion of the pen stroke is less than a predetermined fraction of the number of vector codes created for the entire pen stroke.
Claim 27
Dependent Claim
29 words
The method of claim 17 wherein the translating step includes saving a subset of the coordinate points of a feature and discarding the remaining coordinate points of the feature.
Claim 28
Dependent Claim
28 words
The method of claim 24, further including limiting the subset saved to two coordinate points, one of the two coordinate points being an end point of the feature.
Claim 29
Dependent Claim
48 words
The method of claim 17 wherein the translating step includes: rearranging the order of the feature codes of the input label after the input symbol geometric representation corresponding to the input label is compared to the geometric models; and comparing the rearranged input label to the label models.
Claim 30
Dependent Claim
34 words
The method of claim 17 wherein the comparing labels step includes comparing the input label only with label models having the same number of feature codes as the input label during a first pass.
Claim 31
Dependent Claim
37 words
The method of claim 17 wherein the comparing labels step includes identifying a score for each comparison of the input label with one of the label models and saving the scores that satisfy a predetermined label threshold.
Claim 32
Dependent Claim
38 words
The method of claim 17 wherein the geometric comparing step includes computing a Euclidean vector distance for each geometric model, the Euclidean vector distance representing how closely the geometric model matches the geometric representation of the input symbol.
Claim 33
Dependent Claim
63 words
The method of claim 29 wherein the geometric representation created is limited to exactly two coordinate points for each feature and the step of computing a Euclidean vector distance includes computing the Euclidean vector distance for a selected geometric model by determining a distance between each of the two coordinates points for each feature and corresponding coordinate points for the selected geometric model.
Claim 34
Dependent Claim
21 words
The method of claim 30, further including displaying one of the geometric models whose Euclidean vector distance satisfies the geometric threshold.
Claim 35
Dependent Claim
214 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models having the same number of feature codes as the input label during a first pass, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, wherein the comparing labels step includes comparing the input label with label models having one more or one less feature code during a second pass; identifying the label model or models most closely matching the input label; creating a geometric representation of the input symbol; comparing the geometric models corresponding to the most closely matching label models with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 36
Dependent Claim
214 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models having the same number of feature codes as the input label during a first pass, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, wherein the comparing labels step includes comparing the input label with label models having one more or one less feature code during a second pass; identifying the label model or models most closely matching the input label; creating a geometric representation of the input symbol; comparing the geometric models corresponding to the most closely matching label models with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 37
Dependent Claim
167 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; vectorizing the coordinate information into a plurality of vector codes each of which represents a direction taken while the input symbol was being handwritten; translating the vector codes into an input label of one or more feature codes ordered according to the time sequential order in which the features were written, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models having the same number of feature codes as the input label during a first pass and comparing the input label with label models having one more or one less feature code during a second pass, each label model corresponding to a geometric model of a written symbol; and identifying the input label model or models that most closely match the input label.
Claim 38
Dependent Claim
167 words
A computerized method of recognizing a handwritten input symbol having features written according to a time sequential order, comprising: receiving a time sequence of coordinate information representative of the input symbol; vectorizing the coordinate information into a plurality of vector codes each of which represents a direction taken while the input symbol was being handwritten; translating the vector codes into an input label of one or more feature codes ordered according to the time sequential order in which the features were written, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models having the same number of feature codes as the input label during a first pass and comparing the input label with label models having one more or one less feature code during a second pass, each label model corresponding to a geometric model of a written symbol; and identifying the input label model or models that most closely match the input label.
Claim 39
Dependent Claim
74 words
The method of claim 33, wherein the vectorizing step includes: determining a direction traveled from a first point to a second point as the input symbol is being handwritten; translating the direction into one of a plurality of vector codes; repeating the steps of determining a direction and translating the direction for a plurality of first points and a plurality of second points to create the plurality of vector codes for the input symbol.
Claim 40
Dependent Claim
42 words
The method of claim 33, further including determining whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook and ignoring the end portion if it is determined to be an unintended hook.
Claim 41
Dependent Claim
47 words
The method of claim 35 wherein the determining step includes: identifying an unintended hook if the number of vector codes created for the end portion of the pen stroke is less than a predetermined fraction of the number of vector codes created for the entire pen stroke.
Claim 42
Dependent Claim
69 words
The method of claim 33, further including: storing a plurality of geometric models, each of which corresponding to one of the label models creating a geometric representation of the input symbol; comparing the geometric models corresponding to the most closely matching label models with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 43
Dependent Claim
62 words
The method of claim 37 wherein the geometric representation created is limited to two coordinate points for each feature and the step of computing a Euclidean vector distance includes computing the Euclidean vector distance for a selected geometric model by determining a distance between each of the two coordinates points for each feature and corresponding coordinate points for the selected geometric model.
Claim 44
Dependent Claim
247 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the features of the input symbol and translates the coordinate information for each feature into a feature code representing one of a predetermined number of feature models, the symbol analyzer also creates a geometric representation of the input symbol by saving a subset of the coordinate points of each feature and discarding the remaining coordinate points of the features, the subset saved including an end point of the feature; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models; a label comparator that compares sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten and identifies the label model or models whose feature codes most closely match the feature codes of the input symbol; and a geometric comparator that compares geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with a geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 45
Dependent Claim
247 words
An automatic handwritten symbol recognizer that recognizes a handwritten input symbol having features written according to a time sequential order, comprising: a symbol analyzer that receives a time sequence of coordinate information representing the features of the input symbol and translates the coordinate information for each feature into a feature code representing one of a predetermined number of feature models, the symbol analyzer also creates a geometric representation of the input symbol by saving a subset of the coordinate points of each feature and discarding the remaining coordinate points of the features, the subset saved including an end point of the feature; a memory storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models; a label comparator that compares sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten and identifies the label model or models whose feature codes most closely match the feature codes of the input symbol; and a geometric comparator that compares geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with a geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 46
Dependent Claim
30 words
The handwriting recognizer of claim 39 wherein the symbol analyzer is adapted to translate the coordinate information for each feature into a feature code representing one of thirteen feature models.
Claim 47
Dependent Claim
29 words
The handwriting recognizer of claim 39 wherein the symbol analyzer includes means for vectorizing the coordinate information into a plurality of vector codes representing vector information of the features.
Claim 48
Dependent Claim
19 words
The handwriting recognizer of claim 41 wherein the symbol analyzer includes a filter adapted to smooth anomalous vector codes.
Claim 49
Dependent Claim
26 words
The handwriting recognizer of claim 41 wherein the symbol analyzer includes means for translating a portion of the vector codes into one of the feature codes.
Claim 50
Dependent Claim
37 words
The handwriting recognizer of claim 39 wherein the symbol analyzer includes a hook filter adapted to determine whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook.
Claim 51
Dependent Claim
38 words
The handwriting recognizer of claim 39 wherein the symbol analyzer includes means for arranging the feature codes of the input label according to the sequential order in which the coordinate information corresponding to the feature codes was produced.
Claim 52
Dependent Claim
55 words
The handwriting recognizer of claim 45 wherein the label comparator includes: means for rearranging the order of the feature codes of the input label after the geometric representation of the input symbol corresponding to the input label is compared by the geometric comparator; and means for comparing the rearranged input labels to the label models.
Claim 53
Dependent Claim
36 words
The handwriting recognizer of claim 39 wherein the label comparator includes means for comparing the input label only with label models having the same number of feature codes as the input label during a first pass.
Claim 54
Dependent Claim
41 words
The handwriting recognizer of claim 39 wherein the label comparator includes means for identifying a score for each comparison of the input label with one of the label models and means for saving the scores that satisfy a predetermined label threshold.
Claim 55
Dependent Claim
40 words
The handwriting recognizer of claim 39 wherein the geometric comparator includes means for computing a Euclidean vector distance for each geometric model, the Euclidean vector distance representing how closely the geometric model matches the geometric representation of the input symbol.
Claim 56
Dependent Claim
67 words
The handwriting recognizer of claim 49 wherein the geometric representation of the input symbol is limited to exactly two coordinate points for each feature and the means for computing a Euclidean vector distance computes the Euclidean vector distance for a selected geometric model by determining a distance between each of the two coordinates points for each feature and a corresponding coordinate point for the selected geometric model.
Claim 57
Dependent Claim
28 words
The handwriting recognizer of claim 49, further including output means for causing to be displayed one of the geometric models whose Euclidean vector distance satisfies a geometric threshold.
Claim 58
Dependent Claim
245 words
A computer-readable storage medium for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, comprising: computer instructions for receiving a time sequence of coordinate information representing the Features of the input symbol; computer instructions for translating the coordinate information for each feature into a feature code representing one of a predetermined number of feature models; reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models; computer instructions for comparing sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten and identifies the label model or models whose feature codes most closely match the feature codes of the input symbol; and computer instructions for comparing geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with a geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol; and wherein the computer instructions for comparing the feature codes with the label models include computer instructions for comparing the input label with label models having one more or one less feature code than the input label during a second pass.
Claim 59
Dependent Claim
245 words
A computer-readable storage medium for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, comprising: computer instructions for receiving a time sequence of coordinate information representing the Features of the input symbol; computer instructions for translating the coordinate information for each feature into a feature code representing one of a predetermined number of feature models; reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models; computer instructions for comparing sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten and identifies the label model or models whose feature codes most closely match the feature codes of the input symbol; and computer instructions for comparing geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with a geometric representation of the input symbol and identifies the geometric model or models that most closely match the geometric representation of the input symbol; and wherein the computer instructions for comparing the feature codes with the label models include computer instructions for comparing the input label with label models having one more or one less feature code than the input label during a second pass.
Claim 60
Dependent Claim
266 words
A computer-readable storage medium including executable instructions for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, the executable instructions comprising instructions for: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models without regard for positions of the features represented by the feature codes of the input label, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, each geometric model including data representing positions of features of a reference symbol represented by the geometric model; identifying a most closely matching subset of the stored label models by identifying the label model or models most closely matching the input label regardless of the positions of the features represented by the feature codes of the input label; creating a geometric representation of the input symbol, the geometric representation including data representing positions of features of the input symbol; comparing only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 61
Dependent Claim
266 words
A computer-readable storage medium including executable instructions for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, the executable instructions comprising instructions for: receiving a time sequence of coordinate information representative of the input symbol; translating the coordinate information into an input label of one or more feature codes ordered according to the time sequential order of the features, each feature code representing one of a predetermined number of feature models; comparing the input label to a plurality of stored label models without regard for positions of the features represented by the feature codes of the input label, each label model corresponding to a stored geometric model and including a defined sequence of feature codes that are compared to the input label according to the time sequential order in which the features of the input symbol were written, each geometric model including data representing positions of features of a reference symbol represented by the geometric model; identifying a most closely matching subset of the stored label models by identifying the label model or models most closely matching the input label regardless of the positions of the features represented by the feature codes of the input label; creating a geometric representation of the input symbol, the geometric representation including data representing positions of features of the input symbol; comparing only the geometric models corresponding to the label models of the most closely matching subset with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the input symbol geometric representation.
Claim 62
Dependent Claim
53 words
The storage medium of claim 53 wherein the instructions for translating the coordinate information include instructions for vectorizing the coordinate information into a time sequence of vector codes representing vector information of the features and translating the vector codes for each written feature into a feature code representing one of thirteen feature models.
Claim 63
Dependent Claim
90 words
The storage medium of claim 53 wherein the instructions for translating the coordinate information include instructions for determining whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook by identifying an unintended hook if the number of vector codes created for the end portion of the pen stroke is less than a predetermined fraction of the number of vector codes created for the entire pen stroke and ignoring the end portion if it is determined to be an unintended hook.
Claim 64
Dependent Claim
103 words
The storage medium of claim 53 wherein the instructions for creating a geometric representation include instructions for limiting the geometric representation to exactly two coordinate points for each feature and the instructions for comparing only the geometric models include instructions for computing a Euclidean vector distance for each geometric model corresponding to one of the label models of the most closely matching subset by determining a distance between each of the two coordinates points for each feature and corresponding coordinate points for the geometric model, the Euclidean vector distance representing how closely the geometric model matches the geometric representation of the input symbol.
Claim 65
Dependent Claim
55 words
The storage medium of claim 53 wherein the instructions for translating the coordinate information include instructions for: rearranging the order of the feature codes of the input label after the input symbol geometric representation corresponding to the input label is compared to the geometric models; and comparing the rearranged input label to the label models.
Claim 66
Dependent Claim
237 words
A computer-readable storage medium including executable instructions for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, the executable instructions comprising instructions for: receiving a time sequence of coordinate information representing the features of the input symbol; translating the coordinate information for each feature into a feature code representing one of a predetermined number of feature models; creating a geometric representation of the input symbol by saving a subset of the coordinate points of each feature and discarding the remaining coordinate points of the features, the subset saved including an end point of the feature; storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models, comparing sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten, identifying the label model or models whose feature codes most closely match the feature codes of the input symbol; comparing geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 67
Dependent Claim
237 words
A computer-readable storage medium including executable instructions for controlling a computer to recognize a handwritten input symbol having features written according to a time sequential order, the executable instructions comprising instructions for: receiving a time sequence of coordinate information representing the features of the input symbol; translating the coordinate information for each feature into a feature code representing one of a predetermined number of feature models; creating a geometric representation of the input symbol by saving a subset of the coordinate points of each feature and discarding the remaining coordinate points of the features, the subset saved including an end point of the feature; storing reference symbol information including a plurality of label models and a plurality of geometric models, each label model including a predetermined sequence of feature codes and corresponding to one of the geometric models, comparing sequentially the feature codes of the input symbol with the feature codes of the label models according to the time sequential order in which the features of the input symbol were handwritten, identifying the label model or models whose feature codes most closely match the feature codes of the input symbol; comparing geometric models corresponding to the label models whose feature codes most closely match the feature codes of the input symbol with the geometric representation of the input symbol; and identifying the geometric model or models that most closely match the geometric representation of the input symbol.
Claim 68
Dependent Claim
53 words
The storage medium of claim 58 wherein the instructions for translating the coordinate information include instructions for vectorizing the coordinate information into a time sequence of vector codes representing vector information of the features and translating the vector codes for each written feature into a feature code representing one of thirteen feature models.
Claim 69
Dependent Claim
90 words
The storage medium of claim 58 wherein the instructions for translating the coordinate information include instructions for determining whether an end portion of a pen stroke is intended to be part of a feature or an unintended hook by identifying an unintended hook if the number of vector codes created for the end portion of the pen stroke is less than a predetermined fraction of the number of vector codes created for the entire pen stroke and ignoring the end portion if it is determined to be an unintended hook.
Claim 70
Dependent Claim
55 words
The storage medium of claim 58 wherein the instructions for translating the coordinate information include instructions for: rearranging the order of the feature codes of the input label after the input symbol geometric representation corresponding to the input label is compared to the geometric models; and comparing the rearranged input label to the label models.
References Cited (Backward Citations)
US3979722A
Cited
US4365235A
Cited
US4542526A
Cited
US4630309A
Cited
US4628532A
Cited
US4701960A
Cited
US4680805A
Cited
US4653107A
Cited
US4680804A
Cited
US4685142A
Cited
EP0183347A2
Cited
US4672677A
Cited
US4718103A
Cited
US4979226A
Cited
US5121442A
Cited
US5113452A
Cited
US4987603A
Cited
US5007098A
Cited
US5265174A
Cited
US5151950A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-03-16 | 2001-09-15 | 2002-03-17 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-03-16 | 2005-09-15 | 2006-03-17 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-03-16 | 2009-09-15 | 2010-03-17 | $7700.00 | Window Closed / Lapsed |