US4561105A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Complex pattern recognition method and system
Assignee: COMMUNICATION INTELLIGENCE Corp A CORP OF CA
•
Filing: 1983-01-19
•
Granted: 1985-12-24
•
Expires: 2003-01-19
Abstract
Abstract A method and system for recognizing complex patterns, such as Chinese characters (or Kanji), identifies patterns by stroke recognition using detailed information about stroke shape and specifically curvature characteristics. Written strokes are categorized into different specific stroke types and are assigned stroke identity labels by comparison of distance metrics generated with reference to stroke templates, each template comprising information specifying position of a point and permissible deviation for each such point along a stroke. Deviation values may differ from point to point and from stroke type to stroke type. The data on the written stroke may be rotated or displaced relative to each stroke template to enhance the likelihood of stroke recognition. Limited information about stroke position relative to other strokes may be preserved and employed to resolve ambiguities among accumulations of stroke identity labels found to ambiguously indicate more than one pattern or character.
Inventors
- 👤 Hewitt D. Crane
- 👤 John S. Ostrem
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-06 08:43
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/142; G06F; G06F18/00; G06F18/20; G06V30/19; G06V30/196; G06V30/28; G06V30/287; G06V30/32; G06V30/333; G06V30/347
Claims Analysis
Total Claims: 45
Claim 1
Independent Claim
253 words
A method for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based upon relative movement between a pattern-forming means and a pattern-accommodating means of said registration means, said registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signal information represented by second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, said method comprising for at least one stroke: designating from said first signal information a set of sequential first data points, said set of first data points being selected from or interpolated on the basis of said first signal information along said stroke; defining templates consisting of said second signal information, each said template comprising a set of second data points defining relative sequentially related position values and a set of permissible tolerance values, each of said tolerance values representing a preselected deviation for its associated second data point, at least one of said permissible tolerance values differing from at least one other of said permissible tolerance values for a single template; and comparing said first data points with said second data points to determine which of said templates provides best correspondence between said first and second signal information to produce said third signal information.
Claim 2
Independent Claim
253 words
A method for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based upon relative movement between a pattern-forming means and a pattern-accommodating means of said registration means, said registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signal information represented by second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, said method comprising for at least one stroke: designating from said first signal information a set of sequential first data points, said set of first data points being selected from or interpolated on the basis of said first signal information along said stroke; defining templates consisting of said second signal information, each said template comprising a set of second data points defining relative sequentially related position values and a set of permissible tolerance values, each of said tolerance values representing a preselected deviation for its associated second data point, at least one of said permissible tolerance values differing from at least one other of said permissible tolerance values for a single template; and comparing said first data points with said second data points to determine which of said templates provides best correspondence between said first and second signal information to produce said third signal information.
Claim 3
Dependent Claim
21 words
The method according to claim 1, wherein position is represented in terms comprising angular numerical values in a polar coordinate system.
Claim 4
Dependent Claim
19 words
The method according to claim 1, wherein position is represented in terms comprising locations in a Cartesian coordinate system.
Claim 5
Dependent Claim
55 words
The method according to claim 1 or 2, further including the step, in the absence of acceptance of an identity label, of modifying said first signal information by adding or subtracting an incremental numerical value of at least one of said first data points and again comparing said first data points with each said template.
Claim 6
Dependent Claim
31 words
The method according to claim 4, wherein said modifying step comprises rotating said first signal information of at least one of said first data points relative to said second data points.
Claim 7
Dependent Claim
40 words
The method according to claim 1 or 2, further including the step of spacing said first and second data points evenly along a stroke, at least some of said first data points being points interpolated from said first signal information.
Claim 8
Dependent Claim
42 words
The method according to claim 1 or 2, characterized in that first data points are represented in terms comprising angular position values in a polar coordinate system at locations interpolated to correspond to locations of said second data points of said template.
Claim 9
Dependent Claim
37 words
The method according to claim 1 or 2, wherein said stroke registration means is a signal-receiving means responsive to movement of said character-forming means, and including the step of registering a stroke upon said stroke registration means.
Claim 10
Dependent Claim
35 words
The method according to claim 8, wherein said character-forming means comprises a writing implement and said stroke-registration means comprises a pressure-sensitive position-registering tablet, including the step of writing with said writing implement upon said tablet.
Claim 11
Dependent Claim
57 words
The method according to claim 1 or 2, wherein said character-forming means and said stroke-registration means comprise an instrumented writing implement operative to generate transducer signals specifying pressure and direction versus time, including the step of supplying said signals representing said first signal information to said data processing means in response to writing on a friction surface.
Claim 12
Dependent Claim
52 words
The method according to claim 1 or 2, further including the step, in the absence of acceptance of an identity label, modifying said first signal information to effect a displacement of said first data points relative to said second data points and again compares said first data points with each said template.
Claim 13
Dependent Claim
27 words
In the method according to claim 11, wherein said modifying step further comprises shifting said first data points relative to said second data points along stroke length.
Claim 14
Dependent Claim
38 words
In the method according to claim 1 or 2, further including the step of resolving said first signal information with an angular resolution at each one of said first data points to within no greater than 1.5 degrees.
Claim 15
Dependent Claim
38 words
In the method according to claim 1 or 2, further including the step of resolving said first signal information with an angular resolution at each one of said first data points to within no greater than 0.15 degrees.
Claim 16
Dependent Claim
36 words
In the method according to claim 1 or 2, wherein said comparing step comprises computing the closeness between each one of said first data points and said second data points to obtain a distance metric value.
Claim 17
Dependent Claim
46 words
The method according to claim 15, further including the step of comparing said distance metric value for each said template with an upper decision threshold value, with a lower decision threshold value and with a difference decision threshold value in order to obtain said identity label.
Claim 18
Dependent Claim
53 words
The method according to claim 16, further including the step of assigning a specific identity label of one of said predefined template strokes if the least distance metric value is less than the lower decision threshold value and if the next least distance metric value is greater than the upper decision threshold value.
Claim 19
Dependent Claim
57 words
In the method according to claim 1 or 2, further including the step of calculating distance between corresponding first data points and second data points to obtain difference values; dividing each one of said difference values by the corresponding permissible angular deviation value to obtain quotient values; and summing all quotient values to obtain a distance-metric value.
Claim 20
Dependent Claim
22 words
In the method according to claim 18, further including the step of squaring each one of said quotient values prior to summing.
Claim 21
Dependent Claim
82 words
In the method according to claim 1 or 2, further including the steps of: combining said third signals representing said identity label with other third signals representing other identity labels so obtained to form fourth signals representing a group of related identity labels; and comparing said fourth signals against fifth signals, said fifth signals representing an index to character labels specified by sets of related identity labels to produce sixth signals, said sixth signals representing a character label corresponding to said group.
Claim 22
Dependent Claim
28 words
The method according to claim 20, further including the step of employing said sixth signals to form a visual pattern representing the character identified by said character label.
Claim 23
Dependent Claim
15 words
The method according to claim 20, wherein said character label corresponds to a Kanji character.
Claim 24
Dependent Claim
18 words
The method according to claim 22 wherein said Kanji character is handwritten relative to preceding first data points.
Claim 25
Dependent Claim
27 words
The method according to claim 20, further including the step of using information regarding sequence of said identity labels to produce said sixth signals representing character labels.
Claim 26
Dependent Claim
29 words
The method according to claim 1 or 2, further including the step of comparing said second signal information with said first signal information independent of absolute stroke position values.
Claim 27
Dependent Claim
58 words
The method according to claim 25, further including the step of preserving selected absolute stroke position values of said first signal information independent of said identifying step, and employing said selected absolute stroke position values to resolve ambiguity among recognized patterns only in the event a plurality of patterns is indicated for a single accumulation of identity labels.
Claim 28
Dependent Claim
256 words
In an apparatus for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based on relative movement between a pattern-forming means and a pattern-accommodating means of said stroke registration means, said stroke registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, the improvement characterized in that: said data processing means includes means for designating from said first signal information a set of sequential first data points, said set of first data points being selected from or interpolated on the basis of said first signal information, along said stroke means defining templates consisting of said second signal information, each said template comprising a set of second data points defining relative sequential position values and set of permissible tolerance values, each of said tolerance values representing a preselected deviation for its associated second data point, at least one of said permissible tolerance values differing from at least one other of said permissible tolerance values for a single template; and means for comparing said first data points with said second data points to determine which of said templates provides best correspondence between said first and second signal information to produce said third signal information.
Claim 29
Dependent Claim
256 words
In an apparatus for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based on relative movement between a pattern-forming means and a pattern-accommodating means of said stroke registration means, said stroke registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, the improvement characterized in that: said data processing means includes means for designating from said first signal information a set of sequential first data points, said set of first data points being selected from or interpolated on the basis of said first signal information, along said stroke means defining templates consisting of said second signal information, each said template comprising a set of second data points defining relative sequential position values and set of permissible tolerance values, each of said tolerance values representing a preselected deviation for its associated second data point, at least one of said permissible tolerance values differing from at least one other of said permissible tolerance values for a single template; and means for comparing said first data points with said second data points to determine which of said templates provides best correspondence between said first and second signal information to produce said third signal information.
Claim 30
Dependent Claim
25 words
In the apparatus according to claim 27, characterized in that said pattern-accommodating means is a signal-receiving means responsive to relative movement of said pattern-forming means.
Claim 31
Dependent Claim
24 words
In the apparatus according to claim 27 wherein said pattern-forming means comprises a writing implement and said pattern-accommodating means comprises a pressure-sensitive position-registration tablet.
Claim 32
Dependent Claim
47 words
In the apparatus according to claim 27 wherein said pattern-forming means and said pattern-accommodating means are characterized by an instrumented writing implement operative to generate transducer signals specifying pressure and direction versus time in response to an act of writing with said implement on a friction surface.
Claim 33
Dependent Claim
31 words
In the apparatus according to claim 27, characterized in that said data processing means includes means for rotating said first signal information relative to position values of said second signal information.
Claim 34
Dependent Claim
31 words
In the apparatus according to claim 27, characterized in that said data processing means includes means for displacing said first signal information relative to position values of said second signal information.
Claim 35
Dependent Claim
65 words
In the apparatus according to claim 27, characterized in that said data processing means includes means for preserving selected absolute stroke position values of said first original information independent of said identifying step and to employ said selected absolute stroke position values to resolve ambiguity among recognized patterns only in the event a plurality of patterns is indicated for a single accumulation of identity labels.
Claim 36
Dependent Claim
32 words
In the apparatus according to claim 27, characterized in that said data processing means includes means for comparing said first signal information with said second signal information independent of relative stroke size.
Claim 37
Dependent Claim
33 words
In the apparatus according to claim 27, characterized in that said data processing means includes means for comparing said second signal information with said first single information independent of absolute stroke position values.
Claim 38
Dependent Claim
142 words
The apparatus according to claim 27 wherein said comprising means includes means coupled to receive said first signal information and said second signal information for computing closeness between each one of said first data points and said second data points to obtain a distance metric value for each one of said templates, means coupled to receive each said distance metric value for comprising each said distance metric value with an upper decision threshold, with a lower decision threshold and a difference decision threshold, and means for assigning a specific identity label of one of said predefined template strokes as said third signal information if the least distance metric value is less than the upper decision thresold value and if the next least distance metric value is greater than the sum of the least distance metric value and the difference decision threshold value.
Claim 39
Independent Claim
285 words
A method for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based upon relative movement between a pattern-forming means and a pattern-accommodating means of said registration means, said registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signal information represented by second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, said method comprising for at least one stroke: designating from said first signal information a set of first data points on the basis of said first signal information along said stroke; defining templates consisting of said second signal information, each said template comprising a set of second data points defining at least relative sequentially related position values; comparing said first data points with said second data points by computing the closeness between each one of said first data points and said second data points to obtain a distance metric value for each of said templates, thereafter comparing said distance metric value for each said template with an upper decision threshold, with a lower decision threshold and with a difference threshold and assigning a specific identity label of one of said predefined template strokes as said third signal information if the least distance metric value is less than the upper decision threshold value and if the next least distance metric value is greater than the sum of the least distance metric value and the difference decision threshold value.
Claim 40
Independent Claim
285 words
A method for identifying patterns by means of a pattern registration means and a data processing means, wherein each pattern comprises at least one stroke based upon relative movement between a pattern-forming means and a pattern-accommodating means of said registration means, said registration means being operative to generate first signal information represented by first signals specifying relative position sequentially along a stroke, said data processing means being provided with prestored second signal information represented by second signals and being operative to generate third signals representing third signal information, said third signal information comprising specification of identity labels for strokes for use in developing coded information specifying said pattern, said method comprising for at least one stroke: designating from said first signal information a set of first data points on the basis of said first signal information along said stroke; defining templates consisting of said second signal information, each said template comprising a set of second data points defining at least relative sequentially related position values; comparing said first data points with said second data points by computing the closeness between each one of said first data points and said second data points to obtain a distance metric value for each of said templates, thereafter comparing said distance metric value for each said template with an upper decision threshold, with a lower decision threshold and with a difference threshold and assigning a specific identity label of one of said predefined template strokes as said third signal information if the least distance metric value is less than the upper decision threshold value and if the next least distance metric value is greater than the sum of the least distance metric value and the difference decision threshold value.
Claim 41
Dependent Claim
53 words
The method according to claim 37, further including the step, in the absence of acceptance of an identity label, of modifying said first signal information by adding or subtracting an incremental numerical value of at least one of said first data points and again comparing said first data points with each said template.
Claim 42
Dependent Claim
50 words
The method according to claim 37, further including the step, in the absence of acceptance of an identity label, modifying said first signal information to effect a displacement of said first data points relative to said second data points and again compares said first data points with each said template.
Claim 43
Dependent Claim
80 words
In the method according to claim 37, further including the steps of: combining said third signals representing said identity label with other third signals representing other identity labels so obtained to form fourth signals representing a group of related identity labels; and comparing said fourth signals against fifth signals, said fifth signals representing an index to character labels specified by sets of related identity labels to produce sixth signals, said sixth signals representing a character label corresponding to said group.
Claim 44
Dependent Claim
27 words
The method according to claim 37, further including the step of comparing said second signal information with said first signal information independent of absolute stroke position values.
Claim 45
Dependent Claim
57 words
The method according to claim 37, further including the step of preserving selected absolute stroke position values of said first signal information independent of said identifying step, and employing said selected absolute stroke position values to resolve ambiguity among recognized patterns only in the event a plurality patterns is indicated for a single accumulation of identity labels.
References Cited (Backward Citations)
US3165718A
Cited
US3611290A
Cited
US3618016A
Cited
US3700815A
Cited
US4027284A
Cited
US4015239A
Cited
US4040009A
Cited
US4037198A
Cited
US4040010A
Cited
US4035768A
Cited
US4190820A
Cited
US4179685A
Cited
JPS5418633A
Cited
US4173753A
Cited
US4284975A
Cited
US4365235A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1988-12-23 | 1989-06-24 | 1989-12-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1992-12-23 | 1993-06-24 | 1993-12-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1996-12-23 | 1997-06-24 | 1997-12-24 | $7700.00 | Window Closed / Lapsed |