← Back to Patent Explorer
EP0391044A2 Expired / Lapsed EP ⏱️ 0.0 years remaining

Pattern generation method for registering handwriting

Assignee: Cadix Inc
•
Filing: 1990-02-13
•
Granted: —
•
Expires: 2010-02-13
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A pattern generation method for registering handwriting and a method for updating same that facilitates the obtaining of a registration pattern that reflects accurately the characteristics of an individual handwritten signature. Dynamic programming matching is used to obtain a cumulative error among a plurality of input patterns in the form of a distortion function, and this distortion function is used for shape averaging and time distortion averaging of input patterns.

Inventors

  • 👤 Masami Muroya

Bibliographic Details

Application Number —
Jurisdiction EP
Data Source google_patents
Last Synchronized 2026-11-08 23:45
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/30; G07; G07C; G07C9/00; G07C9/30; G07C9/32; G07C9/35

Claims Analysis

Total Claims: 3
Claim 1
Independent Claim 153 words
A handwritten character registration pattern generation method for obtaining a registration pattern, comprising the steps of: multiple inputting of handwritten characters in the form of coordinate and writing pressure three-­dimensional time series information; normalizing the position and size of multiple handwritten character patterns thus input; calculating a distortion function for selecting a desired pattern from the multiple input patterns as a reference pattern and obtaining a time distortion function between the reference pattern and other input patterns using dynamic programming matching; using the distortion function for time axis correction of the time axis or arc axis of each input pattern; shape averaging the time axis corrected multiple input patterns; distortion averaging the multiple distortion functions; and time distortion correction of the time axis or arc axis of the shape averaged patterns, using the distortion function average; whereby the registration pattern is obtained from the distortion function derived shape average and time distortion average.
Claim 2
Dependent Claim 153 words
A handwritten character registration pattern generation method for obtaining a registration pattern, comprising the steps of: multiple inputting of handwritten characters in the form of coordinate and writing pressure three-­dimensional time series information; normalizing the position and size of multiple handwritten character patterns thus input; calculating a distortion function for selecting a desired pattern from the multiple input patterns as a reference pattern and obtaining a time distortion function between the reference pattern and other input patterns using dynamic programming matching; using the distortion function for time axis correction of the time axis or arc axis of each input pattern; shape averaging the time axis corrected multiple input patterns; distortion averaging the multiple distortion functions; and time distortion correction of the time axis or arc axis of the shape averaged patterns, using the distortion function average; whereby the registration pattern is obtained from the distortion function derived shape average and time distortion average.
Claim 3
Dependent Claim 75 words
A handwritten character registration pattern generation method according to claim 1, wherein the registration pattern is updated in accordance with changes in input patterns corresponding to time-based changes in a handwritten character input pattern, comprising: forming a multiplicity of handwritten character input patterns from an existing registration pattern and new input patterns; and giving a prescribed weighting to the existing registration pattern and the input patterns and performing each of the steps of the method.

References Cited (Backward Citations)

No citation records indexed.

USPTO Annuity & Maintenance Windows

Maintenance schedule is calculated for granted US utility patents.

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag