JPH0567241A - Online handwritten character recognition device - Google Patents

Online handwritten character recognition device

Info

Publication number
JPH0567241A
JPH0567241A JP3229282A JP22928291A JPH0567241A JP H0567241 A JPH0567241 A JP H0567241A JP 3229282 A JP3229282 A JP 3229282A JP 22928291 A JP22928291 A JP 22928291A JP H0567241 A JPH0567241 A JP H0567241A
Authority
JP
Japan
Prior art keywords
pattern
collation
character
character recognition
recognition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP3229282A
Other languages
Japanese (ja)
Inventor
Hiroshi Uno
裕志 宇野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP3229282A priority Critical patent/JPH0567241A/en
Publication of JPH0567241A publication Critical patent/JPH0567241A/en
Pending legal-status Critical Current

Links

Landscapes

  • Character Discrimination (AREA)

Abstract

PURPOSE:To move new pattern data for collation, which is obtained by means of learning and which has a writing habit, between devices so as to improve recognition processing efficiency in an online handwritten character device. CONSTITUTION:A character recognition pattern extraction part 2 extracts recognition patter information 102 from handwritten character information 101 inputted from a handwriting tablet 1, and it is held in a pattern holding buffer 3. A collation operation part 4 outputs similarity between reference pattern data 103 for collation in a pattern base part 5 and recognition pattern information 102, and a character decision part 8 decides a decision character 106 based on the size. New pattern data 105 for collation obtained by learning for recognizing the individual writing habit among standard collation data in the pattern data base 5 is held in a portable card storage medium 9 so as to move it.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】本発明は、オンライン手書き文字
認識装置に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an on-line handwritten character recognition device.

【0002】[0002]

【従来の技術】従来、この種のオンライン手書き文字認
識装置では、認識照合のための基準となる文字認識パタ
ンが装置内に登録されており、個人の書きぐせのため認
識できなかった文字は、学習により覚えさせ、新規文字
認識パタンとして装置内の文字認識パタンに追加登録し
ていた。
2. Description of the Related Art Conventionally, in this type of online handwritten character recognition device, a character recognition pattern, which is a reference for recognition and verification, is registered in the device, and a character that cannot be recognized due to personal writing is It was learned by learning and additionally registered as a new character recognition pattern in the character recognition pattern in the device.

【0003】[0003]

【発明が解決しようとする課題】上述した従来のオンラ
イン手書き文字認識装置では、利用者の個人的な書きぐ
せのある文字を認識するために、学習によって覚えこま
せた照合用の新規文字認識パタンを、他のオンライン手
書き文字認識装置に登録する手段は持っておらず、この
ため新規文字認識パタンデータの有効利用が限定されて
しまうという欠点がある。
In the above-described conventional online handwritten character recognition device, in order to recognize a character that is personally written by the user, a new character recognition pattern for collation learned by learning. Has no means for registering in the other on-line handwritten character recognition device, which has a drawback that effective use of the new character recognition pattern data is limited.

【0004】本発明の目的は上述した欠点を除去し、学
習によって新たに登録した新規文字認識パタンを、他の
オンライン手書き文字認識装置に登録することを可能と
し、新規文字認識パタンデータの有効利用を拡大したオ
ンライン手書き文字認識装置を提供することにある。
An object of the present invention is to eliminate the above-mentioned drawbacks and to enable a new character recognition pattern newly registered by learning to be registered in another on-line handwritten character recognition device, thereby effectively utilizing the new character recognition pattern data. It is to provide an online handwritten character recognition device which is expanded.

【0005】[0005]

【課題を解決するための手段】本発明のオンライン手書
き文字認識装置は、学習によって得た個人的な書きぐせ
のある文字を照合用の新規文字認識パタンとして携帯型
カード状記憶媒体に記憶し、可搬かつ装置ごとに新規登
録可能とした構成を有する。
The on-line handwritten character recognition device of the present invention stores a personally written character obtained by learning as a new character recognition pattern for collation in a portable card-shaped storage medium, It is portable and can be newly registered for each device.

【0006】[0006]

【実施例】次に、本発明について図面を参照して説明す
る。
DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, the present invention will be described with reference to the drawings.

【0007】図1は、本発明の一実施例の構成を示すブ
ロック図である。
FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention.

【0008】図1に示す実施例は、手書きタブレット1
と、手書き文字から文字認識パタンを抽出する文字認識
パタン抽出部2と、抽出した認識パタンを一時記憶する
パタン保持バッファ3と、標準パタンとの類似度を照合
する照合演算部4と、類似度照合用の標準パタンを格納
しておくパタンデータベース5と、照合によって得た類
似度にもとづいて文字判定を行なう文字判定部8と、書
きぐせのある個人ごとの認識パタンを記憶した携帯型カ
ード状記憶媒体9と、携帯型カード状記憶媒体9の認識
パタンをパタンデータベース5に登録する際のインタフ
ェースをとる個人パタン入力インタフェース10とを備
えて成る。
The embodiment shown in FIG. 1 is a handwriting tablet 1.
A character recognition pattern extraction unit 2 for extracting a character recognition pattern from a handwritten character, a pattern holding buffer 3 for temporarily storing the extracted recognition pattern, a matching calculation unit 4 for matching the similarity with a standard pattern, and a similarity. A pattern database 5 that stores standard patterns for collation, a character determination unit 8 that determines characters based on the degree of similarity obtained by collation, and a portable card shape that stores recognition patterns for each person who has a dictation. The storage medium 9 and a personal pattern input interface 10 serving as an interface for registering the recognition pattern of the portable card-shaped storage medium 9 in the pattern database 5 are provided.

【0009】また、パタンデータベース5は、あらかじ
め登録した認識パタンを格納する標準パタンデータベー
ス6、および携帯型カード状記憶媒体9の記憶内容を登
録する個人パタンデータベース7を備えて成る。
The pattern database 5 is provided with a standard pattern database 6 for storing previously registered recognition patterns and a personal pattern database 7 for registering the stored contents of the portable card-shaped storage medium 9.

【0010】次に、本実施例の動作について説明する。Next, the operation of this embodiment will be described.

【0011】手書きタブレット1より入力された手書き
文字情報101は、文字認識パタン抽出部2で認識パタ
ン情報102が抽出され、次いでパタン保持バッファ3
に一時保持される。
From the handwritten character information 101 input from the handwriting tablet 1, the recognition pattern information 102 is extracted by the character recognition pattern extraction unit 2, and the pattern holding buffer 3 is then extracted.
Temporarily held in.

【0012】照合演算部4では、認識パタン情報102
と、パタンデータベース5の標準パタンデータベース6
に登録されている照合用基準パタンデータ103との照
合を行ない、両者の類似度を表わす類似度パラメータ1
04を計算,出力する。
In the matching calculation unit 4, the recognition pattern information 102
And the standard pattern database 6 of the pattern database 5
Is compared with the reference pattern data 103 for matching registered in the, and the similarity parameter 1 indicating the similarity between the two.
04 is calculated and output.

【0013】文字判定部8は、照合によって求めた類似
度の最も大なるものを入力文字に合致した標準パタンと
して判定し、この標準パタンの対応文字を判定文字10
6として出力する。
The character determination unit 8 determines the highest similarity determined by collation as a standard pattern that matches the input character, and determines the corresponding character of this standard pattern as the determination character 10.
Output as 6.

【0014】パタンデータベース5は、標準パタンデー
タベース6と、装置を利用する個人ごとの書きぐせのあ
る文字認識に利用する個人向けパタンデータベース7を
有し、個人パタンデータベース7には、書きぐせのある
新規照合用パタンデータが標準パタンとして登録され
る。
The pattern database 5 has a standard pattern database 6 and a personal pattern database 7 used for character recognition with a writing style for each individual who uses the apparatus. The individual pattern database 7 has a writing style. The new verification pattern data is registered as a standard pattern.

【0015】個人パタンデータベース7に登録する標準
パタンは、標準パタンデータベース6で照合のとれない
書きぐせのある利用者を対象とし、その手書き文字を学
習によって得られる。この学習は、本装置を流用する
か、または専用の学習システムを利用するかのいずれか
によって公知の学習手法を利用して行なわれる。
The standard patterns registered in the personal pattern database 7 are intended for users who have ill-written characters that cannot be collated in the standard pattern database 6, and their handwritten characters can be obtained by learning. This learning is performed using a known learning method by either diverting the present device or using a dedicated learning system.

【0016】個人パタンデータベース7に登録する新規
照合用パタンデータは、携帯型カード状記憶媒体9に記
憶されて利用者個人ごとに保持され、個人パタン入力イ
ンタフェース10を通して個人パタンデータベース7に
ロードされる。
The new collation pattern data registered in the personal pattern database 7 is stored in the portable card-shaped storage medium 9 and held for each user, and loaded into the personal pattern database 7 through the personal pattern input interface 10. ..

【0017】こうして、書きぐせのある利用者の個人パ
タンも、装置間でその都度学習することなく、移動可能
に登録利用し、、文字認識に供することができる。
In this way, the personal pattern of a user who has a writing mistake can be movably registered and used for character recognition without learning each time between devices.

【0018】[0018]

【発明の効果】以上説明したように本発明は、照合の基
準とする標準パタンデータのうち、書きぐせのある個人
の文字を認識するために学習によって得た新規パタンデ
ータを携帯型カード状記憶媒体として分離することによ
り、他のオンライン手書き文字認識装置への移動が可能
となり利用する装置ごとに新たに個人の書きぐせを学習
させる手間をはぶき、認識効率を著しく増大しうるとい
う効果がある。
As described above, according to the present invention, of the standard pattern data used as a reference for collation, the new pattern data obtained by learning for recognizing the characters of an individual who has a writing stroke is stored in a portable card-like memory. Separation as a medium makes it possible to move to another on-line handwritten character recognition device, has the effect of reducing the time and effort required to newly learn the personal writing style for each device used, and significantly increasing the recognition efficiency.

【図面の簡単な説明】[Brief description of drawings]

【図1】本発明の一実施例の構成を示すブロック図であ
る。
FIG. 1 is a block diagram showing a configuration of an exemplary embodiment of the present invention.

【符号の説明】[Explanation of symbols]

1 手書きタブレット 2 文字認識パタン抽出部 3 パタン保持バッファ 4 照合演算部 5 パタンデータベース 6 標準パタンデータベース 7 個人パタンデータベース 8 文字判定部 9 携帯型カード状記憶媒体 10 個人パタン入力インタフェース 1 Handwriting tablet 2 Character recognition pattern extraction unit 3 Pattern holding buffer 4 Collation calculation unit 5 Pattern database 6 Standard pattern database 7 Personal pattern database 8 Character judgment unit 9 Portable card storage medium 10 Personal pattern input interface

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】 学習によって得た個人的な書きぐせのあ
る文字を照合用の新規文字認識パタンとして携帯型カー
ド状記憶媒体に記憶し、可搬かつ装置ごとに新規登録可
能としたことを特徴とするオンライン手書き文字認識装
置。
1. A personalized handwritten character obtained by learning is stored in a portable card-shaped storage medium as a new character recognition pattern for collation, which is portable and can be newly registered for each device. An online handwritten character recognition device.
JP3229282A 1991-09-10 1991-09-10 Online handwritten character recognition device Pending JPH0567241A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP3229282A JPH0567241A (en) 1991-09-10 1991-09-10 Online handwritten character recognition device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP3229282A JPH0567241A (en) 1991-09-10 1991-09-10 Online handwritten character recognition device

Publications (1)

Publication Number Publication Date
JPH0567241A true JPH0567241A (en) 1993-03-19

Family

ID=16889679

Family Applications (1)

Application Number Title Priority Date Filing Date
JP3229282A Pending JPH0567241A (en) 1991-09-10 1991-09-10 Online handwritten character recognition device

Country Status (1)

Country Link
JP (1) JPH0567241A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010102742A (en) * 2003-05-21 2010-05-06 Microsoft Corp System and method for adaptive hand-written character recognition
CN111079490A (en) * 2019-05-29 2020-04-28 广东小天才科技有限公司 Recognition method for written words and electronic equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010102742A (en) * 2003-05-21 2010-05-06 Microsoft Corp System and method for adaptive hand-written character recognition
CN111079490A (en) * 2019-05-29 2020-04-28 广东小天才科技有限公司 Recognition method for written words and electronic equipment

Similar Documents

Publication Publication Date Title
JPH0562391B2 (en)
US10846568B2 (en) Deep learning-based automatic gesture recognition method and system
Manke et al. A connectionist recognizer for on-line cursive handwriting recognition
CN114220179A (en) On-line handwritten signature handwriting retrieval method and system based on faiss
JPH07509576A (en) How to recognize characters
JPH0567241A (en) Online handwritten character recognition device
JPS62159291A (en) Sentence input device
JPH0896081A (en) Character recognizing device and character recognizing method
JPS592191A (en) Recognizing and processing system of handwritten japanese sentence
JPS5842904B2 (en) Handwritten kana/kanji character recognition device
JPS60116082A (en) Individual discrimination method
JPS6228889A (en) Information recognizing device
JPS58214973A (en) Similar character discriminating system
JPH09319828A (en) On-line character recognition device
JP3346943B2 (en) Database search control device
JPS6293776A (en) Information recognizing device
JP3017899B2 (en) Personal identification device and method
JPS59188787A (en) Input device of on-line manuscript character
JP2552281B2 (en) Personal verification device
JPH0634259B2 (en) Character recognition device
JP3130392B2 (en) Character recognition device
JPS59111582A (en) Character recognizing device
JPS61295588A (en) Kanji practicing apparatus
JP2003150903A5 (en)
Wadhawan et al. Design and Analysis of Online Punjabi Signature Verification System Using Grid Optimization