JP2011034437A5 - - Google Patents

Download PDF

Info

Publication number
JP2011034437A5
JP2011034437A5 JP2009181632A JP2009181632A JP2011034437A5 JP 2011034437 A5 JP2011034437 A5 JP 2011034437A5 JP 2009181632 A JP2009181632 A JP 2009181632A JP 2009181632 A JP2009181632 A JP 2009181632A JP 2011034437 A5 JP2011034437 A5 JP 2011034437A5
Authority
JP
Japan
Prior art keywords
code data
writing
movement
detection means
character
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.)
Granted
Application number
JP2009181632A
Other languages
Japanese (ja)
Other versions
JP5495657B2 (en
JP2011034437A (en
Filing date
Publication date
Application filed filed Critical
Priority to JP2009181632A priority Critical patent/JP5495657B2/en
Priority claimed from JP2009181632A external-priority patent/JP5495657B2/en
Publication of JP2011034437A publication Critical patent/JP2011034437A/en
Publication of JP2011034437A5 publication Critical patent/JP2011034437A5/ja
Application granted granted Critical
Publication of JP5495657B2 publication Critical patent/JP5495657B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Description

本発明の文字認識装置は、使用者の手指を撮像する撮像手段と、使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段と、手指の移動を移動ベクトルとして検出する移動検出手段と、入力期間中、移動検出手段で検出した移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段と、各文字を正しい書き順および筆運びで筆記した場合に発生する移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した辞書コードデータを記憶する辞書コードデータ記憶手段と、筆記コードデータと辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段と、を備える。 The character recognition apparatus according to the present invention comprises: an imaging means for imaging a user's finger; an input period detection means for detecting an input period for writing a character and a transition period for shifting to the next character according to a predetermined operation of the user; Movement detection means for detecting movement of fingers as movement vectors, and during the input period, the movement vectors detected by the movement detection means are encoded including the transition part to the next image, and acquisition is made of writing code data compressed according to time series Writing code data acquisition means, moving vectors generated when writing each character in correct writing order and stroke are encoded including the transition part to the next image, and dictionary code data compressed according to time series is stored Dictionary code data storage means, and specifying means for comparing the writing code data and the dictionary code data to specify the character written by the user.

又、本発明の文字認識プログラムは、コンピュータを、使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段、撮像した手指の形状を検出する形状検出手段、手指の移動を移動ベクトルとして検出する移動検出手段、入力期間中、移動検出手段で検出した移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段、筆記コードデータと予め準備された辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段、として機能させる。 In the character recognition program according to the present invention, an input period detection means for detecting an input period for writing a character and a transition period for moving to the next character in accordance with a predetermined operation of a computer is detected, and a shape of a captured finger is detected. Shape detection means, movement detection means for detecting movement of a finger as a movement vector, and a movement vector detected by the movement detection means during the input period, including the transition portion to the next image, coded and compressed according to time series It functions as a writing code data obtaining means for obtaining code data, and a specifying means for comparing the writing code data with the previously prepared dictionary code data to specify a character written by the user.

本発明の文字認識装置は、使用者の手指を撮像する撮像手段と、使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段と、手指の移動を移動ベクトルとして検出する移動検出手段と、入力期間中、移動検出手段で検出した移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段と、各文字を正しい書き順および筆運びで筆記した場合に発生する移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した辞書コードデータを記憶する辞書コードデータ記憶手段と、筆記コードデータと辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段と、を備える。これにより、使用者は連続的に複数の画数からなる文字を筆記することが可能であり、演算量と処理時間が低減され、筆記する場所や大きさや速度に拘らず文字を認識することが出来る。 The character recognition apparatus according to the present invention comprises: an imaging means for imaging a user's finger; an input period detection means for detecting an input period for writing a character and a transition period for shifting to the next character according to a predetermined operation of the user; Movement detection means for detecting movement of fingers as movement vectors, and during the input period, the movement vectors detected by the movement detection means are encoded including the transition part to the next image, and acquisition is made of writing code data compressed according to time series Writing code data acquisition means, moving vectors generated when writing each character in correct writing order and stroke are encoded including the transition part to the next image, and dictionary code data compressed according to time series is stored Dictionary code data storage means, and specifying means for comparing the writing code data and the dictionary code data to specify the character written by the user. Thus, the user can continuously write characters consisting of a plurality of stroke numbers, the amount of computation and processing time can be reduced, and characters can be recognized regardless of the writing location, size and speed. .

又、本発明の文字認識プログラムは、コンピュータを、使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段、撮像した手指の形状を検出する形状検出手段、手指の移動を移動ベクトルとして検出する移動検出手段、入力期間中、移動検出手段で検出した移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段、筆記コードデータと予め準備された辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段、として機能させる。これにより、使用者は連続的に複数の画数からなる文字を筆記することが可能であり、演算量と処理時間が低減され、筆記する場所や大きさや速度に拘らず文字を認識することが出来る。 In the character recognition program according to the present invention, an input period detection means for detecting an input period for writing a character and a transition period for moving to the next character in accordance with a predetermined operation of a computer is detected, and a shape of a captured finger is detected. Shape detection means, movement detection means for detecting movement of a finger as a movement vector, and a movement vector detected by the movement detection means during the input period, including the transition portion to the next image, coded and compressed according to time series It functions as a writing code data obtaining means for obtaining code data, and a specifying means for comparing the writing code data with the previously prepared dictionary code data to specify a character written by the user. Thus, the user can continuously write characters consisting of a plurality of stroke numbers, the amount of computation and processing time can be reduced, and characters can be recognized regardless of the writing location, size and speed .

Claims (6)

使用者の手指を撮像する撮像手段と、
使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段と、
手指の移動を移動ベクトルとして検出する移動検出手段と、
前記入力期間中、前記移動検出手段で検出した前記移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段と、
各文字を筆記した場合に発生する前記移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した辞書コードデータを記憶する辞書コードデータ記憶手段と、
前記筆記コードデータと前記辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段と、を備え、
前記入力期間検出手段は、前記撮像手段によって撮像した手指の形状を検出する形状検出手段を備える、
文字認識装置。
Imaging means for imaging the user's fingers;
Input period detection means for detecting an input period for writing a character and a transition period for moving to the next character according to a predetermined operation of the user;
Movement detection means for detecting movement of a finger as a movement vector;
Writing code data acquisition means for encoding the movement vector detected by the movement detection means during the input period, including the transition part to the next image, and acquiring writing code data compressed according to time series;
A dictionary code data storing means for the motion vector that occurs when noted brush each character encoding including transition portion to Tsugiga stores when dictionary code data compressed according to sequence,
And a specifying means for comparing the writing code data with the dictionary code data to specify a character written by the user.
The input period detection means includes a shape detection means for detecting the shape of the finger imaged by the imaging means.
Character recognition device.
記入力期間検出手段は、前記形状検出手段の検出結果に基づいて前記入力期間と前記移行期間とを検出し、
前記移動検出手段は、前記撮像手段によって撮像した手指の位置を検出する位置検出手段を備え、前記位置検出手段が検出する手指の位置変化から前記移動ベクトルを検出することを特徴とする、請求項1に記載の文字認識装置。
The entering force period detecting means detects said transition period and the input periods on the basis of the detection result of the previous SL shape detection means,
The movement detection means includes position detection means for detecting the position of the finger captured by the imaging means, and detects the movement vector from a change in position of the finger detected by the position detection means. The character recognition device according to 1.
前記筆記コードデータ取得手段は、前記移動ベクトルの移動量が所定の閾値以下の時に静止状態と判定し、前記所定の閾値より大きい場合に移動方向に従って移動ベクトルをコード化し、
前記所定の閾値は、移動量の履歴に基づいて変更されることを特徴とする、請求項1又は2に記載の文字認識装置。
The writing code data acquisition means determines that the stationary state is present when the movement amount of the movement vector is less than a predetermined threshold, and encodes the movement vector according to the movement direction when it is larger than the predetermined threshold.
The character recognition device according to claim 1, wherein the predetermined threshold is changed based on a history of movement amount.
前記辞書コードデータ記憶手段は、各文字に対応する前記辞書コードデータを複数個備え、正しい書き順および筆運びで筆記した場合に加え、正しくない書き順および筆運びで筆記した場合に対応する辞書コードデータを少なくとも1つ備えることを特徴とする、The dictionary code data storage means includes a plurality of the dictionary code data corresponding to each character, and in addition to the case of writing in the correct writing order and writing, a dictionary corresponding to the writing in the incorrect writing order and writing Characterized by comprising at least one code data,
請求項1〜3のいずれかに記載の文字認識装置。The character recognition device according to any one of claims 1 to 3.
前記筆記コードデータ取得手段は、前記移動ベクトルが二つの方向を繰り返す時には繰り返し部分を削除してコード化することを特徴とする、請求項1〜のいずれかに記載の文字認識装置。 The character recognition device according to any one of claims 1 to 4 , wherein said writing code data acquisition means deletes and encodes repeated portions when said movement vector repeats two directions. コンピュータを、
使用者の所定動作に応じ、文字を筆記する入力期間と次文字に移る移行期間とを検出する入力期間検出手段、
撮像した手指の形状を検出する形状検出手段、
手指の移動を移動ベクトルとして検出する移動検出手段、
前記入力期間中、前記移動検出手段で検出した前記移動ベクトルを次画への移行部分を含めてコード化し、時系列にしたがって圧縮した筆記コードデータを取得する筆記コードデータ取得手段、
前記筆記コードデータと予め準備された辞書コードデータとを比較して使用者が筆記した文字を特定する特定手段、
として機能させる、文字認識プログラム。
Computer,
Input period detection means for detecting an input period for writing a character and a transition period for moving to the next character according to a predetermined operation of the user;
Shape detection means for detecting the shape of the imaged finger;
Movement detection means for detecting movement of a finger as a movement vector;
Writing code data acquisition means for encoding the movement vector detected by the movement detection means during the input period, including a transition part to the next image, and acquiring writing code data compressed according to time series;
Specifying means for specifying characters written by the user by comparing the writing code data with dictionary code data prepared in advance;
Character recognition program to function as.
JP2009181632A 2009-08-04 2009-08-04 Character recognition device, character recognition program Active JP5495657B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2009181632A JP5495657B2 (en) 2009-08-04 2009-08-04 Character recognition device, character recognition program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2009181632A JP5495657B2 (en) 2009-08-04 2009-08-04 Character recognition device, character recognition program

Publications (3)

Publication Number Publication Date
JP2011034437A JP2011034437A (en) 2011-02-17
JP2011034437A5 true JP2011034437A5 (en) 2012-09-06
JP5495657B2 JP5495657B2 (en) 2014-05-21

Family

ID=43763431

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2009181632A Active JP5495657B2 (en) 2009-08-04 2009-08-04 Character recognition device, character recognition program

Country Status (1)

Country Link
JP (1) JP5495657B2 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6406279B2 (en) * 2016-02-22 2018-10-17 マツダ株式会社 Automotive braking system

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02157986A (en) * 1988-12-09 1990-06-18 Nec Corp Recognizing character type designating system
JPH04195670A (en) * 1990-11-28 1992-07-15 Toshiba Corp Handwritten character recognizing japanese syllabary to chinese character conversion system
US5491758A (en) * 1993-01-27 1996-02-13 International Business Machines Corporation Automatic handwriting recognition using both static and dynamic parameters
JPH08211979A (en) * 1995-02-02 1996-08-20 Canon Inc Hand shake input device and method
JP3574246B2 (en) * 1995-11-29 2004-10-06 株式会社リコー Pattern recognition device
JPH11143868A (en) * 1997-11-07 1999-05-28 Toshiba Corp Character recognition device, input control method and storage medium
JP2002259046A (en) * 2001-02-28 2002-09-13 Tomoya Sonoda System for entering character and symbol handwritten in air
JP4244614B2 (en) * 2002-10-31 2009-03-25 株式会社日立製作所 Handwriting input device, program, and handwriting input method system
JP2008108051A (en) * 2006-10-25 2008-05-08 Funai Electric Co Ltd Video recording and reproducing device, and character input system

Similar Documents

Publication Publication Date Title
CN112926423B (en) Pinch gesture detection and recognition method, device and system
US8373654B2 (en) Image based motion gesture recognition method and system thereof
KR20200092894A (en) On-device classification of fingertip motion patterns into gestures in real-time
TWI382352B (en) Video based handwritten character input device and method thereof
KR101760159B1 (en) Method and device for detecting gesture inputs
JP2006015757A5 (en)
CN109584268B (en) Moving body tracking device, moving body tracking method, and computer-readable recording medium
KR101631011B1 (en) Gesture recognition apparatus and control method of gesture recognition apparatus
RU2014108870A (en) IMAGE PROCESSOR CONTAINING A GESTURE RECOGNITION SYSTEM WITH A FIXED BRUSH POSITION RECOGNITION BASED ON THE FIRST AND SECOND SET OF SIGNS
CN107111357A (en) Use the gesture identification of gesture element
Tsai et al. Embedded virtual mouse system by using hand gesture recognition
WO2017120522A1 (en) Method of character identification that uses time dependent button presses and time independent swipe gestures
CN103488429B (en) Screen unlocking method and device
CN107292295B (en) Gesture segmentation method and device
Khan et al. Gesthaar: An accelerometer-based gesture recognition method and its application in nui driven pervasive healthcare
JP2011034437A5 (en)
CN101739118A (en) Video handwriting character inputting device and method thereof
Kavarthapu et al. Hand gesture sequence recognition using inertial motion units (IMUs)
Pansare et al. Gestuelle: A system to recognize dynamic hand gestures using hidden Markov model to control windows applications
CN113031464B (en) Device control method, device, electronic device and storage medium
JP3554571B2 (en) Sign language recognition device
Teja et al. A ballistic stroke representation of online handwriting for recognition
CN111104886A (en) Gesture recognition method, device, equipment and storage medium
JP5495657B2 (en) Character recognition device, character recognition program
Marasović et al. User-dependent gesture recognition on Android handheld devices