JPH0764990A - Device for preparing sentence by on-line handwritten character recognition - Google Patents

Abstract

PURPOSE:To provide a sentence preparing device by on-line handwritten character recognition performing the KANA (Japanese syllabary)/KANJI (Chinese characters) conversion of handwritten character. CONSTITUTION:The device is provided with a character recognition part 16 recognizing handwritten characters inputted from a coordinate input means 11 by a character recognition frame, recognition character buffer edition part 17 scoring the characters recognized by the part 16 in the buffer memory by scanning them and editing them by phrase, KANA/KANJI conversion part 18 converting the characters edited by the part 17 into a KANA/KANJI mixed sentence, and display part 20 displaying characters converted by the part 18 on the display means 12.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an online handwriting character recognition system for writing texts, and more particularly, to writing texts by online handwriting character recognition for creating handwritten characters and other kanji conversion mixed sentences. Regarding the device.

[0002]

2. Description of the Related Art In recent years, with the advance of handwriting character recognition technology, a sentence creating device for recognizing handwritten characters and converting them into kana-kanji mixed sentences has come to be used. It was

A box-shaped device in which a transparent tablet and a display are laminated and integrated, and a control device is attached to the device is used as such a text-creating device. This text creation device inputs some handwritten characters and presses the bunsetsu conversion icon to convert the input handwritten characters into kana-kanji in bunsetsu units. Although this conversion is simple, there is a problem that the burden on the user increases because the operation of pressing the phrase conversion icon is performed independently of the input of handwritten characters.

In this conversion, the character recognition process must be terminated each time the phrase conversion icon is pressed, the kana-kanji conversion process must be performed, and the character recognition process must be started again when the input of handwritten characters starts. . Therefore, there is a problem that the process of creating a sentence becomes troublesome.

Further, in this conversion, when the phrase conversion icon is pressed, all the character strings stored in the recognized character buffer are subjected to kana-kanji conversion. Therefore, there has been a problem that the user must always pay attention to the number of characters to be input and the number of remaining recognition frames so as not to run out of recognition frames in the middle of a word.

In order to solve this problem, the recognition frame is scrolled when the character written in the last recognition frame is recognized. This scrolling of the recognition frame has a problem that the recognition character buffer is finite and the buffer is immediately filled up, and in the end, the same caution as described above must be taken.

On the other hand, the kana-kanji conversion has a problem of how to detect the breaks of the clauses of the character strings continuously input.

In order to solve this problem, a method is used in which a punctuation mark, a position where the type of character is changed, or a morphological analysis is used.

However, the punctuation marks and the types of characters do not occur frequently and are merely auxiliary means.
There is a problem that the use of morphological analysis is still insufficient in terms of processing time and detection accuracy.

In order to solve the above problems, the present invention provides a sentence creating device for sequentially converting kana-kanji into handwritten characters in units of clauses.

[0011]

The text creating apparatus of the present invention comprises:
A coordinate input means such as a tablet input device or a pen input device; a control means for processing handwritten characters etc. inputted from the coordinate input means; and handwritten characters etc. inputted from the coordinate input means, or In a sentence creation device by online handwritten character recognition, which comprises a display unit for displaying characters processed by the control unit, the control unit includes a handwritten character input from the coordinate input unit by a character recognition frame. A recognition character recognition unit, and a recognition character buffer editing unit that stores characters and the like recognized by the character recognition unit in a buffer memory, scans the stored characters and the like, edits each clause, and stores the edited characters in the buffer memory. , The kana-kanji conversion part for converting the characters etc. edited by the recognition character buffer editing part into a kana-kanji mixed sentence, and the characters etc. converted by this kana-kanji conversion part There is provided a text creation device online handwriting recognition, characterized in that and a display unit for displaying on.

Further, the recognized character buffer editing unit is adapted to catch blanks, punctuation marks, parentheses, etc. of a character recognition frame as a phrase of a handwritten character and edit a sentence mixed with Kana-Kanji. An object of the present invention is to provide a sentence creation device based on the described online handwritten character recognition.

[0013]

[Function] Handwritten characters are input. This handwritten character is captured for each phrase, and the handwritten character is converted into kana-kanji character for each phrase to create a sentence.

With regard to handwritten characters, blank frames, punctuation marks, parentheses, etc. are caught as bunsetsu, and the handwritten characters are converted into kana-kanji characters by this bunsetsu unit.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the text creating apparatus of the present invention will be described below with reference to the accompanying drawings. As shown in FIG. 2, the sentence creating device 10 includes a coordinate input device 11, a display device 12, and a control device 1.
3 and an external storage device 14.

The coordinate input device 11 is formed of a transparent tablet in the shape of a rectangular plate having a coordinate plane, and is used to input handwritten characters and the like with a pen or the like.

The display device 12 is formed of a rectangular plate-shaped liquid crystal display having the same coordinate plane as the coordinate input device 11, and displays handwritten characters and the like input by the coordinate input device 11.

The coordinate plane of the display device 12 and the coordinate plane of the coordinate input device 11 are integrally laminated so as to be the same.
The coordinates of the coordinate input device 11 can be directly specified from the coordinates of the display device 12, and the display information of the display device 12 can be recognized through the transparent tablet of the coordinate input device 11.

The control device 13 has a functional block structure as shown in FIG. 3, and includes a processing unit 13A and a buffer memory 1.
3B is provided. The processing unit 13A includes a coordinate input unit 15, a character recognition unit 16, a recognized character buffer editing unit 17,
Kana-Kanji conversion unit 18, character string editing function unit 19, display unit 2
0 and the like are provided. Further, the buffer memory 13B includes a coordinate data buffer 21 and a character coordinate data buffer 2.
2, recognition character buffer 23, kana-kanji conversion buffer 2
4. A character string edit buffer 25 and the like are provided.

The coordinate input unit 15 receives coordinate data such as handwritten characters input from the coordinate input device 11 and sequentially stores the coordinate data in the coordinate data buffer 21. If the coordinate data corresponds to an icon P (see FIGS. 5 and 9) for instructing character conversion, character string editing, etc., the recognized character buffer editing unit 1 is in accordance with the instructed content.
7. The character string editing function unit 19 is activated.

The coordinate data stored in the coordinate data buffer 21 includes character recognition frames K1, K2 ... (See FIGS. 5 and 9).
If it is within the range, coordinate data outside the character recognition frame will be input or the pen (not shown) will be lifted for a certain period of time, and the coordinate will be turned on and off until the inspection is performed. It is stored in the data buffer 21. The character recognition unit 16 is activated so that the coordinate data of the coordinate data buffer 21 is copied to the character coordinate data buffer 22 when the time inspection or the frame inspection of the character recognition frame K1 ... Is performed. There is.

The character recognizing unit 16 refers to a character recognizing dictionary or the like stored in the external storage device 14 and recognizes the coordinate data stored in the character coordinate data buffer 22 as a character.

In the character recognition dictionary of the external storage device 14, for example, characters are classified according to the number of strokes as shown in FIG. 4, and strokes are represented by a relative value based on the first point of writing the dictionary pattern. It is given as a point.

The character recognition unit 16 obtains a representative point of each stroke of the coordinate data string stored in the character coordinate data buffer 22 and performs matching with the recognition dictionary pattern according to the number of strokes. The one with the smallest matching difference is passed to the display unit 20 to be displayed as the recognition result, and at the same time, the handwritten character is stored in the area in the recognized character buffer 23 corresponding to the input character recognition frame. ing.

The recognized character buffer editing unit 17 scans the recognized character buffer 23 sequentially from the beginning to find a blank frame in which nothing is input, and outputs the character string delimited by the blank frame to the kana-kanji conversion buffer 24. It has become. If no blank frame is detected, no operation is performed. Since many blank frames may exist in the recognized character buffer 23, this processing is performed for all the frames of the recognized character buffer 23.

The kana-kanji conversion unit 18 is adapted to perform kana-kanji conversion processing on the character string stored in the kana-kanji conversion buffer 24. The converted character string is output to the character edit buffer 25 together with a display command in the document edit area.

The character string editing function unit 19 includes a coordinate input unit 15
The coordinate data given from is analyzed in association with the icon P on the screen, converted into an editing function name, a start point position, an end point position, etc. according to the contents instructed, and the character string edit buffer 25
It is designed to be stored in. The function is executed when the information required for the character string editing operation is prepared.

Information is also set in the character string edit buffer 25 from the kana-kanji conversion unit 18 as described above.

The display unit 20 displays the character information input from the coordinate input device 11 as the handwriting pattern as described above, and displays the characters recognized by the character recognition unit 16 and the instruction from the character string editing function unit 19. Based display device 1
It is designed to be displayed above 1.

If no blank frame is detected when the recognition character buffer editing unit 17 scans the recognition character buffer 23, the recognition frame on the screen is scrolled by a predetermined number of characters. It has become.

The external storage device 14 is a disk for storing a character recognition dictionary, a kana-kanji conversion dictionary, etc., as shown in FIG.

The operation of the document creating apparatus 10 configured as described above will be described with reference to the flowchart of FIG. 1, the operations of FIGS.

When coordinate data is input from the coordinate input device 11 (S1), it is determined whether the coordinate data is handwritten character coordinate data by the coordinate input unit 15 or coordinate data used for character string editing or the like. It is judged (S2). In this determination, the coordinate data is the character recognition frame A on the screen of the display device 12.
It is performed depending on whether it is written in 1 ... If the coordinate data is written in the recognition frame A1, ..., It is the coordinate data that constitutes a handwritten character. Therefore, until another coordinate data is input from the outside of the recognition frame A1 ... Or a fixed time elapses after the pen (not shown) is raised (S3), This coordinate data is stored in the coordinate data buffer 21 (S4). The stored coordinate data also stores the on / off state of the switch of the pen so that it is possible to know how many strokes have been input later.

When the coordinate data is stored in the coordinate data buffer 21 and there is a trimming, the contents of the coordinate data buffer 21 are once copied to the character coordinate data buffer 22 (S5). This copy is recognized by the character recognition unit 16 (S6).

During the recognition process, the recognized characters are sent to the display device 12 via the display unit 20 and displayed, and are stored in the recognized character buffer 23.

In the above description, the input of the coordinate data of the handwritten character and the recognition of the character are performed continuously, but in reality, the input of the coordinate data of the handwritten character is caused by an interrupt. Therefore, while the character is being recognized, the handwriting of the next character is displayed and the coordinate data is stored in the coordinate data buffer 21. That is why the character data is copied to the character coordinate data buffer 22 of the coordinate data buffer 21 before character recognition.

When the coordinate data input from the coordinate input device 11 is not the handwritten character data, it is determined from the coordinate data whether the conversion icon P has been pressed (S).
7). If an icon other than the conversion icon is pressed, the character string editing function unit 19 performs predetermined editing (S8). When the conversion icon P is pressed, the recognition character buffer editing unit 17 is activated to detect the blank frame in the recognition character buffer 23 as described above, and to the kana-kanji conversion buffer 24 in units separated by the blank frame. The storage is performed (S9). Then, the remaining characters are recognized in the character buffer 23.
It is edited to the left within (S10).

Now, assuming that the input of the recognition frame A1 ... Is coordinate data such as "Something is wrong" as shown in FIG. 5, the coordinate data M1, M2, M3 ... It is stored in the recognition character buffer 23 as shown in FIG.
When the conversion icon P is pressed here, only the two character strings “TOSHIBA” and “SHANAI” separated by a blank frame are output to the Yana-Kana conversion buffer 24 shown in FIG. 7, and the remaining characters are output. Is edited left-justified in the recognized character buffer 23 as shown in FIG. At this time, the last 2 "Nou"
Although there are characters, they are not output to the kana-kanji conversion buffer 24 because they are cut by the number of physical recognition frames.

Thereafter, the display unit 12 is displayed by the display unit 20.
The upper recognition frame A1 is also displayed in the upper left of the recognition frame A1 ... as shown in FIG. 9 (S11). If the recognition character buffer editing unit 17 scans and there is no blank frame in the recognition character buffer 23, the recognition character buffer 23 is simply scrolled by a predetermined number. There is no change in the content of.

Following this, the kana-kanji conversion unit 18 is activated, and the character string stored in the kana-kanji conversion buffer 24 is converted into kana-kanji and stored in the character string edit buffer 25 (S12). The kana-kanji conversion processing operates on the character string unit stored in the kana-kanji conversion buffer 24, but since the conversion result can be displayed at one time by connecting them, they are set to 1
It is stored in the character string edit buffer 25 as a result of conversion of one kana-kanji character.

When the kana-kanji conversion process is completed, the conversion result stored in the character string edit buffer 25 is displayed on the screen of the display device 12 by the display process of the display section 20 and the process returns to the beginning (S13).

The document creating apparatus of the present invention is not limited to the above embodiment. For example, punctuation marks, parentheses, or the like may be used as breaks in the blank frame of the phrase. These punctuation marks, parentheses, etc. may be used at the punctuation position where the result is determined by performing morphological analysis on the character string input during normal document creation.

Further, as the timing at which the recognition character buffer editing unit 17 is activated, the time when the user explicitly designates a stroke in the recognition frame may be used. further,
There may be a plurality of frames that can be opened when writing a word.

[0044]

As described above, the text creating apparatus according to the present invention has a coordinate input means such as a tablet input device or a pen input device, and a control means for processing handwritten characters and the like input from the coordinate input means. And a handwriting character or the like input from the coordinate input means, or a display means for displaying a character or the like processed by the control means. , A character recognition unit for recognizing handwritten characters and the like input from the coordinate input means by a character recognition frame, the characters and the like recognized by the character recognition unit are stored in a buffer memory, and the stored characters and the like are scanned. A recognition character buffer editing unit that edits each clause and stores it in the buffer memory, and a Kana-Kanji character that converts characters edited by the recognition character buffer editing unit into a Kana-Kanji mixed sentence Since the conversion unit and the display unit for displaying the characters converted by the Kana-Kanji conversion unit on the display means, it is possible to sequentially create a Kana-Kanji mixed sentence for each phrase regardless of the input stage of handwritten characters. You can Therefore, it is not necessary to be aware of the remaining handwritten characters in the recognition frame.

Further, since the recognized character buffer editing unit catches blanks, punctuation marks, parentheses, etc. of the character recognition frame as phrases of handwritten characters and edits sentences containing kana-kanji, it is easy to segment the handwriting. You can

[Brief description of drawings]

FIG. 1 is a flow chart for explaining the operation of a text creation device of the present invention.

FIG. 2 is a block diagram showing an outline of a text creation device of the present invention.

FIG. 3 is an explanatory view showing a part of FIG. 2 in detail.

FIG. 4 is an explanatory diagram showing a storage example of the external storage device of FIG.

5 is an explanatory diagram showing a display example of the display device of FIG. 2. FIG.

FIG. 6 is an explanatory diagram showing a storage example of a buffer memory in FIG.

FIG. 7 is an explanatory diagram showing a conversion example of FIG.

FIG. 8 is an explanatory diagram showing a display example of the display device of FIG.

FIG. 9 is an explanatory diagram showing a storage example of the buffer memory in FIG.

[Explanation of symbols]

 10 Text Writing Device 11 Coordinate Input Device 12 Display Device 13 Control Device 14 External Storage Device 15 Coordinate Input Unit 16 Character Recognition Unit 17 Character Recognition Buffer Editing Unit 18 Kana-Kanji Conversion Unit 19 Character String Editing Function Unit 20 Display Unit 21 Coordinate Data Buffer 22 Character coordinate data buffer 23 Recognized character buffer 24 Kana-Kanji conversion buffer 25 Character string editing buffer

Claims (2)

[Claims] 1. A coordinate input means such as a tablet input device or a pen input device, a control means for processing handwritten characters and the like input from the coordinate input means, and a handwritten character input from the coordinate input means. Etc., or a display means for displaying characters processed by the control means, and a sentence creation device by online handwritten character recognition, comprising: the control means, the handwritten character input from the coordinate input means. And the like are stored in a buffer memory, and the stored characters and the like are scanned, edited for each phrase, and stored in the buffer memory. The recognition character buffer editing unit, the Kana-Kanji conversion unit that converts the characters edited by this recognition character buffer editing unit into a sentence containing Kana-Kanji, and the Kana-Kanji conversion unit Writing device online handwriting recognition, characterized in that it comprises a display unit for displaying characters and the like on the display unit. 2. The recognition character buffer editing unit is adapted to catch blanks, punctuation marks, parentheses, etc. of a character recognition frame as a phrase of a handwritten character and edit a sentence containing Kana-Kanji characters. A sentence creation device based on the described online handwritten character recognition.