JPS61170877A - Recognizing device of hand-written character - Google Patents

Abstract

PURPOSE:To make it possible that a character writer inputs characters in accordance with his taste and personality, by setting a character frame for hand- written character input in a character input area of an input tablet and setting its size by his intention. CONSTITUTION:A prescribed form 15 is positioned and placed on the tablet surface of an input tablet 2 in accordance with a character input area 10. Square character frames 14 are printed throughout on this form 15 in plural rows and columns, and one character should be written in each character frame 14 by his hand. He selects freely and uses one of forms different in size of character frames 14 by his intention. When he writes characters in character frames 14 on the form with an input pen 13, a hand-written character recognizing device 1 recognizes characters and outputs its results to a host device 4.

Description

DETAILED DESCRIPTION OF THE INVENTION [Technical Field of the Invention] The present invention relates to a handwritten character recognition device that receives characters input by hand on an input tablet and performs dictionary matching processing to recognize the input characters.

<Summary of the Invention> The handwritten character recognition device of the present invention sets a character frame for pre-handwritten input of characters in the character input area of an input tablet, and also sets the size of the character frame according to the intention of the person writing the characters. It is configured so that it can be set as appropriate, thereby making it possible to input characters according to the preferences and individuality of the person writing the characters.

<Background of the Invention> Conventionally, a type of seed-written character recognition device has been proposed in which a plurality of character frames are set in a character input area of an input tablet for inputting a single character. Normally, these character frames are determined to a predetermined size in consideration of the accuracy of the device, etc., but since each person writing characters has their own preferences and individuality, some people writing characters may choose to make the character frame particularly small. There are other problems, such as feeling that it is cramped, and some people writing characters feel that the character frame is especially large and uncomfortable.

By the way, if these character frames are set to a smaller size, the amount of characters input per page will increase, but because the input characters will become smaller, the recognition accuracy will decrease for characters that include voiced marks or characters that have a large number of strokes. There is a risk of On the other hand, if the size of the character frame is set larger, parts such as voiced marks will naturally be written larger, which improves character recognition accuracy, but on the other hand,
There are disadvantages such as a reduction in the amount of characters input per page. However, when introducing this type of character recognition device into a specific system, some systems place emphasis on a large amount of character input, while others place importance on high character recognition accuracy. It was difficult to adapt to all these systems.

<Purpose of the Invention> An object of the present invention is to provide a handwritten character recognition device that solves the above problems at once by configuring the size of the character frame to be appropriately set according to the intention of the person writing the characters. do.

<Configuration and Effects of the Invention> In order to achieve the above object, the present invention provides an input tablet in which a character frame for inputting characters by hand in a character input area is set, and a method for specifying the size of the character frame. an input pen for handwriting characters by touching the pen tip to the input tablet left;
"i*i*azix,b:is y It was decided to provide a means for specifying and obtaining a character frame based on human character skills, and a means for cutting out the specified character frame and recognizing and processing input characters within the character frame.

According to the device of the present invention, since the size of the character frame can be set appropriately according to the preferences and individuality of the person writing in characters, the person writing in characters can perform character input work with the same feeling as normal character writing operation, and input Work efficiency improves. Furthermore, since the size of the character frame can be changed depending on the system in which this device is installed, it is possible to adapt the device to the requirements of each system each time, and the object of the invention can be achieved.

<Description of Embodiments> FIG. 2 shows an overall schematic configuration of a character processing system incorporating the handwritten literature recognition device 1 of the present invention.

The illustrated handwritten character recognition device 1 is composed of an input table 2 and a recognition processing section 3, and each of these components is electrically connected to a host device 4 by a cord line.

Here, when the handwritten character recognition device 1 is connected to a dedicated terminal for a bank, for example, the host-side device 4 refers to the dedicated terminal, that is, the "immediately superior" terminal, and the host-side device 4 in the illustrated example is In this case, CRT (Cathode Ray
The host computer main body 7 is equipped with a computer tube 5 and a keyboard 6, and a printer 8 and a floppy disk device 9 are connected thereto.

The recognition processing unit 3 includes a CPU (CentralPr
In addition to RAM (Ra
ndam AccessMemory) s ROM
(Read 0nly Men+ory), etc., and this recognition processing unit 3 controls input processing of handwritten characters, a series of character recognition processing including dictionary matching, and output processing of recognition results. be done.

The input tablet 2 has a character input area 10, a touch key area 11, and an error lamp 12 on the tablet surface.
Each of the areas 10 and 11 is formed so as to be able to sense the touch of the pen tip of a dedicated input pen 13. The character input area 10 is connected to the input pen 13 via the form 15.
A pen tip is brought into contact with the tablet surface and moved to input a desired character by hand, and a coordinate detection circuit consisting of a matrix circuit is incorporated inside the tablet surface corresponding to the character input area 10. , thereby detecting the X and Y coordinates of the pen tip that is in contact with the character input area 10.

A predetermined form 15 is positioned and placed on the tablet surface of the input tablet 2 in correspondence with the character input area 10. On this form 15, square-shaped character frames 14 are printed in series over multiple rows and multiple stages, and each character frame 1
4 allows you to handwrite and input characters one by one. In the case of this embodiment, the size of the character frame 14 is set to 5 [
Prepare in advance a first form set to 10 (m) in length and width, and a third form set to 20 (n) in length and width, and have a person fill in the characters. The structure is such that users can freely select and use any form of their own will.

After positioning and fixing any form on the tablet surface in this way, when characters are handwritten using the input pen 13 into the character frame 14 of that form, the handwritten character recognition device 1 cuts out the character frame for inputting characters. After recognizing the characters within the character frame, the recognition result is output to the host device 4 together with information specifying the character frame. In the illustrated example, this character frame identification information includes a series of character frame numbers (numbers 1, 2, and 2 in FIG. 4 (1)) set corresponding to each character frame 14.
．． 3. . . ), but the information is not limited to this, and may also be information specifying the columns and columns of the character frame 14, as shown in FIG. 4 (2), for example. Furthermore, Figure 4 (
3), when the character frame 14 is set in block units, the character frame specifying information includes the block number and the character frame number in each block (number 1 in the figure).
．． 2, 3°..., 10).

The touch key area 11 is selected and operated with the tip of the input pen 13, and is operated by character frame designation key 1 shown in FIG.
In addition to 6, there are 0 multiple 0 files for manually inputting various commands.
'ri'・71- are arranged and there are 7/. This character frame key 16 is used to specify the size of a character frame to be cut out during character recognition processing. When using the first form, the frame hand key 16A shown in FIG. When using the frame key 16B, when using the third form, use the smart key 16C, and the pen 13 respectively.
Use to perform selection operations.

The input pen 13 has a structure in which, for example, magnetic lines of force are generated at the pen tip when the pen tip touches the input tablet 2 and a predetermined writing pressure is applied. By detecting the movement locus of the character, each stroke of the input character from the stroke to the stroke is obtained as data.

FIG. 3 shows the contents of the memory in the recognition processing section 3, and a program area 17 in the figure stores a series of programs for character recognition processing.

The work area 18 includes a coordinate counter 19, a coordinate storage area 20, a substroke counter 21, a direction code storage area 22, a stroke counter 23, a stroke code storage area 24, a character frame number storage area 25, a character frame boundary value storage area 26, and a flag. It has a setting area 27 etc.
The coordinate counter 19 is entered by the input pen 1 on the input tablet 2.
The coordinate storage area 20 stores the coordinates of each pen position of the input pen 13 moving on the input tablet 2, and the substroke counter 21 stores the 8-direction code containing the character stroke (Fig. 6). The direction code storage area 22 stores the 8-direction code of each sub-stroke (described later) that makes up a character stroke, and the stroke counter 23 stores the number of character strokes that make up a character. The area 24 contains a code that specifies the type of stroke input, and the character frame number storage area 25 contains character frame number data for character input.
The character frame boundary value storage area 26 contains coordinate data XMAX indicating the boundary value of the character frame related to character input.

XMIN+YMAX*YMfM is the flag setting function, and a flag (hereinafter referred to as "character output flag") indicating whether or not the character recognition result has been output to the host device 4 is set in the rear 27. In addition, the character frame type storage area 28 stores character frame data that defines the size of any character frame set for each of the first to third forms, and the stroke recognition dictionary area 29 stores character frame data. In the character recognition dictionary area 30, there is reference data for all constituent strokes and reference data for a character composed of one stroke (for example, the number "2"). Standard collation data for constituent characters (for example, the number "5") are stored.

FIG. 1 shows the control operation of the recognition processing section 3.
First, in step 31, the recognition processing unit 3 is initialized, and in the next step 32, data specifying the size of the character frame set in the second form (referred to as "second character frame data") is stored in the character frame type storage area. 28. In the next step 33, it is determined whether or not a command has been input from the touch key area 11 of the input tablet 2.
If the determination is "S", the command code is sent to the host device 4 (step 34).If the command input is an input start command that requests tablet input, the memory is stored in the next step 36. The contents of the work area 16 are cleared.

On the other hand, if any character frame designation key 16 is pressed in the touch key area 11 and a command to designate the type of character frame is input, step 35 is "NO";
Step 37 becomes YES' and the process proceeds to step 38.

In this step 38, for example, when the frame hand key 16A of the character frame designation keys 16 is pressed, the first character frame data that defines the size of the character frame set in the first form is also changed to the frame input key 16C. When is pressed, the third character frame data that defines the size of the character frame set in the third form is set in the character frame type storage area 28, respectively.

In this way, when the pen tip of the input pen 13 contacts the character input area 10 of the input tablet 2 via the form 15 and a predetermined writing pressure is applied, "frame 7)'A"i゛?
Jt7)! ! II! ! "Pa°"・X f 77" 40
(D.

The determination "Is it written?" becomes "YES" and the process proceeds to the next step 41. In this step 41, after the coordinates of the writing point are detected by the coordinate detection circuit, cutting out of a character frame and calculation of a character frame number are executed using the coordinate data.

FIG. 7 shows a subroutine that is called in conjunction with step 41. First, in step 110 of FIG. 7, the recognition processing section 3 reads the character frame data D and the like that are centered in the character frame type storage area 28.

The DV (shown in FIG. 8) is read and set in a register in the CPU.

Now, suppose the character frame data Dx and Dv are each 15 [Tsuru]
, the coordinate X of the writing point P is 100 [Tsuru], and the coordinate Y is 1
If it is 60 (mm), the next step 111.112
, by dividing each coordinate X, Y by the character frame data Dx, Dv and rounding up the solution, the numbers n, m of the column and column of the character frame 14 related to the writing point P (in this case, the column number n is "7", stage number m is rill)
(See formula 00 below).

Dx 15 The column and column number data of the character frame 14 are stored in the character frame number storage area 25 either as they are or after being converted into a series of character frame number data (for example, as shown in FIG. 4(1)).

Next, in step 113, character frame data DX is multiplied by the column number to obtain character frame boundary value data (See 00 type).

XMAX=Dx Xn=15X7=105
(m) ・・・・”■XMIN =X, ax to D-
405-15.90 [Tsuru]... ■Furthermore, in the next step 114, similar calculations (see formula 00 below) are executed to obtain character boundary value data YMAX, Yold.

Yptax = Dv Xm = 15X11 = 165 (
am) -=■YMIN=YMAX-Dy=1
65-15=150 (Tsuru)...■Thus, these boundary value data XMAN * XMIN + YMAX +
After YMIN is stored in the character frame data area 26, the subroutine shown in FIG. 7 is completed, and the process returns to the main routine shown in FIG.

Returning to the main routine of FIG. 1, first at step 42,
After the contents of the coordinate counter 19 and the stroke counter 23 in the work area 18 are cleared, in step 43, the subroutine for stroke input processing shown in FIG. 9 is called and executed.

Now, suppose that the first stroke of a character (for example, the number "4") consisting of the first and second character strokes is written in the character frame 14. First, step 7 in FIG.
1, it is determined whether the writing point in step 40 is within the character frame 14, and if the determination is "YES", the contents of the coordinate counter 19 are incremented by 1, and the coordinate detection circuit in the input tablet 2 The detected pen position coordinates are stored at a predetermined location in the coordinate storage area 20 corresponding to the contents of the coordinate counter 19 (steps 72 and 73).

When the pen tip moves and a character stroke is drawn within the same character frame 14, the determination in step 74 is NO'', and the process returns to step 71 to ask, ``Is it within the same character frame?''
The determination becomes "YES", and as above, the coordinate counter 1
9 is added and the pen position coordinates are stored (steps 72, 73).

Note that the determination in step 71 is based on the pen position coordinates (X, Y
) and the boundary value data XMAX, X□, etc. set in the character frame boundary value storage area 26.

This is done by comparing Ysax and YMIN, and when the multi-values of X and Y satisfy the following formula 00, the determination in step 71 becomes "YES".

X□8≦X≦X WAX・・・・・・■YMIN≦Y
, 5 YMAX...■ Steps 71 to 73 above
The processing operation is repeatedly executed every time the pen tip position passes a coordinate point, and when the pen tip leaves the input tablet 2 due to the completion of the input of the first stroke, the determination in step 74 becomes "YES", and step Proceed to 75.
- In step 75, points where the coordinates of the stroke input abruptly change (for example, points where they change by 90 degrees) are detected as changing points, and the character stroke is separated at each changing point and divided into a plurality of sub-strokes.

10(1) and (2) show examples of substroke division for characters r2J r5J, in which black dots 65 are writing points, black dots 66 are writing separation points, white points 67 are change points, Straight lines 68 each indicate a substroke.

Each of the above-mentioned substrokes is converted into a direction code shown by numbers 1 to 8 in FIG. Then, in the following step 77, the direction code of each substroke is stored in the direction code storage area 22.

FIG. 11 shows an example of direction code conversion for the first stroke of the number "5", and in the figure, ■■■■■■■■ indicates the direction code of each sub-stroke. In this code conversion, when adjacent direction codes are continuous (in the illustrated example, the portions ``■'' to ``■''), a so-called rounding process is performed to make the direction code ``■■■'' associated with a long stroke representative.

Figure 12 shows the direction code string of the number "5" after rounding, the first stroke has a direction code of ■■■■, and the second stroke has a direction code of ■. .

Next, returning to the example of number "4", the first stroke input is checked against the contents of the stroke recognition dictionary area 29 in step 78, and a direction code string matching the direction code string of the first stroke input is determined. It is checked whether there is standard data with Then, when matching data exists, the determination of "Is it a match?" in step 79 becomes "YES", and after incrementing the stroke counter 23 by 1 in step 80, in the next step 81, the character stroke related to the standard data is calculated. A code for specifying a stroke (hereinafter referred to as a "stroke code") is stored in the stroke code storage area 24 according to the contents of the stroke counter 23.
Set to the specified location and return to the main routine. On the other hand, if the standard data related to matching does not exist in the dictionary area 29, the result of step 79 is "No", and in this case, the process returns to the main routine as an input error.

If the pen tip protrudes outside the character frame 14 during the process of drawing a character stroke, the determination of "Are they in the same character frame?" in step 71 will be "NO" and an error sound will be generated in step 82. In this case, when the pen tip is released from the input tablet 2, the next step 83 is "YES".
This causes an input error and returns to the main routine.

In this way, if the step 79.83 returns as an input error, the determination in step 44 in FIG. 1 is "Y".
ES'', and in steps 45 and 46 an error sound is generated and the error lamp 12 is lit.

On the other hand, if the input is completed and the main routine is returned to, the determination in step 44 is "No", and then in step 47, the stroke input so far (in the example with the number "4", only the first stroke) is determined. It is checked whether standard data matching the characters consisting of (input completed) exists in the dictionary area 29,30. Number "
4", the first stroke alone does not constitute a character, so the determination in step 48 "Is it a match?" is "NO".
”, and in the next step 49, the character frame number set in the character frame number storage area 25 and the error code indicating a matching mismatch are sent as a pair to the host device 4, and then in step 50, the character frame number set in the character frame number storage area 25 is sent to the host device 4. The contents of 27 are cleared.

If the input character consists of only the first stroke (for example, the number "2"), the determination in step 48 becomes "YES", and the character frame number and its recognized character code are determined in step 51. After the pair is sent to the host device 4, a character output flag "1" is set in the flag setting area 27 in step 52.

The next steps 53 and 54 are for a certain period of time (e.g. CPU
Within (71-(?C2 ~ Set 0 time for about 5 seconds)
1), it is checked whether there is any writing with the input pen 13 in the character input area 10. In the case of the example of the number "4", since the first character of the second stroke is written in the same character frame 14, the determination in step 53 "Is it time over?" is "NO", and the determination in step 54 "arrival" is "NO". "Is it a brush?" judgment is "YIES", and step 55 "Are they in the same character frame?"
The determination becomes “YES” and the process proceeds to step 43, where the second
The subroutine shown in FIG. 9 is executed for the stroke.

If the second stroke is not input within the set time in the standby state of steps 53 and 54, the determination of "Is it time over?" in step 53 is "YES".
”, the process advances to step 56, and then the host side device 4
It is checked whether the recognized character code has been output to the flag setting area 27, that is, whether the character output flag "1" has been set in the flag setting area 27. In this case, the determination in step 56 is N
O”, so in steps 57 and 58 an error sound is generated and the error lamp 12 is lit to inform the character entry person that the input of the first stroke is invalid, and then the process waits for the next character entry. (step 40).

Note that if input of all strokes constituting a character has been completed, steps 57 and 58 are not executed, and the input standby state of step 40 is entered.

Thus, in the input process for the second stroke of the number "4", in step 47 "Verification match?" ” is judged “Y”
ES'', and at this stage the recognized character code is sent to the host device 4 together with the character frame number (step 51).

In the character input process, if you want to modify the input characters that have been recognized, you can place the pen tip in the character frame 14 in which the character to be modified is written, and write a new character by hand. . In this case, when the process moves to character correction immediately after the completion of inputting one character or one stroke, step 53 becomes "NO", step 54 becomes "YIES", step 55 becomes "NO", and the process proceeds to step 59. If the character output flag is not set, step 60
．． ．． After generating an error sound and lighting the error lamp 12 in step 61 to inform the character entry person that the input of the first stroke is invalid, the process proceeds to step 41, where character correction processing is performed based on the subroutine of FIG. is executed.

FIG. 13 shows the contents of the memory in the host device 4. In the figure, a program area 141 stores a program for receiving and processing commands and character recognition data sent from the handwritten character recognition device 1, as well as a series of programs related to system processing, and a form format information writing area. 142 stores the format of the form 15 installed on the input tablet 2.

The work area 143 includes a received character storage area 144, a character frame number storage area 145, and a character frame type storage area 14.
6 etc., the received character storage area 143 contains the recognized character code sent from the handwritten character recognition device 1, and the character frame number storage area 145 contains the character frame number associated with the received character, and the character frame type storage area At 146, information specifying the character frame size is entered. Also character storage area 1
Reference numeral 47 is for storing received characters one after another at addresses corresponding to the value of the character frame number.

FIG. 14 shows the control operation of the host side device 4. First, initialization is performed in step 91, and the contents of the work area 143 of the memory are cleared. Next, the contents of the form format information storage area 142 are read out and C
After the format of the form is displayed on the screen of the RT 5, reception of information from the terminal (including the handwritten character recognition device 1) is permitted (step 92.93).

At this stage, if the handwritten character recognition device l transmits a recognized character code or error code and its character frame number information as a pair, and this is received by the host device 4, the determination in step 94 "Received?" “YlliS”, step 95 [Is the received content a command? ” is “NO”
”, and the received information is stored in the received character storage area 144 and the character frame number storage area 145, respectively.

If a command is received under the reception acceptance state, step 95 becomes "YBS", and reception from the terminal is prohibited in step 96. If the command is a command that specifies the character frame size, step 97 becomes @YHS'', and step 9
8, the character frame size specification information is stored in character frame type storage area 1.
If the command is any other command, the process corresponding to the command is executed in step 99.

The next step 100 is to determine whether or not the received information is an error code. In the embodiment with the number "4", the error code is detected on the host side at the end of the first stroke recognition. As already mentioned, it is transmitted to the device 4 (step 49 in FIG. 1).

Therefore, in this case, the determination at step 100 is "YES"
In step 103, the display position of the CRT 5 corresponding to the received character frame number is cleared, and in the next step 104, the character storage area 14 corresponding to the received character frame number is cleared.
Address 7 is cleared.

On the other hand, at the end of the recognition of the second stroke of the number "4", the recognized character code is sent to the host device 4 along with the character frame number (step 51 in FIG. 1), so in this case step 100 The determination is "NO", and in step 101, the CR corresponding to the received character frame number is
The character corresponding to the recognized character code (in this case, the number "4") is displayed at the display position of T5, and the step 1
02, the character storage area 14 according to the character frame number
The received character code is stored at address 7.

The series of processes described above is repeatedly executed each time there is a reception, and as a result, the received characters are displayed one after another on the CRT 5, and the received information is stored in the character storage area 147 (step 101. 102).

Also, the above applies not only when inputting new characters, but also when inputting new characters.
The same applies to character correction; in this case as well, the corrected character is sent to the host device 4 together with the character frame number involved in the correction, so that the corrected character is correctly displayed at the character correction position on the CRT 5.

In the above, the character frame designation key 16 is provided in the touch key area 11 of the input tablet 2, and the character frame size can be changed by operating one of the frame hand keys 16A, frame center key 16B, and frame insert key 16C with a pen. As already mentioned, this is an example of setting.

15 and 16 show an embodiment in which the character frame size is specified from the keyboard 6 of the host side device 4, and the first
5 shows the control flow of the recognition processing section 3, and FIG. 16 shows the control flow of the host side device 4.

In FIG. 15, first, in step 120, the recognition processing unit 3
is initialized, and in the next step 121 the host side device 4
Reception from is permitted. When the character frame size specification information is received from the host device 4, the determination of “Received?” in step 122 becomes “YES”, and reception from the host device 4 is prohibited, and the received information is It is stored in the character frame type storage area 28 of the memory (steps 123 and 124>.The next step 125 is to determine whether or not there is a command input from the input tablet 2.
@YES', send the command code to the host device 4, and if the command is an input start command that requests tablet input, step 1
Clear the contents of the memory work area 16 in step 28,
The process moves to character input processing similar to that shown in FIG. Note that the following steps 39 to 61 are the same as the flow shown in FIG. 1, and the corresponding steps are designated by the same reference numerals and the explanation thereof will be omitted.

On the other hand, in the host side device 4, initialization is first performed at step 130 in FIG.
Guide characters are displayed on RT5 to prompt the user to specify the character frame type. Then, when the character frame is specified as large, medium, or small by key operation on the keyboard 6, the determination of ``Is there input?'' in step 132 becomes ``YES'', and the next step 1
At 33, the character frame designation information is transmitted from the host side device 4 to the handwritten character recognition device 1, and the character frame type is stored in the character frame type storage area 146. After the report is displayed on the screen of the CRT5, 0 reception from the terminal is allowed! (Xy 1 knob 134
．． 135). If a command is received in this state, both steps 136 and 137 become YES, and after step 138 prohibits reception from the terminal, the process corresponding to the command is executed in step 139.

On the other hand, when a recognized character code or an error code is received from the handwritten character recognition device 1 under the reception acceptance state, step 137 becomes "NO" and the process proceeds to step 100. Step 100 and subsequent steps are the same as those in FIG. 14, and corresponding steps are given the same reference numerals and their explanations will be omitted.

[Brief explanation of the drawing]

FIG. 1 is a flowchart showing the control operation of the handwritten character recognition device according to the present invention, FIG. 2 is an external view showing the overall configuration of the handwritten character recognition device, FIG. 3 is a diagram showing the memory map of the handwritten character recognition device, and FIG. Figure 4 is a diagram showing an example of character frame number setting, Figure 5 is an enlarged view of the touch key area, Figure 6 is a diagram to explain the 8-direction code, and Figure 7 is character frame cutting and character frame number calculation. FIG. 8 is a flowchart showing the subroutine of the process, FIG. 8 is a diagram for explaining the method of character extraction and character frame number calculation, FIG.
) (2) is a diagram showing an example of substroke division for characters r2J r5J, Figure 11 is a diagram showing an example of direction code conversion for the first stroke of character "5", and Figure 12 is a diagram showing an example of character "5" after rounding. 13 is a diagram showing the memory map of the host side device, FIG. 14 is a flowchart showing the control operation of the host side device, and FIG. 15 is a diagram showing the handwritten character recognition device in another embodiment. Flowchart showing the control operation. FIG. 16 is a flowchart showing the control operation of the host side device in another embodiment. 1...Handwritten character recognition device 2...Input tablet 3...Recognition processing section 10...Character input area 13...Input pen 14・・・・・・Character frame "+,,a" 7λ stroke length 6 showing Wataru 4i
7 ノ, , , ++3ctt, z, tb *, t2・
・Input fugulet 3, , , t, =, sit (menu i heat plρ1
1. Kaeri enters the market! 100. 8 l to j) L...k sho l La N4=Otsu ★Cloud frame number g 誼e い い Ｇ Ｇ Ｇ Ｇ Ｇ Ｇ, j Kota attack + key area #payer map” A153 Y, Stoi 躬釆 b memory mug Mo1 no 2z Otoka Yami Kudo 11th Σ

Claims (4)

[Claims] (1) An input tablet on which a character frame for inputting characters by hand in the character input area is set, a character frame designation section for specifying the size of the character frame, and a pen tip touching the input tablet. and a recognition processing section that takes in handwritten input characters from the character input area of the input tablet and executes character recognition, and the recognition processing section receives characters from the character frame designation section. A means for capturing frame designation information, a means for identifying and obtaining a character frame for character input based on the character frame designation information, and a means for cutting out the specified character frame and recognizing and processing input characters within the character frame. A handwritten character recognition device comprising: (2) The handwritten character recognition device according to claim 1, wherein the character frame designation section is provided in an input tablet. (3) The handwritten character recognition device according to claim 1, wherein the character frame designation section is provided in a keyboard of a host device. (4) The handwritten character recognition device according to claim 1, wherein the recognition processing section includes a computer including a CPU and a memory.