JPS61182184A - Device for recognizing hand-written character - Google Patents

Abstract

PURPOSE:To execute without fail and easily the positioning of a slip format by positioning a slip format by the contacting operation of the input pen for the input tablet. CONSTITUTION:For the format of a slip 15, for example, a measure-shaped character frame 14 is in a series printed and formed over the plural columns and plural stages, and the character is inputted by the hand-writing up to one character in respective character frames 14. The slip is positioned and fixed on the tablet surface, the slip format for a character input area 10 is set and operated, and thereafter, when the character is written by the hands by using an input pen 13 into character frames 14 of the slip, the character frame loaded to the character input in a hand-writing character recognizing device 1 is cut out, the character in the character frame is recognized, and thereafter, the recognizing result is outputted to a host side device 4 together with the information to specify the character frame. The character frame specifying information may be a series of the character frame number set in accordance with respective character frames 14 and for example the information may be the information to specify the column and stage of the character frames 14.

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 makes it possible to align the input tablet and the form by simply touching the input pen to the form on the input tablet. This simplifies the alignment work and improves the success rate of character recognition processing.

<Background of the Invention> Conventionally, this seed potato character recognition device uses a system in which a predetermined form is positioned and fixed on an input tablet, and characters are handwritten into the form using an input pen. Normally, this form is printed in a predetermined format that includes multiple character frames, and for example, each time a character is addressed in each character frame, the characters within that frame are cut out. Character recognition processing is now being executed. Therefore, in conventional devices, the format of the form is stored in advance as fixed data inside the device or in the host device, and when input characters are imported, this fixed data is loaded and the format of the form is stored in the character input area of the input tablet. By setting , the above-mentioned input characters are cut out.

However, with this method, if the form is not properly aligned on the input tablet, the form format set in the character input area will be misaligned with respect to the format of the form, leading to misreading or unreadable characters. This becomes a factor that reduces the success rate.

Therefore, in order to ensure and easily align the forms, positioning lines for form alignment are printed on the tablet surface of the input tablet, and positioning frames are attached. Input tablets are often misaligned due to variations in the manufacturing process, making it difficult to always achieve accurate alignment.

In this way, after positioning and temporarily fixing the form on the input tablet, the person filling in the characters writes the characters "kawa" within the character frame that constitutes the form format in the manner shown in FIGS. 21 (1) and (2). and ``san'' are entered, and whether or not the alignment is accurate is determined based on whether or not these character inputs are correctly recognized.

However, with this method, it is necessary to repeat the above-mentioned character entry work while moving the form in accordance with the direction of misalignment, making the work of aligning the form complicated and time-consuming, and placing an extremely heavy burden on the person completing the form. It's a big thing.

<Purpose of the Invention> The purpose of the present invention is to provide a handwritten character recognition device that can reliably and easily align the form format between an input tablet and a form, in order to solve the above problems. do.

<Structure and Effects of the Invention> In order to achieve the above object, the present invention includes an input tablet on which a form having a predetermined format is positioned on a character input area, and a pen tip brought into contact with the form on the input tablet. In the handwritten character recognition device, the handwritten character recognition device is equipped with an input pen for handwriting characters by hand, and a recognition processing section that takes in handwritten input characters from the character input area of the input tablet and executes character recognition. A means for capturing the coordinates of the pen position brought into contact with the form on the input tablet as the base point coordinates before starting, and a means for setting the format of the form for the character input area based on the base point coordinates to create a link between the input tablet and the form. It was decided to include means for performing position alignment and means for cutting out handwritten characters from the character input area based on the set form format and performing character recognition processing.

According to this invention, it is possible to align the form format by touching the input pen with the input tablet, which simplifies and speeds up this type of alignment work, and greatly reduces the workload of the person filling out characters. . In addition, since the position of the form format is perfectly aligned, there is no misreading or unreading of input characters due to misalignment of the form format, and the success rate of the device is greatly improved, achieving the purpose of the invention. It has a remarkable effect.

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

The illustrated handwritten character recognition device 1 is composed of an input tablet 2 and a recognition processing section 3, and each of these components is electrically connected to a host device 4 via a cord line. Here, the host side device 4 refers to the dedicated terminal, that is, the "immediately higher level" when the handwritten character recognition device 1 is connected to a bank dedicated terminal, for example, and refers to the host side device in the illustrated example. 4, CRT (Cathode RayTub
e) A printer 8 and a floppy disk device 9 are connected to a host computer main body 7 equipped with a printer 5 and a keyboard 6.

The recognition processing unit 3 includes a CPU (CentralPr
RAM (R
andamAccess Memory), ROM
The 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 on the tablet surface. Touch key area 11 and error lamp 12
Each of the areas 10.11 is formed so as to be able to sense the touch of the pen tip of the dedicated input pen 13. The character input area 10 is connected to the input pen 1 via the form 15.
Touch the pen tip in step 3 to the tablet surface and move it,
This is for inputting desired characters by hand, and a coordinate detection circuit consisting of a matrix circuit is built into the inside of the tablet surface corresponding to the character input area 10, thereby detecting the position of the pen tip in contact with the character input area 10. Detect the X and Y coordinates.

Form positioning means is provided on the tablet surface of the input tablet 2 in correspondence with the character input area 10, and a form having a predetermined format is positioned and arranged in accordance with this positioning means. Note that this positioning means may be a positioning line printed on the tablet surface, or may be a positioning frame pasted on the tablet surface.

In the case of the illustrated example, the format of the form 15 is formed by printing a series of square-shaped character frames 14 in multiple rows and multiple stages, and characters are input by hand in each character frame 14 one by one. ing. In this embodiment, the character frame 14
A first form whose size is set to 5 [crane] in length and width,
The second form is set to 10 (fl) each in the vertical and horizontal directions, and
A third form set to 0(m) is prepared in advance, and the person filling in the characters can freely select and use any of the forms at his or her own will.

After positioning and fixing one of the forms on the tablet surface and setting the form format for the character input area 10 using the method described later, the character frame 1 of that form is
4. When a character is handwritten using the input pen 13 in the input pen 13, the handwritten character recognition device 1 cuts out the character frame for inputting the character, recognizes the character within the character frame, and then converts the recognition result into the character frame. It is output to the host device 4 along with the identifying information. This character frame specifying information may be a series of character frame numbers set corresponding to each character frame 14, or may be information that specifies, for example, the column and column of the character frame 14.

The touch key area 11 is selected and operated with the tip of the input pen 13, and has a plurality of function keys arranged therein for inputting various commands. Note that a character frame specification key can be provided in this touch key area 11 for specifying the character frame size to be cut out (large, medium, or small) during character recognition processing, but in the case of this embodiment, this type of character frame The designated key is arranged in the keyboard 6 of the host device 4, and the designated key is located in the first . Second
．． Among the third forms, one of the keys is selectively operated depending on the form to be used.

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 moving locus of the lines of magnetic force in the character input area 10, each stroke of the input character from writing to writing is obtained as data.

FIG. 3 shows the contents of the memory in the recognition processing section 3, and a program area 16 in the figure stores a series of programs for character recognition processing. The work area 17 includes a coordinate counter 18, a coordinate storage area 19, a substroke counter 20, a direction code storage area 21, a stroke counter 22, a stroke code storage area 23, a character frame number storage area 24, and a character frame boundary value storage area 25.
, the flag setting area 26, etc.

Among these, the coordinate counter 18 stores the number of coordinate points that the input pen 13 has passed on the input tablet 2, and the coordinate storage area 19 stores the coordinates of each pen position of the input pen 13 as it moves on the input tablet 2. The number of 8-direction codes (shown in FIG. 6) included in a character stroke is stored in the direction code storage area 20, and the 8-direction code of each sub-stroke (described later) that constitutes the character stroke is stored in the stroke counter 22. indicates the number of character strokes that make up a character, the stroke code storage area 23 contains a code that specifies the type of stroke input, and the character frame number storage area 24 contains the number data of the character frame involved in character input, and the character frame boundary. The value storage area 25 contains coordinate data XMA31 + indicating the boundary value of the character frame for character input.
The flag setting area 26 stores flags (hereinafter referred to as "character output flags") indicating whether or not a character recognition result has been output to the host device 4.

Further, the character frame type storage area 27 stores character frame data that defines the size of any character frame set in each of the first to third forms, and the base point coordinate storage area 28
The base point coordinates (described later) of the form format set in the character input area 10 are stored in . Furthermore, in the stroke recognition dictionary area 29, standard data for comparison of all the strokes that make up a character, standard data for comparison of a character made up of one stroke (for example, the number "2"), and character recognition In the dictionary area 30,
Characters composed of two or more strokes (for example, the number “
5") are respectively 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, reception from the host device 4 is permitted.

Now, in the host device 4, when any character frame designation key on the keyboard 6 is pressed, this character frame designation information is received by the recognition processing unit 3, and the determination in step 33 is "
YES". Thereby, in step 34, reception from the host device 4 is prohibited, and in the next step 35, the character frame designation information is stored in the character frame type area 27.

The next step 36 is the operation for setting the form format for the character input area 10 of the input tablet 2, specifically, the point ( which becomes the standard of the @ form format).
Hereinafter, it is determined whether or not there has been an operation for setting a base point (hereinafter referred to as a "base point").

FIGS. 5 to 8 show examples of base point position settings in various document formats. FIG. 5 shows an example of a format having nine columns and three columns of character frames 14, in which the base point Q is set in the first character frame 14A located at the left end of the first column. FIG. 6 shows an example of a format having character frames 14 in seven columns and three columns (however, the first column is four columns), and the base point Q is set in the first character frame 14B located in the center of the first column. be. Figure 7 shows a format with 7 columns and 2 columns of character frames, and the last character frame 14C located at the right end of the second column.
This is an example in which the base point Q is set at . Figure 8 shows a format in which there are two blocks of 8-column, two-column character frames, and the first character frame 14D is located at the left end of the first column of each block.
+ and base point Ql at 14Dt, respectively.

This is an example in which Q2 is set.

In this base point setting operation, as shown in FIG.
3 is held vertically and the pen tip touches the base point Q, but the method is not limited to this, as shown in Fig. The input pen 13 may be held in a natural writing posture with an inclination (Qy is an inclination in the front-back direction), and the pen tip may be brought into contact with the position of the base point Q in this state.

However, in the latter method, as shown in FIG. 11, the format f2 set in the character input area 10 tends to shift toward the lower right direction in accordance with the inclinations Qx and Qy with respect to the format f+ of the form.

Thus, returning to FIG. 1, when there is a writing motion for setting the base point, the determination of "Drawing?" in step 36 is "YE".
S'', and after the coordinates of the writing point (base point) are detected by the coordinate detection circuit, the base point coordinate data is stored in the base point coordinate storage area 28 of the memory (step 37
). Then, in the next step 38, a confirmation sound indicating the completion of the base point setting operation is emitted, and then, in step 38, this base point coordinate data is transmitted to the host side device 4.

In the next step 40, it is determined whether a command has been input from the touch key area 11 of the input tablet 2. If the determination is "YES", the command code is transmitted to the host device 4 (step 41). ). If the command input is an input start command that requests tablet input, the determination in step 42 is "YH
3'', and in the next step 43, the contents of the work area 17 of the memory are cleared.

In this way, when the pen tip of the input pen 13 comes into contact with the character input area 10 of the input booklet 2 via the form 15 and a predetermined writing pressure is applied, the determination of "Is there a command input?" in step 44 is NO", and step 45 The judgment of “Is it painted?” is “
YES" and the process proceeds to the next step 46. In this step 46, after the coordinates of the writing point are detected by the coordinate detection circuit, the coordinate data and the base point coordinate data are used to cut out a character frame and, Calculation of character frame number is executed.

FIG. 12 shows a subroutine called in conjunction with step 46. First, in step 110 of FIG. (shown in Figure 13) and set it in a register in the CPU.

Now, suppose the character frame data Dx and Dy are each 15 [Tsuru]
, the coordinates (X, Y) of the writing point P are (100, 160)
(However, the unit of coordinates is (n)), the coordinates of base point Q (
If Xo, Yo) is (50°230), then at boxwood steps 111°112, the difference in each coordinate (x
-xo).

By dividing (Ya Y) by the data Dx, Dv and rounding up the solution, the column and column numbers n and m of the character frame 14 related to the writing point P (in this case, the column number n is "4")
, stage number m is "5") (see formula 00 below).

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.

Next, in step 113, the character frame data DX is multiplied by the column number and the base point coordinate X0 is added to obtain character frame boundary value data XM□.
is subtracted to obtain character boundary value data X14IN (see formula 00 below).

XIIAX = Dx X n + XO=15X 4
+50=110 (Tsuru) ......■ XMIN = XMAX DX =110 15=9
0 (m)...■ Further, in the next step 114, the following calculation (see formula 00 below) is similarly executed to obtain character frame boundary value data YMAX*YMIN.

Yxax=Yo D, xm=230 15X5=1
55 (tm)...■ YMIN = YMAX -Dv =155-15=1
70 (Tsuru)...■Thus, these boundary value data XM
A M + Xl, lI N + YMAX,
After YMIN is stored in the character frame boundary value storage area 25, the subroutine of FIG. 12 is completed and the process returns to the main routine of FIG.

Returning to the main routine in FIG. 1, first at step 47,
After the contents of the coordinate counter 19 and the stroke counter 22 in the work area 17 are cleared, in step 48, the subroutine for stroke input processing shown in FIG. 14 is called and executed.

Assuming 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, in step 71 of FIG. The writing point in step 45 is character frame 14
It is determined whether or not it is within the range, and if the determination is "YES", the contents of the coordinate counter 18 are incremented by 1, and the input tablet 2 is
The pen position coordinates detected by the coordinate detection circuit in the pen are stored at a predetermined location in the coordinate storage area 19 corresponding to the contents of the coordinate counter 18 (steps 72 and 73). Then, when the pen tip moves and a character stroke is drawn within the same character frame 14, the determination of "Is it a separation of strokes?" in step 74 is "
NO", the process returns to step 71, and the determination of "Are they in the same character frame?" becomes "YES", and as before, the coordinate counter 18
is added and the pen position coordinates are stored (step 7).
2.73).

Note that the determination in step 71 is based on the pen position coordinates (X, Y
) and the boundary value data set in the character frame boundary value storage area 25, XMAXIXMIN, YMAX,
This is done by comparing YMIN, and when each value of X and Y satisfies the following formula 00, the determination in step 71 becomes "YES".

XMIN≦X≦X, AX・・・・・・■Y old, ≦Y≦Y
I□・・・・・・■ The processing operations in steps 71 to 73 above are repeatedly executed every time the pen tip position passes a coordinate point, and the pen tip separates from the input point press 2 when the input of the first stroke is completed. At this point, the determination in step 74 becomes "YES", and the process advances to step 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 divided into a plurality of sub-strokes at each changing point.

Figures 5 (1) and (2) show examples of substroke division for characters r2J r5J. In the figures, black dots 67 are writing points, black dots 68 are writing separation points, and white dots 69 are changing points. , straight line 7o indicate sub-strokes, respectively.

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 21.

FIG. 16 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 17 shows the direction code string of the number "5" after rounding, where 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 When matching data exists, the judgment of "Is it a match?" in step 79 becomes @YES", and after incrementing the stroke counter 22 by 1 in step 80, in step 81, the character stroke related to the standard data is A code for specifying a stroke (hereinafter referred to as a "stroke code") is stored in the stroke code storage area 23 according to the contents of the stroke counter 22.
Set to the specified location and return to the main routine. On the other hand, if the standard data related to -.does not exist in the dictionary area 29, the result in 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, due to the irregular writing of the pen tip from the input tablet 2, the next step 83 is "YES".
This results in an input error and the process returns to the main routine.

In this way, if the step 79.83 returns as an input error, the determination in step 49 in FIG. 1 is "Y".
ES'', an error sound is generated in steps 50 and 51, and the error lamp 12 is lit.

On the other hand, when returning to the main routine due to completion of input, the determination in step 49 is Nθ'', and then in step 52, the stroke input so far (in the example with the number "4", only the first stroke is input) It is checked whether standard data matching the character consisting of "Complete" exists in the dictionary area 29.30. Number "
4", the first stroke alone does not constitute a character, so the determination of "Is it a match?" in step 53 is "N
O'', and in the next step 54, the character frame number set in the character frame number storage area 24 and an error code indicating a matching mismatch are sent as a pair to the host device 4, and then a flag is set in step 55. The contents of area 26 are cleared.

If the input character consists of only the first stroke (for example, the number "2"), the determination in step 53 becomes "YES", and the character frame number and its recognized character code are determined in step 56. are sent as a pair to the host device 4, and then a character output flag "1" is set in the flag setting area 26 in step 57.

The next steps 58 and 59 are for a certain period of time (e.g. CPU
It is checked whether or not there is writing with the input pen 13 in the character input area 10 within a period of time (about 2 to 5 seconds is set in the timer). In the case of the example with the number "4", the second stroke is written in the same character frame 14 in succession, so the determination in step 58 "Is it time over?" is NO'', and the determination in step 59 "Is it written?" The determination in step 60 is "YES", and the determination in step 60 is "YES" in step 48, and the process proceeds to step 48, where the subroutine shown in FIG. 14 is executed for the second stroke.

If the second stroke is not input within the set time in the standby state of steps 58 and 59, the determination of "Is it time over?" in step 58 is "YES".
”, the process advances to step 61, and then the host side device 4
It is checked whether or not the recognized character code has been output to, that is, whether the character output flag "1" has been set in the flag setting area 26. In this case, since the determination in step 61 is "NO", in steps 62 and 63 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. After that, it waits for the next character input (step 45). Note that if input of all strokes constituting a character has been completed, steps 62 and 63 are not executed and the input standby state of step 45 is entered.

Thus, in the input process for the second stroke of the number "4", the determination of "Verification match?" in step 48 is "Y".
ES'', and at this stage the recognized character code is sent to the host device 4 together with the character frame number (step 56).

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 proceeding to the character correction process immediately after completing input of one character or one stroke, step 58 becomes "No", step 59 becomes "YES", step 60 becomes "NO", and the process proceeds to step 64. If the output flag is not set, ST, PRO 5, 6
6, 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 proceeds to step 46, where character correction processing is performed based on the subroutine of FIG. 14. is executed.

FIG. 18 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. In 142, the format of the form 15 to be placed on the entry form 2 is stored.

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 In 146, character frame size designation information is set. 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. 19 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 step 9
2, the subroutine shown in FIG. 20 is called to execute processing related to setting the form format.

(Details will be explained later). As a result, the predetermined form format is displayed on the screen of the CRT5, and then the terminal (
(including the handwritten character recognition device 1) is permitted (steps 93 and 94).

At this stage, if the handwritten character recognition device 1 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?" “YES”, step 9
5, "Is the received content a command?" is determined as "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 "YES" and step 96
to prohibit reception from the terminal. If the command is a command that specifies the character frame size, step 97 becomes "YES", and in step 98, the character frame size designation information is stored in the character frame type storage area 146; If so, step 9
At step 9, the process corresponding to the command is executed.

In the next step 100, the received character frame number is set to the specified value of the form format to be described later (step 12 in Fig. 20).
If the determination is "NO", a character indicating an input error is displayed on the CRT 5 in step 101.
Also, in step 102, an error tone is emitted.

On the other hand, if the determination in step 100 is "YES", then in step 103 it is determined whether or not the received information is an error code.

As mentioned above, in the embodiment of the number "4", an error code is sent to the host device 4 at the end of the recognition of the first stroke (step 54 in FIG. 1).

Therefore, in this case, the determination in step 103 is "YES"
and the characters received in step 104.

The display position of the CRT 5 corresponding to the frame number is cleared, and in the next step 105, the address of the character storage area 147 corresponding to the character frame number 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 together with the character frame number (step 56 in FIG. 1), so in this case step 103 The determination is 6NO', and in step 106, 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
07, the character storage area 14 according to the character frame number
The received character code is stored at address 7.

The above-mentioned series of processes is repeatedly executed every 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 106. 107).

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.

FIG. 20 shows a subroutine called and executed in step 92 of FIG. 19.

First, in step 120, the CR in the host side device 4 is
Guidance characters prompting the user to select a character frame size are displayed on the screen of T5. In this embodiment, the first . Second. As already mentioned, the third form is prepared, and at this first stage, depending on the form to be used, select one of the character frame designation keys on the keyboard 6 to select the character frame. Specify the size of . If this character frame is specified, step 121 "Is there input?"
The determination is "YES", and the size of the character frame specified in the next step 122 is stored in the character frame type storage area 146.
is memorized.

Next, guide characters are displayed on the screen of the CRT 5 to prompt the user to input data for defining the form format, that is, the number of columns and columns of character frames (step 123). When the number of columns and columns of the character frame are input using the keyboard 6, the determination of "Is there an input?" in step 124 becomes "YES", and this key input data is stored in the form format information storage area as the specified value of the form format. 1
42 (step 125).

Next, in step 126, guidance characters are displayed on the screen of the CRT 5 to prompt the base point setting operation of the form format described above, and in the next step 127, character frame designation information indicating the size of the character frame is displayed on the screen of the CRT 5 (handwritten characters). The information is transmitted to the recognition device 1), and reception from the terminal is permitted in step 12B. In response to this, the handwritten character recognition device 1 stores the character frame designation information, performs the base point setting operation, and transmits the base point coordinate data to the host side device 4, as described above (see Fig. 1). Step 32~
39). In this way, when the host side device 4 receives the base point coordinate data, the determination of "Received?" in step 129 becomes "YES", and after reception from the terminal is prohibited in step 130, the received data is processed in step 131. Display (base point coordinates) on the CRT5 screen, and then step 1
At step 31, the form format is displayed on the screen of the CRT 5 based on the data stored in the form format information storage area 142, and the subroutine shown in FIG. 20 is completed.

[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 for explaining the 8-direction code, Figures 5 to 8 are diagrams showing base point setting examples,
Figures 9 and 10 are diagrams showing the base point setting operation;
The figure is a diagram for explaining the misaligned state of the form format caused by the operation example in Figure 10, Figure 12 is a flowchart showing the subroutine of character frame cutting and character frame number calculation processing, and Figure 13 is a character frame FIG. 14 is a flowchart showing a subroutine for stroke input processing; FIG.
Figure (11(2) is a diagram showing an example of substroke division for characters r2J r5J, Figure 16 is 1 of character "5"
A diagram showing an example of the direction code conversion for the stroke.
8 is a diagram showing the memory map of the host side device, FIG. 19 is a flowchart showing the control operation of the host side device, and FIG.
FIG. 0 is a flowchart of a subroutine related to setting a form format, and FIG. 21 is a diagram for explaining a method of determining accuracy of alignment in a conventional example. l...Handwritten character recognition device 2...Input tablet 3...Recognition processing unit 10...Character input area 13...Input pen 14・・・・・・Character frame 15・・・・・・Includes IE for 2nd time 4-4-Bun nko. Nostim's real talent A, Qi12! 2 input 2 let 3 ゑ, this 9th generation (1ri - 1L door) θ support entry crab y7 /3/4 Female customer 1 volume / j - East Chuken 3 + 1 = ♀”'WINA, @ To the death of Noah Horn input 0
7 ``A9=Shi Ki Yanen Arashi 1 matter and one shout 6 fu stems, ?Namazu run I month and 〒,'v figure/ltA the;+-/7';U1 4 good store establishment jko Ita・hr
F;-v Haruka 4” Kajuku Kamisae/Sushi 597 times? E-phrase court tt'ti cane kopic +/(-71'Zla host toi 9
・11. Work i'I < Gen motion I γ Distance flow + Yard study / l Shoulder stroke 111 examples are shown here. 9 → 2C drawing number/d drawing

Claims (2)

[Claims] (1) An input tablet on which a form having a predetermined format is positioned and arranged on a character input area, an input pen for handwriting characters by bringing the pen tip into contact with the form on the input tablet, and the input tablet. and a recognition processing unit that takes in handwritten input characters from the character input area and executes character recognition, and the recognition processing unit takes in the coordinates of the pen position that is brought into contact with the form on the input tablet as the base point coordinates before starting character input. means for aligning the input tablet and the form by setting the format of the form for the character input area based on the base point coordinates; A handwritten character recognition device comprising means for extracting a character and performing character recognition processing. (2) The recognition processing unit is configured with a computer circuit including a CPU and memory.
The handwritten character recognition device described in Section 1.