JP3353954B2 - Handwriting input display method and handwriting input display device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION The present invention relates to an electronic organizer,
Handwriting input table suitable for use in portable computers, etc.
The present invention relates to an indication method and a handwriting input display device .

[0002]

2. Description of the Related Art In recent years, devices capable of inputting characters by hand, such as electronic organizers, have become widespread. Unlike a normal word processor, such a device that can input characters by hand can input characters by writing characters on a board using a pen instead of a keyboard. You can easily input text as if you were writing text with a pencil on top. Compared with the case of using a keyboard, there is no need to memorize key positions and the like, so even a beginner can easily input characters.

[0003] In such an apparatus capable of inputting characters by hand, an input frame for inputting characters is provided, and an input frame is not provided, and characters can be input at an arbitrary position. There is something.

In an apparatus provided with an input frame, a user inputs characters by hand in the input frame one by one. This input frame is usually divided into a plurality of areas, and the user inputs one character to each area. Since the input position is restricted, the operability is poor for the user by that much. However, since the area for inputting each character is divided, it is necessary to cut out the input character one character at a time. And each character can be relatively accurately recognized.

On the other hand, in an apparatus having no input frame, a user inputs a character by hand at an arbitrary position on an input board (tablet). In this case, the character input by handwriting is recognized as a character at a predetermined timing.

That is, when a character is input, a boundary between the input character and the character is determined. Then, each cut-out character is recognized as one character, and the recognition result is displayed.

As a result, for example, as shown in FIG. 39 (a), when the user inputs the kanji character "Akira", the characters "day" and "month" constitute one character. If the input character is cut out, the input character is recognized as the kanji character of “Akira”.

However, as shown in FIG. 39 (b), the characters of "day" and "month" are relatively separated, so that these characters are cut out as separate characters. In some cases, "day" and "month"
Are recognized as separate characters.

[0009]

As described above, in the conventional apparatus, the result recognized as the character of "bright" or the result recognized as the character of "day" and "month" is not intended by the user. Must be re-entered if different from
There was a problem that it took time to input intended characters.

The present invention has been made in view of such a situation, and is intended to allow desired characters, figures, and the like to be input more quickly.

[0011]

Means for Solving the Problems Handwritten input display of the present invention
The method is based on the handwriting input of
Input control step to control and processing of input control step
Controls the storage of handwriting whose input is controlled by the
Processing of the handwriting storage control step
Handwriting whose memory is controlled by segmentation into segmentation
First recognition that classifies and performs character recognition and obtains a recognition result
And the handwriting memory control step
The controlled handwriting and the first recognition step
A first recognition result among the received recognition results.
A first display control step, and an input control step.
Handwriting newly input by the
First determination to determine whether the instruction is a modification instruction
The steps and the processing of the first determination step allow
If it is determined that the instruction to modify the
The recognition result obtained by the processing of the first recognition step
The segmentation corrected by the correction instructions.
Determining whether a corresponding second recognition result is included
The second determination step and the processing of the second determination step
The segmentation corrected by the correction instructions.
If it is determined that the corresponding second recognition result is included
The second recognition result is controlled to display the second recognition result.
The display control step and the processing of the second determination step
The segmentation corrected by the correction instructions.
If it is determined that the corresponding second recognition result is not included,
Is stored by the processing of the handwriting storage control step.
For handwriting, segmentation based on correction instructions
A new character recognition is performed on the corresponding portion, and the third
A second recognition step for obtaining a recognition result, and a second recognition step.
Display the third recognition result recognized by the
And a third display control step of performing control so as to perform the control .

The instruction to correct the segmentation can be made by gesture. Further, correction instructions for segmentation, the expansion of handwriting input, reduced, deleted, moved, or any indication of deformation
It can be set to a certain thing. In addition, the handwriting input of the present invention
Force display device, input means for receiving handwriting input of handwriting,
Handwriting storage means for storing handwriting input by the input means
And the handwriting stored by the handwriting storage means is segmented.
And perform character recognition to obtain recognition results.
Recognition means, handwriting stored by handwriting storage means, recognition
The first recognition result among the recognition results obtained by the means
Display means for displaying, and newly input by the input means
Whether the handwriting is an instruction to correct the segmentation
The first determining means for determining and the first determining means
It has been determined that an instruction to correct the fragmentation has been input.
In the case, the recognition result obtained by the recognition means
A second recognition corresponding to the more modified segmentation
Second determining means for determining whether or not a recognition result is included
Is corrected by the correction instruction by the second determination means.
The second recognition result corresponding to the segmentation performed is
If it is determined that it is included, the display means displays the second
The recognition result is further displayed, and a correction instruction is issued by the second determination means.
A second corresponding to the segmentation modified by
If it is determined that the recognition result is not included, the recognition unit
Indicates that any of the handwritings stored by the handwriting storage
In the part corresponding to the segmentation based on the correct instruction
On the other hand, character recognition is newly performed, and the third recognition result is obtained.
The display means obtains the third recognition recognized by the recognition means.
The result is further displayed.

[0013]

The handwriting input display method and the handwriting input of the present invention
The display device receives handwriting input of handwriting and
Handwriting is memorized and the memorized handwriting is segmented
Character recognition is performed, and the recognition result is obtained.
And the first of the obtained recognition results
Is displayed and the newly entered handwriting is
It is determined whether the instruction is a modification instruction of the
It has been determined that an instruction to correct the fragmentation has been input.
In the case, the obtained recognition result was corrected by the correction instruction
Contains the second recognition result corresponding to the segmentation
It is determined whether or not the security
Including the second recognition result corresponding to the fragmentation
If it is determined that there is a second recognition result,
Corresponds to segmentation modified by correct instructions
If it is determined that the second recognition result is not included,
Of the remembered handwriting, segment based on correction instructions
Character recognition is newly added to the part corresponding to the
Is performed to obtain a third recognition result, and the third recognition result is
Is displayed.

[0014]

FIG. 1 is a block diagram showing the configuration of an embodiment of an apparatus to which the handwriting input display method of the present invention is applied. C
The PU 1 controls each unit in accordance with a program stored in the ROM 2 to execute a character input / display operation. The RAM 3 stores predetermined data and the like as needed. The backup RAM 4 is always supplied with a predetermined power from the battery 5, and stores information to be stored even when the power of the apparatus is turned off. The timer 6 includes a quartz oscillator 7
, The battery 5 is always operated.

The display controller 11 develops data input through the bus line 8 into the V-RAM 12 and displays the developed image on the display unit 13. The input tablet 15
By operating the pen 16, the input coordinate position data is output to the tablet interface 14, and the tablet interface 14 outputs the data to the bus line 8.
CPU 1 or display controller 1
1 is output.

The microphone 18 outputs the collected audio signal to the solid-state recording processing circuit 17 and stores it. The audio signal output from the solid-state recording processing circuit 17 is supplied to a speaker 21 via an adder 20 and emitted. Dialer 19 is a CPU
1 and outputs a predetermined dial signal to the speaker 21 via the adder 20.

A plurality of key switch groups 22 are operated when the operation of the apparatus is switched, and a signal corresponding to the operation is transmitted from the key interface 23 to the CP via the bus line 8.
The data is output to U1. The power supply circuit 25 is turned on by operating a predetermined one of the plurality of key switch groups 24 to supply power to each unit, and the recording, reproduction, stop,
It is possible to execute volume adjustment and the like.

Further, an IC (not shown) is provided in the socket 26.
The card can be inserted, I
The C card interface 27 exchanges data with the IC card.

For example, a modem or the like can be connected to the pin connector 29, and signals can be transmitted and received to and from the extension interface 28 via the modem.

The input tablet 15 is made of a transparent material and is formed on the display unit 13. As a result, the display on the display unit 13 can be viewed through the input tablet 15.

Next, the operation of the embodiment of FIG. 1 will be described with reference to FIG.
This will be described with reference to the flowchart of FIG. When a predetermined character is handwritten on the input tablet 15 with the pen 16, the handwriting data is supplied to the RAM 3 via the tablet interface 14 and stored. This data is read out by the display controller 11, and the V-RA
It is supplied to M12 and is developed as bitmap data. Further, the data stored in the V-RAM 12 is read by the display controller 11, supplied to the display unit 13, and displayed. Thus, the handwriting of the pen 16 is displayed on the display unit 13.

This input is performed at an arbitrary position on the input tablet 15, and is performed in a state where a so-called input frame is not provided. The input handwriting data is stored in the handwritten handwriting database DB1 in the RAM 3.

When the input is made in this manner, the CPU 1
First performs a character recognition process in step S1. At this time, the CPU 1 reads out the handwriting from the handwritten handwriting database DB1, and recognizes this handwriting in the character recognition 1
It is divided into character segmentation as a unit. Then, character recognition is performed for each character segmentation , and the recognition result obtained as a result of the recognition is supplied to and stored in the recognition result database DB2 of the RAM 3.

Next, the process proceeds to step S2, where the first recognition result among the recognition results obtained as described above is read from the recognition result database DB2 and displayed on the display unit 13. In other words, CPU1, the character segment
For each annotation , a similarity (score) with a predetermined character stored in advance is calculated, and the recognition results are ranked in order from the one with the highest similarity, and the recognition result with the highest similarity is ranked It is displayed here as the first recognition result.

Next, the process proceeds to step S3, where a handwriting newly input by the user is received. Then, in step S4, it is determined whether or not the handwriting received in step S3 is for instructing correction of character segmentation. If it is not an instruction to correct the character segmentation, processing other than the processing in FIG. 2 will be performed, and the processing shown in this flowchart is terminated. If the input is an instruction to correct the character segmentation, the process proceeds from step S4 to step S5.

In this embodiment, as shown in FIGS. 3 to 10, the correction of the character segmentation is performed by enlarging the range of the handwriting within the character segmentation (FIG. 3) and reducing the range of the handwriting within the character segmentation (FIG. 4). , Partial erasure of handwriting in character segmentation (Fig. 5), movement of the position of a subset of handwriting in character segmentation (Fig. 6), enlargement of the size of a subset of handwriting in character segmentation (Fig. 7), character Reducing the size of handwriting subsets in segmentation (Figure 8), adding new handwriting in character segmentation (Figure 9), or modifying the shape of handwriting subsets in character segmentation (Figure 10) To be one of

The details of each process will be described later with reference to FIGS. 11 to 29. For easy understanding, eight types of modified examples of character segmentation will be briefly described here.

As shown in FIG. 3, the enlargement of the handwriting range in the character segmentation is performed, for example, by using “Ishii” in Hiragana.
Is input by hand, and the input of the first image and the second image of "i", which should be recognized as one character, is classified as separate character segmentation and the character is recognized. The first stroke and the second stroke are modified so as to be included in the same character segmentation.

As shown in FIG. 4, for example, a kanji character “Wataru Yaguchi” is input and the characters “arrow” and “mouth”, which should be originally recognized as two independent characters, are reduced as shown in FIG. Is recognized as the character "knowledge" in one character segmentation,
In order to recognize the “arrow” and the “mouth” of the character “knowledge” as independent characters, the character segmentation is modified into two parts.

As shown in FIG. 5, the partial erasure of the handwriting in the character segmentation is performed when the character "large" is to be input and the character "heaven" has been input. This is used when erasing one image and changing the character to "large".

As shown in FIG. 6, the position of the subset of the handwriting in the character segmentation is moved, for example, in such a manner that the character "" is to be input, and the second image is projected above the first image. The character "Earth"
Is used to move the first image upward and move it to a position in contact with the second image.

As shown in FIG. 7, the size of the subset of the handwriting in the character segmentation can be expanded, for example, by inputting "tai" in hiragana, but the size of the hiragana "i" If the hiragana “i” is recognized as a lowercase “ぃ” because it is smaller than “”, change the lowercase “ぃ” to a normal size “i”. Used when

As shown in FIG. 8, the size of the subset of the handwriting in the character segmentation can be reduced by, for example, inputting "two places", and inputting a large katakana "ka" of the central character. If this character has been recognized as a normal size "ka" because of this, it is used to change it to a lowercase "ka".

As shown in FIG. 9, the addition of a new handwriting into the character segmentation is based on the fact that the character "dog" should have been input, but the character "large" had been input by mistake. If you notice from, add a dot to the character segmentation that contains the letter "
This is used to change this to the character "dog".

As shown in FIG. 10, the deformation of the shape of the subset of the handwriting in the character segmentation is as shown in FIG. In such a case, it is used when the shape is deformed so that the right end portion of the first image is bent downward, and the recognition result is set to “A” in katakana.

Returning to FIG. 2, when it is determined in step S4 that the input is for instructing the correction of the character segmentation, the process proceeds to step S5, in which whether or not a recognition result matching the correction instruction exists. Is determined. That is, at this time, the CPU 1 determines whether or not the recognition result corresponding to the corrected character segmentation is stored in the recognition result database DB2. If such a recognition result has already been obtained, the process proceeds to step S6. Then, the recognition result is read out and displayed on the display unit 13.

For example, as in the embodiment shown in FIG. 4, when a kanji character "Yaguchi" is input, the first recognition result may be "Ki", for example, as the second recognition result. If “Yaguchi” has already been obtained, and an instruction to reduce the range of the handwriting in the character segmentation shown in FIG. 4 is issued, the already obtained second candidate recognition result “Yaguchi” will be displayed.

On the other hand, if it is determined in step S5 that there is no recognition result that matches the correction instruction, the process proceeds to step S7, where a handwriting having character segmentation that matches the correction instruction is generated. That is, at this time, the CPU 1 redoes the segmentation of the character segmentation in response to the correction instruction, reads out the handwriting corresponding to the corrected character segmentation from the handwritten handwriting database DB1, and sets the handwriting included in the character segmentation. Then, this is supplied to the handwritten handwriting database for correction DB3 in the RAM 3 and stored therein. The more detailed processing in step S7 will be described later with reference to FIG.

Next, the process proceeds to step S8, in which the character segmentation stored in the correction handwriting database DB3 is recognized. Then, the recognition result obtained as a result of the recognition is stored in the correction recognition result database DB4 in the RAM 3.
And store it.

[0040] then proceeds to step S9, the contents of the correction for the recognition result database DB4, the recognition result data base D
Rewrite the contents of B2. Then, after step S9, the process returns to step S2, and the subsequent processes are repeatedly executed.

In this embodiment, step S3
In the above, the instruction for correcting the character segmentation is received as a gesture (handwriting input). However, it is also possible to make an input from an icon displayed on the display unit 13 or a predetermined input from a keyboard, a mouse, or the like. It is.

Although the handwritten handwriting database DB1 and the handwritten handwriting database DB3 for correction are configured as independent ones, the handwritten handwriting database DB1 may be directly changed when the corrected handwritten handwriting is generated in step S7. The correction handwritten handwriting database DB3 can be omitted. In this case, the character recognition in step S8 is performed using the handwritten handwriting database DB1.

[0043] Similarly, the recognition result data base DB2
And the recognition result database for correction DB4 may be reduced to one. In this case, the result of character recognition in step S8, the recognition result data base DB2 is changed directly.

Here, the structure of the data will be described. The input handwriting is represented as follows for each image. First image s [1] = ｛(x [1], y [1]),..., (X
[N], y [n])｝ Second stroke s [2] = ｛(x [n + 1], y [n + 1]),
｝｝ 3rd drawing s [3] = ｛｝ ｋ ｋ kth drawing s [k] = ｛｝

That is, the handwriting data s [i] of the i-th image is represented by a sequence of coordinate points (x [a], y [a]),.
[B], y [b]).

Further, the character recognition result is expressed as follows. First place r [1] = ｛<s [a11], s [b11]: code [1] [1]>, <s [a12], s [b12]: code [1] [2]>, 〈 s [a13], s [b13]: code [1] [3]>, ..., <s [a1q], s [b1q]: code [1] [q]> ｑ second r [ 2] = ｛<s [a21], s [b21]: code [1] [1]>, <s [a22], s [b22]: code [1] [2]>, <s [a23], s [b23]: code [1] [3]>, ..., <s [a2p], s [b2p]: code [1] [p]>}, ...

The recognition result at the j-th place is a start stroke s [m] and an end stroke s [n] of a stroke (handwriting for one stroke) constituting a character, and a character code code [] of a recognition result for the stroke group. The three elements of [] are defined as one unit, and have units corresponding to the number of character segmentations. For example, in the second example from the top in FIG. 3, Becomes

The processing for generating the handwritten handwriting having the character segmentation that matches the correction instruction in step S7 will be described below with reference to the second example from the top in FIG. That is, the handwriting sets of the first to fifth strokes are s [1], s [2], s [3], s
[4] and s [5]. On the other hand, the character segmentation result G [i] is expressed as follows. G [1] = {s [1]} G [2] = {s [2]} G [3] = {s [3]} G [4] = {s [4], s [5]}

This character segmentation result G [i]
The character recognition result R [i] corresponding to is represented as follows. R [1] = ｛'し' R [2] = ｛'1'｝ R [3] = ｛'し' R [4] = ｛'い'

In the case of the third processing from the top in FIG.
Since this is a process of combining [1] and G [2], the character segmentation G ′ [1] after inputting the handwriting range expansion symbol
Is as follows: G ′ [1] = {s [1], s [2]}

Then, s [1] and s [2], which are different from the handwriting before the input of the enlargement instruction symbol, are stored in the correction handwritten handwriting database DB3.

The following is an example of handwriting data generated in response to the correction instruction described above.

G [1] = {s [1]} G [2] = {s [2]} → G ′ [1] = {s [1], s [2]｝ Before inputting correction instruction After inputting correction instruction

Reduction of handwriting range divided by character segmentation G [1] = {s [1], s [2], s [3]} → G ′ [1] = {s [1]}

Addition of handwriting to character segmented handwriting G [1] = {s [1], s [2], s [3]} → G ′ [1] = {s [1], s [ 2], s [3], s ′｝

G [1] = {s [1], s [2], s [3]} G [2] = {s [4], s [5]} → G '[1] = {s [1]} G' [2] = {s [4], s [5]}

The position of the subset of the character-segmented handwriting is moved. The shape of the subset of the character-segmented handwriting is enlarged. The size of the subset of the character-segmented handwriting is enlarged. Size reduction As described above, the four instructions are common and are as follows. G [1] = {s [1], s [2], s [3]} G [2] = {s [4], s [5]} → G ′ [1] = {s ′ [1] , S ′ [2], s ′ [3]} G ′ [2] = {s ′ [4], s ′ [5]} where s ′ [i] is the internal data of s [i] ( Handwriting data whose point sequence coordinates have been changed.

In step S8, in the case of the embodiment of FIG. 3, the recognition result R 'for the handwriting {s [1], s [2]} corresponding to the corrected character segmentation.
[1] becomes R '[1] = {' i '}.

Further, in step S9, in the case of the embodiment of FIG. 3, the character recognition result R [i] and the character segmentation result G [i] are as follows. R [1] = ｛'し' R [1] = ｛s [1]｝ R [2] = ｛'1'｝ R [2] = ｛s [2]｝ R [3] = ｛''{R [3] = {s [3]} R [4] = {' in '} R [4] = {s [4], s [5]}

This is R '[1] = {' i '}, G'
[1] = {s [1], s [2]}. That is, the following is performed. R [1], R [2] → R ′ [1] G [1], G [2] → G ′ [1] R [3] → R [2] G [3] → G [2] R [ 4] → R [3] G [3] → G [2]

Next, a more detailed process of generating a handwritten handwriting having a character segmentation that matches the correction instruction in step S7 in FIG. 2 will be described with reference to the flowchart in FIG.

First, in step S21, if the handwriting data required for character recognition in step S8 in FIG. 2 does not exist in the correction handwritten handwriting database DB3,
This is read from the handwritten handwriting database DB1 and stored. That is, since the character recognition in step S8 is performed based on the database stored in the correction handwriting database DB3, it is necessary to prepare all necessary handwriting data in the correction handwriting database DB3. There is.

Next, in steps S22 to S29,
It is determined whether the handwriting data (gesture) received in step S3 in FIG. 2 is one of the above eight types of correction instructions. When it is determined that none of the eight types of correction instructions is present, the process proceeds to step S30, and error processing is performed.

If it is determined in steps S22 to S29 that the instruction is one of the eight types of correction instructions, the process proceeds to steps S32 to S39, respectively, where processing corresponding to each type of correction instruction is executed. Is done.

That is, when it is determined in step S22 that the correction instruction is a handwriting range enlargement instruction, step S32 is performed.
In, a handwriting range enlarging process is executed. Step S
If it is determined in step S23 that the instruction is a handwriting range reduction instruction, a handwriting range reduction process is executed in step S33.
When it is determined in step S24 that the instruction is a handwriting partial erasure instruction, in step S34, a handwriting partial erasure process is executed.

If it is determined in step S25 that the instruction is to move the position of a subset of handwriting, then in step S35, a partial handwriting position moving process is executed. Step S2
If it is determined in step S6 that the instruction is an instruction to enlarge the size of a subset of handwriting, in step S36, partial handwriting size enlargement processing is executed. If it is determined in step S27 that the instruction is for reducing the size of a subset of handwriting, step S3
At 7, a partial handwriting size reduction process is executed.

Further, when it is determined in step S28 that the instruction is a handwriting addition instruction to handwriting, in step S38, processing for adding handwriting to handwriting is executed. When it is determined in step S29 that the instruction is a handwriting shape deformation instruction, in step S39, handwriting shape deformation processing is executed.

Next, details of each processing of steps S32 to S39 will be sequentially described.

FIG. 12 shows details of the handwriting range enlarging process in step S32. First, in step S51, a circumscribed rectangle of the handwriting range enlargement instruction symbol 51 is obtained. Next, the process proceeds to step S52, and a set of handwritings including all or a part of the circumscribed rectangle obtained in step S51 is obtained. In step S53, the range expansion code and the start image number and end image number of the handwriting obtained in step S52 are output to the correction handwritten handwriting database DB3.

That is, as shown in FIG. 13, when the first and second strokes of the hiragana character "i" are classified as different character segmentations, the range enlargement instruction is performed so as to be applied to the two character segmentations. When the symbol 51 is input, a circumscribed rectangle of this symbol having a substantially V-shaped shape oriented in the horizontal direction is obtained (step S51), and the handwriting data of the character segmentation including the whole or a part of the circumscribed rectangle is 1 These are grouped as one character segmentation (steps S52 and S53).
This is recognized as the hiragana "i" in the process of step S8.

FIG. 14 shows details of the handwriting range reduction processing in step S33. First, in step S61, a circumscribed rectangle of the handwriting range reduction instruction symbol 52 is obtained. Then, in step S62, in the character segmentation in which the handwriting range reduction instruction symbol 52 exists, a handwriting existing to the left of the handwriting range reduction instruction symbol 52 is obtained, and the start image number and end image number of the handwriting are corrected by handwriting for correction. It is supplied to the handwriting database DB3 and stored.

Further, in step S63, in the character segmentation in which the handwriting range reduction instruction symbol 52 is present, the start image number and the end image number of the handwriting existing on the right side of the handwriting range reduction instruction symbol 52 are corrected. It is supplied to DB3 and stored.

For example, as shown in FIG. 15, in a state where a kanji “word” is input in one character segmentation, if it is desired to recognize this as two characters instead of one character, A handwriting range reduction instruction symbol 52 having a substantially V shape is input between the handwriting of “word” and the handwriting of “go” among the handwritings constituting the “word”. Then, a circumscribed rectangle of this symbol is obtained (step S61), and the handwriting (“word”) located on the left side of the circumscribed rectangle and the handwriting (“go”) located on the right side are respectively subjected to individual character segmentation. (Steps S62 and S63). Therefore, if the corrected character segmentation is processed in step S8 in FIG.
“Word” and “Go” are each recognized as two independent characters.

FIG. 16 shows details of the handwriting part erasing process in step S34. First, in step S71, a circumscribed rectangle of the handwriting part erasure symbol 53 is obtained.
Next, in step S72, a set of handwritings included in the circumscribed rectangle obtained in step S71 is obtained. Also,
In step S73, character segmentation information (handwriting) excluding the handwriting obtained in step S72 is generated from the currently displayed character segmentation, and this is output to the handwritten handwriting database for correction DB3 as handwritten handwriting data for correction. Is memorized. The process further proceeds to step S74, and the handwriting (handwriting included in the circumscribed rectangle of the handwriting partially erased symbol 53) obtained in step S72 is erased from the correction handwritten handwriting database DB3.

For example, as shown in FIG. 17, in the state where the character of “heaven” is input by handwriting, a handwriting part erasure symbol 53 of a substantially alphabetical character “N” is added to the first stroke of “heaven”. Is entered, this handwriting partial erasure symbol 5
The handwriting of the first image included in the circumscribed rectangle of No. 3 is selected as the handwriting to be erased (steps S71 and S72). And this handwriting is handwritten handwriting database DB3 for correction.
, Character segmentation composed of the handwritings of the remaining second to fourth strokes is generated (step S7).
3, S74). As a result, when this is recognized in step S8, a recognition result as a "large" character is obtained.

FIG. 18 shows details of the partial handwriting position moving process in step S35. First step S
At 81, a circumscribed rectangle of the loop portion of the partial handwriting position movement symbol 54 is determined. That is, the partial handwriting position movement symbol 54 is constituted by a circular loop portion and a linear tail portion, and a circumscribed rectangle of the loop portion is obtained. Next, in step S82, a set of handwritings included in the circumscribed rectangle is obtained.

Further, in step S83, the starting point (X ₀ , Y ₀ ) of the tail portion of the partial handwriting position movement symbol 54
And the end point (X ₁ , Y ₁ ) are obtained. Next, step S84
Then, (X ₁ −X ₀ , Y ₁ −Y ₀ ) is added to the coordinate values of the handwriting included in the circumscribed rectangle obtained in step S82. That is, data is generated by moving this handwriting by the length thereof in the direction of the tail of the partial handwriting position movement symbol 54.
Then, the information of the character segmentation including the changed handwriting is output to the correction handwritten handwriting database DB3.

For example, as shown in FIG. 19, in the state where the character “earth” is being input, the first
When the partial handwriting position movement symbol 54 is input so that a part of the image is included in the loop portion, the partial handwriting position movement symbol 5
A circumscribed rectangle of the loop portion of No. 4 is obtained (step S8).
1) Further, a handwriting (first image) in the circumscribed rectangle is obtained (step S82).

Then, the coordinates of the starting point and the ending point of the tail portion are obtained (step S83), and a handwriting is generated by moving the handwriting of the first image by the length in the direction of the tail portion (step S83). S84). As a result,
When the set of handwritings whose position of the first image has been moved is subjected to character recognition in step S8, a recognition result of "work" is obtained.

Further, it is assumed that the user has input two characters "tree" and "tree" by handwriting as shown in FIG. 20, for example. Among the two strokes of the “tree”, the fourth stroke of the character segmentation 1 of the “tree” on the left does not originally intersect with the second stroke of the character segmentation 2 of the “tree” on the right. However, if the user decides that the fourth and second strokes
Assuming that the input has been made to intersect the image, this input of one character segmentation is recognized as “forest”.

Therefore, if the character segmentation is separated so as to separate it into two character segmentations, handwriting corresponding to the separated character segmentation must be newly generated (the processing in step S7 in FIG. 2 is performed). The character segmentation 1 of "tree" on the left and the character segmentation 2 of "tree" on the right are each recognized independently, and the character segmentation 1 on the left is recognized as "tree". Character segmentation 2 is the fourth of the "tree" on the left
Since the image intersects with the second image, there is a high possibility that the image is erroneously recognized as a character “book”.

That is, when it is determined in step S5 in FIG. 2 that there is no recognition result that matches the correction instruction, as shown in step S7, a handwritten handwriting having a character segmentation that matches the correction instruction must be generated. Recognizing the recognized character "book" as the original character "tree" becomes difficult unless an input is performed again.

However, in this embodiment, FIG.
As shown in FIG. 1, for example, when the first handwriting to the fourth drawing constituting the “tree” on the left side are included in the loop portion and the partial handwriting position movement symbol 54 is input so as to move leftward at the tail portion, the left side Since the intersection between the fourth image of the “tree” and the second image of the “tree” on the right side is released, the character “tree” can be easily recognized even in the character segmentation 2.

FIG. 22 shows details of the partial handwriting size enlarging process in step S36 in FIG. First, in step S91, a circumscribed rectangle of the rectangular loop portion of the partial handwriting enlarging instruction symbol 55 composed of a rectangular loop portion and a tail portion protruding outside the rectangular loop is obtained. Then, in step S92, a set of handwritings included in the circumscribed rectangle is obtained. Next, step S93
The coordinates of the lower left point (X ₀ , Y ₀ ) and the upper right point (X ₁ , Y ₁ ) of the tail portion of the partial handwriting enlargement instruction symbol 55 are obtained.

Further, the process proceeds to step S94,
The coordinate values of the lower left vertex (X ₂ , Y ₂ ) and the upper right vertex (X ₃ , Y ₃ ) of the circumscribed rectangle of the rectangular loop portion obtained at 91 are obtained. Then, the process proceeds to step S95, and step S9
The coordinate value of the handwriting (handwriting included in the circumscribed rectangle of the rectangular loop portion of the partial handwriting enlarging instruction symbol 55) obtained in step 2 is calculated according to the following equation, and is used as corrected handwriting data.

[0086]

(Equation 1)

Here, x 'and y' are the handwriting data after correction, and (x, y) is the data before correction.

As can be seen from this equation, if the direction of the tail of the partial handwriting enlargement instruction symbol 55 is set to 45 degrees, the ratio of the original handwriting in the vertical direction and the horizontal direction is not changed, and the handwriting is not changed. Although it is enlarged, if you set it in a direction other than 45 degrees,
The ratio changes and is enlarged.

For example, as shown in FIG.
Is recognized as a lowercase character, when the partial handwriting enlargement instruction symbol 55 is input so as to surround the character “ぃ” in the rectangular loop portion, “ぃ” is selected as the handwriting included in the rectangular loop portion ( Steps S91 and S92), and the coordinates of this character "@" (lowercase) are changed according to the above formula (steps S94 and S95). Therefore, when this is recognized in step S8, it is recognized as "i" (uppercase).

FIG. 24 shows details of the partial handwriting size reduction process in step S37 of FIG. First, in step S101, a circumscribed rectangle of the rectangular loop portion of the partial handwriting reduction instruction symbol 56 composed of a rectangular loop portion and a tail portion protruding inside the rectangular loop portion is obtained. Next, in step S102, a set of handwritings included in the circumscribed rectangle is obtained. In step S103, the lower left point (X ₀ , Y ₀ ) and the upper right point (X ₁ ,
The coordinates of Y ₁ ) are obtained.

The process further proceeds to step S104, where the lower left vertex (X ₂ , Y ₂ ) and the upper right vertex (X ₃ , X ₃ , X ₂ ) of the circumscribed rectangle obtained in step S101 (the circumscribed rectangle of the rectangular loop portion) are obtained.
Y ₃ ) is obtained. Next, the process proceeds to step S105, and the coordinate values of the handwriting (handwriting included in the circumscribed rectangle) obtained in step S102 are converted as correction handwriting data according to the following equation. It should be noted that this equation is given by the above equation (1).
Of is identical to the formula, the magnitude of the coordinate values X ₂ and X _3, Y ₂ and Y ₃ are, because different from the case of 1, the operation of reducing the handwriting.

[0092]

(Equation 2)

For example, as shown in FIG. 25, when the katakana character “ka” is recognized as an uppercase letter in the “two places” character, the partial handwriting reduction instruction symbol 56 is replaced with the character “ka” in the square loop portion. ”Is selected as the handwriting included in the rectangular loop portion (steps S101 and S102), and its coordinate value is converted according to the above equation (steps S103, S104 and S1).
05). Therefore, this converted data is stored in step S8.
When the character is recognized by, "ka" is obtained.

FIG. 26 shows the details of the processing for adding a handwriting to the handwriting in step S38 in FIG. First, in step S111, a character segmentation in which the additional instruction handwriting 57 exists is obtained. Next, step S1
12, the handwriting database DB for correction corresponding to the character segmentation obtained in step S111
At the end of the handwriting in No. 3, an additional instruction handwriting is added. Then, in step S113, the start image number and the end image number corresponding to the character segmentation to which the handwriting data is added in step S112 are supplied to the handwritten handwriting database DB3 for correction and stored.

For example, as shown in FIG. 27, in a state where the character "Large" has been input and recognized, if an additional instruction handwriting 57 is added to the upper right of the first stroke of the character "Large", the handwriting becomes " The characters are added to the three images constituting the "large" (steps S111 and S112), and the character is composed of a total of four images. As a result, this is step S
When the character recognition processing is performed in step 8, "dog" is obtained as a recognition result.

FIG. 28 shows the details of the handwriting shape deformation process in step S39 of FIG. First step S
At 121, a handwriting to be combined with the input deformation instruction handwriting 58 is determined. Next, the process proceeds to step S122, where the coordinate point sequence data of the input deformation instruction handwriting is combined with the coordinate point sequence data in the correction handwriting database DB3 corresponding to the handwriting obtained in step S121, and this is combined with the correction handwriting. Supply to handwriting database DB3.

For example, as shown in FIG. 29, when the alphabetical letter "T" is input and displayed, when a deformation instruction handwriting 58 that bends to the lower right is added to the right end of the first image, it is combined and added. The first image is selected as the handwriting (step S121). Then, the point sequence data of the deformation instruction handwriting 58 is added to the point sequence data of the first image (step S122). As a result, when the added data is subjected to character recognition processing in step S8, katakana "a" is obtained.

FIG. 30 shows a configuration example of the format of the correction handwritten handwriting database DB3. As shown in the figure, first, data corresponding to each image is sequentially arranged. At the beginning of the data of each of these images, the image number of the image is displayed, and then the number n of coordinate points constituting the image is displayed.
, And then, the coordinate values (x ₀ , y ₀ ), (x ₁ , y ₁ ),..., (X _n−1 ,
yn _-1 ) are sequentially arranged. At the end of each of these pieces of image data, a handwriting data part end symbol is arranged.

Following the end symbol of the handwriting data section, a correction type code and the number of character segmentations to be re-recognized are arranged. The correction type code is a code for identifying any of the above-described eight types of correction processing. After the number of character segmentations to be re-recognized, the start image number and the end image number of the character segmentation to be re-recognized are sequentially arranged. Finally, an end-of-file symbol is arranged.

In the above description, characters are processed. However, the present invention can be applied to the case of processing graphics. FIG. 31 to FIG. 38 show an embodiment in this case. FIGS. 31 to 38 correspond to the respective embodiments of FIGS. 3 to 10 in the case of correcting the above eight types of characters.

In the embodiment shown in FIG. 31, three figures and a straight line connecting them are input as shown in FIG. 31A, and as shown in FIG. , Graphic segmentation is divided into six. Therefore, as shown in FIG.
1 is first entered across the two graphic segmentations, as shown in FIG.
One graphic segmentation is changed to one segmentation, and the handwriting previously placed in a separate graphic segmentation is treated as a handwriting in one segmentation. As a result, a correct recognition result (a square in this embodiment) is obtained.

In the embodiment shown in FIG. 32, as shown in FIG. 31A, three figures and line segments connecting them are input as in the case of FIG. It is recognized as shown in FIG. In this embodiment, the first rectangle and the next horizontal line segment are 1
Is recognized as a figure in one figure segmentation. Then, as shown in FIG. 3C, when the handwriting range reduction instruction symbol 52 is input, as shown in FIG.
The handwriting arranged on the left and right of the handwriting range reduction instruction symbol (gesture) 52 is processed as a figure of separate figure segmentation.

In FIG. 33, as shown in FIG. 33A, three figures and horizontal line segments connecting them are input, and they are recognized as shown in FIG. ing. Of these figures, the rightmost figure has a left-hand arc-shaped line segment that is double-inputted, so that one of them is erased as shown in FIG. When the symbol 53 is input, the line segment corresponding to the handwriting part erasure symbol 53 is erased as shown in FIG.

In the embodiment shown in FIG. 34, as shown in FIG. 34A, a substantially rectangular figure and a single straight line extending downward from the approximate center of the figure are input. . Then, the figure is recognized as a figure in which a rectangle and a straight line are combined as shown in FIG. Therefore, as shown in FIG. 9C, when the partial handwriting position movement symbol 54 is set so that a part of a straight line is included in the loop portion and the tail portion is directed upward for a predetermined length, As shown in FIG. 3D, this straight line is moved to a position that divides the rectangle into approximately two.

In the embodiment shown in FIG. 35, as shown in FIG. 35A, an arrow is input between a square and a triangle. As shown in FIG. 3B, among these figures, a triangle figure is recognized as a small triangle. In this state, when the partial handwriting enlargement instruction symbol 55 is input so that the triangle is included in the rectangular loop and the tail portion of a predetermined length is protruded outward as shown in FIG. This triangle is modified to a larger triangle, as shown in d).

In the embodiment shown in FIG. 36, an arrow is input between a circle and a square as shown in FIG.
Then, as shown in FIG. 3B, the circle is recognized as a shape larger than the square. Then, as shown in FIG. 7C, when the partial handwriting reduction instruction symbol 56 is input so that the circle is included in the rectangular loop and the tail part projects inward, as shown in FIG. , This circle is reduced.

In the embodiment of FIG. 37, as shown in FIG. 37A, three figures and a line connecting them are input, and as shown in FIG. Recognized as figure segmentation. Then, as shown in FIG. 9C, when the additional handwriting 57 is input so as to connect the diagonal lines of the leftmost square figure, for example, a diagonal line is added to this square as shown in FIG. The shape is recognized.

In the embodiment shown in FIG. 38, as shown in FIG. 38 (a), a figure in which a part of the line on the left side of the circle is missing is input, and as shown in FIG. Has been recognized as. Therefore, as shown in FIG. 9C, the shape deformation symbol 58 is connected so that the missing portion of the circle is connected.
Is input, the figure is recognized not as an arc but as a circle, as shown in FIG.

As described above, the present invention has been described by taking as an example the case of processing characters and figures. However, the present invention can be applied to the case of processing an arbitrary shape.

[0110]

As described above, the handwriting input and display method of the present invention is as described above.
According to the handwriting input display device, when an intended recognition result is not obtained, a correction is instructed and a handwriting having a segmentation matching the correction instruction is generated, so that a correct recognition result is not obtained. In addition, a desired recognition result can be reliably obtained without re-inputting.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of an apparatus to which a handwriting input display method of the present invention is applied.

FIG. 2 is a flowchart illustrating the operation of the embodiment of FIG.

FIG. 3 is a diagram illustrating expansion of a handwriting range in character segmentation.

FIG. 4 is a diagram illustrating reduction of a handwriting range in character segmentation.

FIG. 5 is a diagram illustrating partial erasure of handwriting in character segmentation.

FIG. 6 is a diagram for explaining position movement of a subset of handwriting in character segmentation.

FIG. 7 is a diagram illustrating the enlargement of the size of a subset of handwriting in the character segmentation.

FIG. 8 is a diagram illustrating reduction in size of a subset of handwriting in character segmentation.

FIG. 9 is a diagram for explaining handwriting addition to handwriting in character segmentation.

FIG. 10 is a diagram illustrating shape deformation of a subset of handwriting in character segmentation.

FIG. 11 is a flowchart illustrating a more detailed process of step S7 in FIG. 2;

FIG. 12 is a flowchart illustrating a more detailed process of step S32 in FIG. 11;

FIG. 13 is a diagram for explaining the processing in FIG. 12;

FIG. 14 is a flowchart illustrating a more detailed process of step S33 in FIG. 11;

FIG. 15 is a diagram illustrating the process of FIG.

FIG. 16 is a flowchart illustrating a more detailed process of step S34 in FIG. 11;

FIG. 17 is a diagram for explaining the processing in FIG. 16;

FIG. 18 is a flowchart illustrating a more detailed process of step S35 in FIG. 11;

FIG. 19 is a view for explaining the processing in FIG. 18;

FIG. 20 is another diagram illustrating the process of step S35 in FIG. 11;

FIG. 21 is yet another diagram illustrating the process of FIG. 35;

FIG. 22 is a flowchart illustrating a more detailed process of step S36 in FIG. 11;

FIG. 23 is a view for explaining the processing in FIG. 22;

FIG. 24 is a flowchart illustrating a more detailed process of step S37 in FIG. 11;

FIG. 25 is a diagram for explaining the processing in FIG. 24;

FIG. 26 is a flowchart illustrating a more detailed process of step S38 in FIG. 11;

FIG. 27 is a diagram for explaining the processing in FIG. 26;

FIG. 28 is a flowchart illustrating a more detailed process of step S39 in FIG. 11;

FIG. 29 is a diagram for explaining the processing in FIG. 28;

30 is a diagram illustrating a correcting handwritten data based format.

FIG. 31 is a diagram illustrating a process of enlarging the handwriting range of a figure.

FIG. 32 is a diagram for explaining a handwriting range reduction process of a figure.

FIG. 33 is a diagram for explaining a handwriting part erasure process of a figure.

FIG. 34 is a diagram for describing a partial handwriting position moving process of a graphic.

FIG. 35 is a diagram illustrating a process of enlarging the size of a partial handwriting of a graphic.

FIG. 36 is a diagram illustrating a partial handwriting size reduction process of a graphic.

FIG. 37 is a diagram illustrating a process of adding a handwriting to a handwriting of a figure.

FIG. 38 is a diagram illustrating a shape deformation process of a handwriting of a figure.

FIG. 39 is a diagram illustrating a conventional character input method.

[Explanation of symbols]

 1 CPU 2 ROM 3 RAM 8 Bus line 11 Display controller 12 V-RAM 13 Display section 14 Tablet interface 15 Input tablet 16 Pen

Continuation of front page (56) References JP-A-4-336688 (JP, A) JP-A-1-237882 (JP, A) JP-A-7-37039 (JP, A) JP-A-5-182029 (JP) JP-A-6-4207 (JP, A) JP-A-6-242882 (JP, A) JP-A-59-2189 (JP, A) JP-A-60-75980 (JP, A) 63-78275 (JP, A) JP-A-61-107468 (JP, A) II. New OS for pen input in pursuit of portability: PenPoint, NIKKEI BYTE, Japan, April 1991, pp. 236-249 (58) Fields investigated (Int. Cl. ⁷ , DB name) G06K 9/00-9 / 82 G06F 3/03

Claims (4)

(57) [Claims] An input unit for receiving a handwriting input by a user
And a storage unit for recording information, and a display unit for displaying information.
In the handwriting input display method, a handwriting input of a handwriting to the input unit by the user may be performed.
An input control step of controlling and before the input is controlled by the processing of the input control step.
A handwriting storage control unit for controlling storage of handwriting in the storage unit;
And the memory is controlled by the processing of the handwriting memory control step.
Classify the handwriting into segmentation
And the storage is controlled by the processing of the first recognition step of obtaining a recognition result and the handwriting storage control step.
And the handwriting obtained in the first recognition step.
A first recognition result among the received recognition results.
A first display control step for controlling the display, and a brush newly input by the processing of the input control step.
Whether the trace is an instruction to correct the segmentation
A first determination step of determining the segmentation, and the processing of the first determination step
If it is determined that a correction instruction for the
The recognition result obtained by the processing of the first recognition step
The segmentation corrected by the correction instruction.
Whether the second recognition result corresponding to the
The second determination step and the processing of the second determination step determine whether the correction instruction
A second corresponding to said more modified segmentation
If it is determined that the recognition result of the second
Display control for displaying the recognition result of the image
Step and the processing of the second determination step, the correction instruction
A second corresponding to said more modified segmentation
If it is determined that the recognition result of
The brush stored by the process of the trace storage control step
Out of the trace, the segmentation based on the correction instruction
Character recognition for the part corresponding to the
A second recognition step of obtaining a third recognition result; and the second recognition step performed by the processing of the second recognition step.
A third display system that controls to display the recognition result of No. 3
And a step for displaying handwritten input. 2. The handwritten input display method according to claim 1, wherein the instruction to correct the segmentation is performed by a gesture. 3. The method according to claim 1, wherein the correction instruction of the segmentation is any one of enlargement, reduction, deletion, movement, and deformation of the input handwriting. Handwriting input display method described in. 4. An input means for receiving handwriting input of handwriting, Handwriting for storing the handwriting input by the input means
Storage means; Segmenting the handwriting stored by the handwriting storage means
And perform character recognition to obtain recognition results.
Recognition means; The handwriting stored by the handwriting storage means;
First recognition result among the recognition results obtained by the recognition means
Display means for displaying The handwriting newly input by the input means is
First to judge whether it is an instruction to correct the mention
Determination means, By the first determination means, the segmentation
If it is determined that a correction instruction has been input, the recognition means
To the recognition result obtained by
A second recognition corresponding to the corrected segmentation
Second determining means for determining whether or not the result is included;
With The second determination means corrects the data according to the correction instruction.
Second recognition result corresponding to said segmentation obtained
Is determined to be included, the display means
Further displaying the second recognition result, The second determining means corrects the data according to the correction instruction.
Second recognition result corresponding to said segmentation obtained
If it is determined that is not included, The recognition means is stored by the handwriting storage means.
Out of the handwriting Corresponds to the segmentation based on the correction instruction
New part In addition, character recognition is performed
Gain insights, The display means is configured to display the second information recognized by the recognition means.
Handwriting input characterized by further displaying the recognition result of No.3
Power display.