JPH06195324A - Method and device for inputting character - Google Patents

Abstract

PURPOSE:To convert a desired part in a recognized and displayed characterstring to a significant character by providing a selecting process for selecting a desired character from a displayed candidate group, and setting a selected character as a character of a result of conversion. CONSTITUTION:In a character input method for inputting a first character-string by converting it to a second character-string, input means 11, 12 for inputting a handwritten character, a recognizing means 13 for recognizing the inputted character, and a first display means for displaying the recognized and obtained character are provided. Also, this device is provided with a designating means 11 for designating a part of the displayed character, and a second display means 12 for referring to a BUSHU (a common part which becomes a guide for looking for a character) dictionary 23 in which a character and BUSHU discriminating information of the character are stored, selecting a character group having a designated BUSHU from in plural candidate groups which are recognized and obtained and setting it as a candidate group, and displaying it. In such a way, a desired character is selected from the displayed candidate group by a recognized candidate selecting means 22.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION The present invention relates to a character input method and device,
More specifically, the present invention relates to a character input method and device for converting a first character into a second character and inputting the converted character.

[0002]

2. Description of the Related Art Generally, a character recognition device extracts a characteristic of an input character, refers to a dictionary stored in advance, and outputs the most similar character among them as a first candidate. Since it is quite possible that the first candidate is not necessarily the intended character, by giving a predetermined instruction, the candidates are sequentially output in the second, third, ...

For example, it is assumed that "visit" is input by handwriting in a handwritten character recognition device. The first candidate is "Hu", and the second and lower candidates are "Loss", "Sales", "Visit", "Translation",
It is assumed that it was “set”.

In this case, since the target Chinese character is the fourth candidate, if the instruction to display the next candidate is given three times, it will be displayed on the screen.

[0005]

Originally, if input correctly, the intended character should be the first candidate, but if there are many similar characters or characters with a large number of strokes, etc. difficult.

In some cases, a large number of candidates, such as several tens, may be generated, and it is necessary to give instructions such as the next display many times until the target character is displayed.

Further, particularly in a low-priced recognition device, although it is possible to display a plurality of recognized candidates, the number of remaining candidates is at most a few, and it is still necessary to search for a target character. .

[0008]

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is a character that can efficiently narrow down a candidate group when searching for a target character from the recognition candidate group. It is intended to provide an input method.

The character input method of the present invention which achieves this object includes the following steps. That is, in the character input method of converting the first character string into the second character string and inputting it, the input step of inputting handwritten characters and the recognition step of recognizing the input character are obtained. It is obtained by referring to a first display process for displaying a character, a specified process for designating a part of the displayed character, and a radical dictionary storing the character and radical identifying information of the character. A character group having a specified radical is selected from the plurality of candidate groups to be a candidate group, and a desired display character is selected from the second display process to be displayed and the displayed candidate group. And a selection process.

A character input device that solves the first problem has the following structure. That is, in the character input device for converting the first character string into the second character string and inputting it, the input means for inputting the handwritten character, the recognizing means for recognizing the input character, and the recognized character are obtained. The first display means for displaying the character, the designating means for designating a part of the displayed character, the radical dictionary storing the radical identification information of the character, and the character are obtained by recognition. From the plurality of candidate groups, a character group having a designated radical is selected to form a candidate group, and a desired display character is selected from the second display unit and the displayed candidate group. And selection means.

In the second invention, when recognizing an input handwritten character string, it is possible to convert a desired portion of the recognized and displayed character string into a meaningful character. It is intended to provide a method.

In order to achieve this object, the character input method of the present invention includes the following steps. That is, in the character input method of converting the first character string into the second character string and inputting the input character string, an input step of inputting handwritten characters, a recognition step of recognizing the input character string, and an input character string Of the designated character string by referring to the display process for displaying the individual first recognition candidates of, the designated process for designating a desired continuous character string in the displayed character string, and the dictionary storing the idioms. And a search process for searching for the existence of a combination of candidate groups.

Further, the object of the second invention is achieved.
The character input device has the following configuration. That is, in a character input device for converting a first character string into a second character string and inputting it, an input means for inputting handwritten characters, a recognition means for recognizing the input character string, and an input character string. Of each of the first recognition candidates of, the designating means for designating a desired continuous character string in the displayed character string, and the dictionary storing the idiom are referred to And a search means for searching for the existence of a combination of candidate groups.

The third aspect of the present invention is to provide a character input method which enables a target character string to be obtained by a simple operation even if there is no candidate having all the intended characters in the conversion candidates. Is.

In order to achieve this object, the character input method of the third invention comprises the following steps. That is, in the character input method of converting the first character string into the second character string and inputting it, an input step of inputting the character string and a conversion step of converting the input character string into a kana-kanji mixed character string, A display process for displaying the converted candidate group and a design process for designating a plurality of desired partial character strings of the converted character string in the displayed candidate group are provided.

A character input device that solves the above-mentioned second problem has the following structure. That is, in a character input device for converting and inputting a first character string into a second character string, an input means for inputting the character string and a converting means for converting the input character string into a kana-kanji mixed character string. A display unit for displaying the converted candidate group and a specifying unit for specifying a plurality of desired partial character strings of the converted character string in the displayed candidate group are provided.

According to a fourth aspect of the present invention, even if there is no candidate having the intended entire character string in the converted candidate group, if there is a partial character string of the object, the object is targeted from the character string. It is intended to provide a character input method that makes it possible to obtain the entire character string.

In order to achieve this object, the character input method of the present invention comprises the following steps. That is, in the character input method of converting the first character string into the second character string and inputting it, an input step of inputting the character string and a conversion step of converting the input character string into a kana-kanji mixed character string, A first display step for displaying the converted candidate group, a designated step for designating a desired partial character string of the converted character string in the displayed candidate group, and a character string including the designated partial character string are displayed. A search process of searching with reference to a predetermined dictionary, a second display process of displaying a candidate group obtained by the search, and a desired process among the candidate groups displayed in the second display process. And a selection step for selecting one character string.

A character input device that solves the above-mentioned fourth problem has the following structure. That is, in a character input device for converting and inputting a first character string into a second character string, an input means for inputting the character string and a converting means for converting the input character string into a kana-kanji mixed character string. First display means for displaying the converted candidate group, designating means for designating a desired partial character string of the converted character string in the displayed candidate group, and character string including the designated partial character string are displayed. Search means for searching with reference to a predetermined dictionary, second display means for displaying a candidate group obtained by the search, and a desired group among the candidate groups displayed by the second display means 1 And a selection means for selecting one character string.

[0020]

In the process and configuration of the present invention, for example, when the recognition result for the input character is displayed and the radical is correct even if the recognition result is not the intended character, an instruction to that effect is given. By doing so, it becomes possible to narrow down to the character group having the same radical in the recognition result candidate group.

[0021]

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a block diagram of the character recognition apparatus in the embodiment. In the figure, 11 is a pen for inputting characters. An input / output unit 12 is composed of a liquid crystal display device and a coordinate input device located on the front surface of the display screen and provided with a transparent electrode plate having a plurality of input frames for handwritten characters. There is. The pen 11 is provided with a pen switch, which is turned on by pushing the pen 11 with a predetermined force. When a character is input, the coordinate data input while the pen 11 is being pressed is validated and the recognition process is performed. However, a point is displayed at the position on the display screen corresponding to the coordinate position input when the pen switch is on. As a result, it is possible to input a character as if the character is to be recognized by writing with a normal pen in the same sense.

Reference numeral 21 is a character recognition means for performing character recognition processing in accordance with the coordinate data obtained from the input / output unit 12 and outputting a plurality of character codes having a high degree of similarity, which is described in, for example, Japanese Patent Publication No. 62-39460. It is derived by the algorithm. Reference numeral 22 is a recognition candidate selection means for selecting from the group of candidates obtained from the character recognition means 21 by referring to the character radical dictionary 23. Details of the character radical dictionary 23 will be described later.

A concrete processing outline of the character recognition apparatus of the embodiment having the above-mentioned configuration will be described. However, the present apparatus is provided with a CPU (not shown) for performing its control and processing, a ROM storing the operation processing procedure of the CPU, and a RAM used as a work area. The program is stored in this ROM. It is the same in the second to fourth embodiments described later that the program according to the flowchart is stored in the ROM.

As shown in FIG. 5, the input / output unit 12 of the embodiment includes a frame for inputting characters, a logical erase button 56 for instructing to erase the displayed characters, and a recognition button 57 for instructing recognition. It is displayed. Each of the buttons 56 and 57 is designed to give an operation instruction by touching the position of the pen 11 (turning on the pen switch). For example, when a character is input by handwriting in the input frame of FIG. 5 and the pen 11 is touched with the recognition button 57, the input / output unit 12
The stroke of each input frame stored in the character recognition means 21
Passed to.

The character recognition means 21 analyzes the stroke for each input frame sent from the input / output unit 12, sends the obtained recognition candidate group for each input frame to the recognition candidate selection unit 22, and at the same time The recognition result is displayed by sending a character string composed of candidates to the input / output unit 12.

Now, as shown in FIG. 5, when "visit" is manually input and the recognition button 57 is touched with the pen 11, it is recognized (displayed) as "permit" as shown in FIG. . That is, it is a case where the handwritten character "visit" is recognized as "permission". If the candidate groups for the handwritten character "Visit" are shown in the order of similarity, "Hu", "Loss", "Sales", "Translation"
Assume the case of "visit""visit""set". That is, the recognition candidate selection means 22 stores these recognition candidates for the handwritten character "visit". Of course, other handwritten character strings "question" are also stored in the candidate group for each character, but since the recognition results of these are correct, description thereof will be omitted.

In the embodiment, when the result as shown in FIG. 6 is displayed, it is understood that at least the radicals (or deviations) of the characters "permissive" which are erroneously recognized are matched. Therefore, the operator gives a narrowing-down instruction for selecting a candidate for the erroneously recognized character.

Specifically, as shown in FIG. 7, the radical part of the character "permission" in the recognition result is moved from left to right (not on the left side of the porch "noon") with the pen 11 with a line 71. Is drawn (this line 71 does not necessarily have to be drawn). That is, “word” is selected as the radical to be selected. In addition, it is judged from the input coordinate position whether or not it is an input for the character "permission" which is the recognition result, and whether the written line is drawn from the left to the right only on the radical. it can.
Also, here, a line is drawn only in the horizontal direction above the radical, but as is clear from the explanation below, it is actually sufficient to draw a line that crosses a part of the entire character (a line that spans the entire frame is drawn. If the meaning is different).

When the operator receives an instruction on the radical part, the recognition candidate selection means 22 refers to the character radical dictionary 23 and refers to the character group as a department in the candidate group supplied from the character recognition means 21. Select only characters with ". In the case of the embodiment, the candidate for the handwritten character "Visit" is "Hu"
Since "loss", "sales", "translation", "custom", "visit", and "set", "translation", "custom", "visit", and "set" are selected. As a result, as shown in the figure, these selected candidate groups are displayed as shown in the window 70. The operator looks at this window and touches the desired character "visit" with the pen 11 to correct the recognition result.

Further, when the tracing range is set to cross the entire character, the selection direction is all parts, so that the recognized results are displayed in the same order as shown in FIG. It should be noted that the number of candidates displayed as shown is four in the case shown, and if there is no target character among them, the next candidate is displayed by performing a predetermined operation.
At least, the characters as candidates can be narrowed down, which is significantly advantageous as compared with the conventional character recognition devices.

In the embodiment, in order to realize the above process, the character radical dictionary 23 stores a radical table that stores the relation between radical types and their existing positions, each character code and the part of the character. It is a character table that stores neck relationships. A specific example of this radical table is shown in FIG. 3, and a specific example of the character table is shown in FIG.

As described above, as shown in FIG. 6, when pen input is performed in the input frame in which the first candidate is displayed,
It can be judged that the input is for the character "permitted" from the coordinate position.

The JIS code for the character "Ku" is "3576".
Therefore, by referring to the character table, it is found that the radical code is “72”. The radical code “72” refers to the radical table, and the designation method is when tracing with the pen from left to right.
In the state of FIG. 6, it can be confirmed that the radical “word” has been selected.

Therefore, the recognition candidate selection means 22 supplies from the character recognition means 21 only the character having the same radical code as the first recognition candidate "permission" for the handwritten character "visit" supplied from the character recognition means 21. The selected candidate group is selected and displayed as a window 70 as shown in FIG.

In the radical table of FIG. 3, there are two radicals for the same radical "shellfish" because the radicals are located on the left and right sides of the character and on the upper and lower sides. It comes from being there. That is, the letters "loss" and the letters "negative"
And are the same radical as each other, but their existence position is different.
In order to distinguish this, in the embodiment, as shown in the figure, different radical cords are attached depending on the positions where radicals may exist. For example, as a result of inputting a certain character, "negative" is input, and by drawing a half line up and down, the radical "shellfish" located below is selected.

When the above processing contents are summarized here, the recognition candidate selection means 22 of the embodiment may proceed the processing in the procedure shown in FIG.

It has already been explained that when a character is input by handwriting, the character recognition means 21 displays the first candidate for the input character (or character string) and sends the candidate group to the recognition candidate selection means 22. .

Therefore, first, in step S21, a candidate group for the character input from the character recognition means 21 is input. Then, in step S22, the radical for the first candidate is obtained using the character table shown in FIG. 4 (at this time, the character of the first candidate is displayed on the screen of the input / output unit 12). ).

In the next step S23, it is determined whether or not there is an input by the pen 11 in the character input frame just recognized. If it is determined that the input is other than the input box, it is determined that it is the next character input to be recognized or a specific instruction, and the process proceeds to step S24.

If it is just recognized and it is judged that the first candidate is an input to the inside of the displayed frame, the process proceeds to step S25 and the start position and the end position of the input are input to the entire frame. Determine whether it is an instruction.

If it is determined that the instruction is for the entire frame, the flow advances to step S26 to display the input candidate group in the same rank. If it is determined that the instruction is not for the entire frame, the process proceeds to step S27, and the character having the radical of the first candidate is selected from the input candidate group and the selected character is displayed. .

When the process proceeds to step S28, one of the displayed candidates is selected and the correction of the erroneously recognized character of interest is completed.

As described above, according to the embodiment, when a character having the same radical is recognized although it is erroneously recognized, a predetermined operation is performed to display only candidates having the same radical. Therefore, it becomes easy to find the desired character.

<Description of Second Embodiment> The above-mentioned embodiment (first embodiment)
In the second embodiment), the candidates are efficiently narrowed down even if the radical is the same as the desired character while being erroneously recognized. However, two or more characters input in the second embodiment ( An example of correcting the input character based on the (character string) will be described.

FIG. 9 shows a block configuration of the second embodiment. The difference from the first embodiment is that the recognition candidate character string selection means 24 and the idiom dictionary 25 have changed.

The outline will be described. Now using the pen 11,
When I input "visit" and gave recognition instruction,
As shown in 2, it is assumed that it is recognized as "forgive". Upon seeing this result, the operator draws a line with a pen so as to cross the "forbidden" part that is erroneous as a idiom or a word (the line need not be drawn as in the first embodiment). ).

Although the explanation is before and after, the recognition candidate for the handwritten character "visit" and the rank of the similarity thereof are the same as those in the first embodiment, and the candidate of the recognition result for the handwritten character "question" and the rank thereof are "question". , "Between".

The recognition candidate character string selecting means 24 searches the phrase dictionary 25 for a character string based on a combination of individual candidates. However, in order to reduce the number of combinations, one of the two characters designated by the pen 11 may be correctly recognized, and, for example, “grant” may be excluded.

Then, the character string displayed in the designated range is replaced with the character string obtained by the search.

The internal structure of the idiom dictionary 25 is, for example, as shown in FIG. 11, in which a combination of Kanji codes is stored.

In the above example, there is "visit" in the combination, and the code of the character string is "4B2C" +
Since it is confirmed that "4C64" actually exists in the phrase dictionary 25, the misrecognized character string "permission" is replaced by the correct answer "visit".

The operation of the recognition candidate character string selection means 24 in the second embodiment will be described with reference to the flowchart of FIG.

First, in step S31, a candidate group for each handwritten character string input from the character recognition means 21 is input.

Then, in step S32, it is determined whether or not the input by the pen 11 is for the frame displaying the result just recognized. If it is determined that the input is other than the frame, the process proceeds to step S33 and the corresponding process is performed.

If it is determined that the pen 11 has been input for the recognized character (character string), step S34
Then, it is determined whether or not the instruction is an instruction that extends over two or more characters in the character string of the recognition result. If it is determined that the instruction is for only one character, the process proceeds to step S35 to display the second candidate of the instructed character and the subsequent candidates,
Ask one of them to be selected in step S36.

On the other hand, if it is determined that the instruction is for two or more characters, the process advances to step S37 to search whether the combination of individual candidate characters forming the instructed character string exists in the idiom dictionary 25. Then, as a result, the found character string is deleted from the specified character string, and it is displayed at that position.
Correct the recognition result.

<Explanation of Third Embodiment> Next, in the above first and second embodiments, the handwritten character itself is recognized. The case of inputting and recognizing it and converting it into kana-kanji will be explained. However, in the third embodiment, since there is a feature after the reading is input, the reading may be input by using the pen, the keyboard, or another device.

The problem will be pointed out with reference to FIGS. These drawings correspond to the input / output unit 12 in the first and second embodiments.

Now, using the pen 124, "Rieko"
Suppose you typed "Rieko" in the hope that it would be converted to. FIG. 24 shows an example of the converted state.

If the target phrase is displayed on the candidate display section 122, the target phrase is output to the text display section 121 by touching the display.

However, as shown in FIG. 24, when the target idiom (expected idiom) is not displayed on the text display section 122, the "next candidate" key or the "previous candidate" key of the kana conversion section 123 is pressed by the pen 124. Touch with to display other candidates. Nevertheless, if the target phrase does not exist in the candidates, the delimiter position for kana-kanji conversion is adjusted using the "delimiter ←" key or the "delimiter →" key, and conversion is performed again.

In the state of FIG. 24, the input kana characters are 3
It means that the characters are separated by the first character, but if you touch the "Break ←" key twice, it will be separated by the first character as shown in FIG. 25. Is displayed. When the target kanji "Ri" is displayed, by touching the display, the kanji candidates for the kana character string "e" are displayed next, as shown in FIG.

By repeating the same operation, the target idiom is output to the text display section 121.

However, in this case, it is necessary to repeat the operation until the desired idiom is displayed. In addition, since there are many candidates, there is a problem that the number of operations and the operation require a great deal of time.

Therefore, in the third embodiment, an example for solving such a point will be described.

First, a screen transition example of the kana-kanji conversion device of the third embodiment is shown in FIGS. 14 to 16 and will be described. Also in this embodiment, operation and input are performed by touching or writing on the screen with the pen 124. However,
The same applies to a mouse, a keyboard, etc., and thus the present invention is not limited thereto. Similarly to the previous example, a case where the character string "Rieko" is input in the expectation that it will be converted to "Rieko" will be described.

As shown in FIG. 14, even when the target idiom is not displayed on the candidate display portion 122, the displayed idiom candidates may include a character common to the target idiom. For example, a part of the target idiom is output to the text display unit 121 by enclosing the character with a circle using the pen 124, for example. Further, as shown in FIG. 15, two or more characters can be surrounded by a circle. By the above operation, the target idiom can be output to the text display unit 121 as shown in FIG.

A block configuration of the kana-kanji conversion device of the third embodiment is shown in FIG. 13, and each unit will be described in the order of the flowchart of FIG.

First, in step S51, the text input means 101 inputs or edits a character string by using character recognition or a keyboard. In step S52, the text output means 102 outputs the input character string to the screen. In step S53, the conversion operation means 103 designates the range of kana-kanji conversion for the character string input to the text input means 101 and activates the conversion means 104.

In step S54, the conversion means 10
Reference numeral 4 converts the input kana character string into a kanji / kana mixed character string and outputs it to the text output means 102. In step S55, when a plurality of kana-kanji mixed character strings correspond to a kana character string, each kanji-kana mixed character string is output as a candidate to the candidate output means 106.

Then, in step S56, a pen input on the screen is awaited.

In step S57, if the position of the pen input is the candidate display portion 22 and the locus is recognized as a point, it is interpreted as the input of the idiom selection command, and the process proceeds to step S58. It proceeds to step S60.

In step S58, the idiom selection means 1
At 07, it is determined which candidate is displayed at the position where the point is input, and the entire character string of the candidate is extracted. Then, in step S59, the extracted character string is output to the text output means 102.

Further, when the processing proceeds to step S60, if the position of the pen input is the candidate display portion 122 and the locus is recognized as a circle, it is interpreted as the input of the phrase selection command. If not, the process proceeds to step S63.

In step S61, the character selection means 108 extracts all the characters included in the area surrounded by the circles. Specifically, as shown in FIG. 23, the X coordinate of the center of the character is between the X coordinate of the left end and the X coordinate of the right end of the locus of the circle, and the Y coordinate of the center of the character is the circle of the circle. When it is between the Y coordinate of the upper end and the Y coordinate of the lower end of the locus, it is determined that the character is included in the area. In step S62, the extracted character is converted into the text output means 2
Output to.

On the other hand, when the process proceeds to step S63, the process for other commands is performed. here,
The candidates to be displayed may be switched using the "next candidate" key, the "division ←" key, or the like. Moreover, you may decide the conversion result with respect to this idiom.

In step S64, if the conversion result is confirmed by the processing in step S63, the process proceeds to step S65. If not, step S
Return to 51.

In step S65, the idiom registration means 105 newly registers the character string obtained by repeating the character selection command in the idiom dictionary.

By the above operation, if the displayed idiom candidate includes the target idiom and the character in the chest, the character can be directly output to the text output means by selecting the character. Even if the target idiom is not displayed as a candidate, there is an effect that the number of operations for displaying another candidate or changing the length of a delimiter is smaller than that of the conventional kana-kanji conversion device.

Further, by adding the function of newly registering the character string thus obtained in the idiom dictionary, when the same idiom is converted next time, the entire idiom can be designated at once. , Can be operated faster.

<Explanation of Fourth Embodiment> FIGS. 19 and 20 show examples of screens of the kana-kanji conversion device of the fourth embodiment.

To simplify the explanation, the case of converting the reading "Rieko" into "Rieko" will be explained.

If the target idiom is displayed on the candidate display portion 122, the target idiom is output to the text display portion 21 by touching the display (that is, the locus is a point). It

As shown in FIG. 19, even when the target idiom is not displayed on the candidate display portion 122, if the displayed idiom candidates include a character common to the target idiom. By enclosing the character with a circle with the pen 24, only the idiom including the character is displayed from the candidates as shown in FIG.

FIG. 18 shows a block diagram of a kana-kanji conversion device according to the fourth embodiment.

In this embodiment, the matching means 10
Reference numeral 9 compares each candidate character string with a candidate character string marked with a circle, and outputs the former candidate character string to the candidate output means 106 when the characters surrounded by a circle match.

On the contrary, as shown in FIG. 21, by putting a mark X on a character that is not common to the target idiom, as shown in FIG.
It is also possible to display candidates in which the marked characters are replaced with other characters (corresponding to the case where a mark other than the X mark is logically surrounded by a ○ mark).

As a result of the above operation, if at least one character common to the target idiom is included in the displayed idiom candidates, the number of candidates to be displayed is limited by selecting the character. Therefore, even if the number of candidates is large and the target idiom is not displayed immediately as a candidate, the number of operations for displaying other candidates is smaller than that of the conventional kana-kanji conversion device. is there.

In the above embodiments, each device is described as a single device, but it goes without saying that a system that operates by combining a plurality of devices (apparatus) may be used. Further, although the program for realizing the function is stored in the ROM, it goes without saying that the program may be externally loaded and executed.

[0091]

As described above, according to the first invention, it is possible to efficiently narrow down a candidate group when searching for a target character from the recognition candidate group.

According to the second invention, when recognizing an input handwritten character string, it is possible to convert a desired portion in the recognized and displayed character string into a significant character. .

Further, according to the third invention, even if there is no candidate having all the intended characters in the conversion candidates, the target character string can be obtained by a simple operation.

Further, according to the fourth invention, even if there is no candidate having all the intended character strings in the converted candidate group, if there is a target partial character string, the character string It is possible to obtain the target entire character string from.

[0095]

[Brief description of drawings]

FIG. 1 is a block configuration diagram of a character recognition device in a first embodiment.

FIG. 2 is a flowchart showing a character processing procedure in the first embodiment.

FIG. 3 is a diagram showing an example of contents of a radical table in the first embodiment.

FIG. 4 is a diagram showing an example of contents of a character table in the first embodiment.

FIG. 5 is a diagram showing an input example of a handwritten character string in the first embodiment.

FIG. 6 is a diagram showing an example of a recognition result in the first embodiment.

FIG. 7 is a diagram for explaining an operation example of narrowing down candidates in the first embodiment.

FIG. 8 is a diagram showing an operation example of displaying another candidate of the recognition result in the first embodiment.

FIG. 9 is a block configuration diagram of a character recognition device according to a second embodiment.

FIG. 10 is a flowchart showing a character processing procedure in the second embodiment.

FIG. 11 is a diagram showing an example of contents of a phrase dictionary according to the second embodiment.

FIG. 12 is a diagram showing a correction operation of a recognition candidate character string in the second embodiment.

FIG. 13 is a block configuration diagram of a character processing device according to a third embodiment.

FIG. 14 is a diagram showing an example of a correction processing operation for kana-kanji conversion according to the third embodiment.

FIG. 15 is a diagram showing an example of a correction processing operation for kana-kanji conversion in the third embodiment.

FIG. 16 is a diagram showing a state in which a target character string is converted in the third embodiment.

FIG. 17 is a flowchart showing the contents of character processing in the third embodiment.

FIG. 18 is a block configuration diagram of a character processing device according to a fourth embodiment.

FIG. 19 is a diagram showing an example of a correction processing operation for kana-kanji conversion according to the fourth embodiment.

FIG. 20 is a diagram showing an example of a correction processing operation for kana-kanji conversion according to the fourth embodiment.

FIG. 21 is a diagram showing an example of another correction processing operation of kana-kanji conversion according to the fourth embodiment.

FIG. 22 is a diagram showing an example of another correction processing operation of kana-kanji conversion in the fourth embodiment.

FIG. 23 is a diagram for explaining the principle of designation and determination of a specific character string in the third or fourth embodiment.

FIG. 24 is a diagram showing a general kana-kanji conversion operation procedure.

FIG. 25 is a diagram showing a general kana-kanji conversion operation procedure.

FIG. 26 is a diagram showing a general kana-kanji conversion operation procedure.

[Explanation of symbols]

 11 pen 12 input / output section 21 character recognition means 22 recognition candidate selection means 23 character radical dictionary

Front page continued (72) Inventor Takashi Harada 3-30-2 Shimomaruko, Ota-ku, Tokyo Canon Inc. (72) Inventor Eiji Takasu 3-30-2 Shimomaruko, Ota-ku, Tokyo Canon Inc. (72) Inventor Katsuhiko Sakaguchi 3-30-2 Shimomaruko, Ota-ku, Tokyo Canon Inc.

Claims (8)

[Claims] 1. A character input method for converting a first character string into a second character string and inputting the input character string, wherein an input step of inputting a handwritten character and a recognition step of recognizing the input character are performed. The first display step for displaying the obtained character, the specified step for specifying a part of the displayed character, and the radical dictionary storing the character and radical identification information of the character are referred to for recognition. A character group having a specified radical is selected from the plurality of obtained candidate groups to form a candidate group, and a second display step for displaying and a desired character from the displayed candidate group. A character input method comprising: a selecting step for selecting, and selecting the selected character as a character of a conversion result. 2. In a character input device for converting a first character string into a second character string and inputting the input character, input means for inputting handwritten characters, recognition means for recognizing the input characters, The first display means for displaying the obtained character, the designating means for designating a part of the displayed character, and the radical dictionary storing the character and radical identification information of the character are referred to for recognition. Second display means for selecting and displaying a character group having a designated radical from the plurality of obtained candidate groups and displaying the selected character group, and a desired character from the displayed candidate group. A character input device, comprising: a selecting unit for selecting the selected character, the selected character being a character resulting from the conversion. 3. A character input method for converting a first character string into a second character string and inputting the input character string, wherein an input step of inputting a handwritten character and a recognition step of recognizing the input character string are input. The display process for displaying the individual first recognition candidates of the displayed character string, the specified process for specifying the desired continuous character string in the displayed character string, and the dictionary for storing the idiom are referred to for the specified process. A character input method comprising: a search step for searching for the existence of a combination of character string candidate groups, and using the character string obtained by the search as a conversion result. 4. A character input device for converting a first character string into a second character string and inputting the input character string, inputting means for inputting handwritten characters, and recognizing means for recognizing the input character string. The display means for displaying the respective first recognition candidates of the character string, the designating means for designating a desired continuous character string in the displayed character string, and the dictionary storing the idiom are referred to and designated. A character input device comprising: a search means for searching for the presence of a combination of a candidate group of character strings, wherein the character string obtained by the search is used as a conversion result. 5. A character input method for converting a first character string into a second character string and inputting the same, wherein an input step of inputting the character string and a conversion for converting the input character string into a kana-kanji mixed character string. The process includes a process, a display process for displaying the converted candidate group, and a designated process for designating a plurality of desired partial character strings of the converted character string in the displayed candidate group. A character input method, wherein a combination of partial character strings is used as a character string of a conversion result. 6. A character input device for converting a first character string into a second character string and inputting the input character string, and converting the input character string into a kana-kanji mixed character string. Means for displaying the converted candidate group, and designating means for designating a plurality of desired partial character strings of the converted character string in the displayed candidate group, and designated by the designating means. A character input method, wherein a combination of partial character strings is used as a character string of a conversion result. 7. A character input method for converting a first character string into a second character string and inputting it, wherein an input step of inputting the character string and a conversion for converting the input character string into a kana-kanji mixed character string. Including a step, a first display step for displaying the converted candidate group, a designated step for designating a desired partial character string of the converted character string in the displayed candidate group, and a designated partial character string A search process for searching a character string by referring to a predetermined dictionary, a second display process for displaying a candidate group obtained by the search, and a desired process selected from the candidate groups displayed in the second display process. And a selection step for selecting one character string, and the character string selected in the selection step is used as a conversion result. 8. A character input device for converting and inputting a first character string into a second character string, and inputting means for inputting the character string, and conversion for converting the input character string into a kana-kanji mixed character string. Means, first display means for displaying the converted candidate group, specifying means for specifying a desired partial character string of the converted character string in the displayed candidate group, and the specified partial character string Retrieval means for retrieving a character string by referring to a predetermined dictionary, second display means for displaying a candidate group obtained by retrieval, and a desired group among the candidate groups displayed by the second display means. A character input device, comprising: a selection unit that selects one of the character strings, and the character string selected by the selection unit is used as a conversion result.