JP2022148901A - Character recognition apparatus, character recognition method, and program - Google Patents

Abstract

To efficiently utilize handwritten information so that a desired character can be selected from a wide range of candidates.SOLUTION: A character recognition apparatus includes: a touch-panel display unit 17 which receives a character image based on a handwritten input operation; and a control unit 21 which executes recognition processing on the received character image to derive a first character from the character image, and causes the touch-panel display unit 17 to display the derived first character as a candidate of character desired by a user. The touch-panel display unit 17 can receive a designation operation indicating that the first character is not the character desired by the user but a character similar to the character desired by the user. The control unit 21 derives, when receiving the designation operation, a second character having a predetermined relationship with the first character, and causes the touch-panel display unit 17 to display the derived second character as an additional candidate of the character desired by the user.SELECTED DRAWING: Figure 2

Description

The present invention relates to a character recognition device, character recognition method and program.

There has been proposed a technique of sequentially displaying recognition candidate characters for each character to be corrected in a series of character strings recognized by handwritten input and easily correcting them to desired recognition candidate characters without the need for selection operations. (For example, Patent Document 1)

Japanese Patent Application Laid-Open No. 2008-299431

Including the technique described in the patent document, if there is no desired character among a plurality of characters that are candidates for correction, it is necessary to perform character recognition processing by handwriting again.

The present invention has been made in view of the above circumstances, and its object is to make effective use of handwritten input contents and to accept selection of desired characters from a wide range of candidates. It is an object of the present invention to provide a character recognition device, a character recognition method, and a program.

According to one aspect of the present invention, an input unit that receives a character image based on an input operation in a handwritten format, performs recognition processing on the character image received by the input unit, and recognizes a first character from the character image. and a display control unit configured to display the first character derived by the character derivation unit as a candidate for a character desired by the user, wherein the input unit receives the first character , a designation operation indicating that the character is not the character desired by the user but is similar to the character desired by the user, and the character derivation unit receives the designation operation by the input unit Then, a second character having a predetermined relationship with the first character is further derived, and the display control unit converts the second character derived by the character derivation unit into a character desired by the user. It is characterized in that it is displayed as an additional candidate.

According to the present invention, it is possible to effectively utilize handwritten input content and accept selection of a desired character from a wide range of candidates.

1 is a diagram showing the external configuration of an electronic dictionary according to one embodiment of the present invention; FIG. FIG. 2 is a block diagram showing the functional configuration of an electronic circuit of the electronic dictionary according to the same embodiment; 4 is a flow chart showing the processing contents for handwritten input characters according to the embodiment; 4 is a flowchart of a subroutine showing detailed processing contents of stroke data correction processing of FIG. 3 according to the embodiment; The figure which illustrates the screen which shows the handwritten character input and its recognition result which concern on the same embodiment. FIG. 4 is a diagram showing a process of deriving a plurality of corrected stroke data according to the same embodiment; FIG. 4 is a diagram showing transition of screens of the touch panel type display unit according to the embodiment; FIG. 4 is a diagram showing transition of screens of the touch panel type display unit according to the embodiment; FIG. 4 is a diagram exemplifying a part of a biased table stored in various table storage areas according to the embodiment; FIG. 10 is a diagram for explaining a process of deriving biased Kanji candidates from user-inputted stroke data according to the embodiment; FIG. 10 is a diagram showing an example in which user-inputted stroke data is replaced with the most recent character shape component according to the embodiment;

An embodiment in which the present invention is applied to an electronic dictionary will be described below with reference to the drawings.
[Constitution]
FIG. 1 is a front view showing the external configuration of an electronic dictionary 10 according to the embodiment. Note that this embodiment is configured not only as an electronic dictionary 10 described below, but also as a tablet-type PC (Personal Computer) equipped with a dictionary function, a smartphone, an electronic book, a portable game machine, a server on a communication network. and so on.

The electronic dictionary 10 comprises a foldable case in which a body case 11 and a lid case 12 can be opened/closed via a hinge portion 13 . [Home] key 14a, function designation key 14b, character input key 14c, [decision] key 14d, [return] key 14e, [BOX] key 14f, cursor movement A key input section 14 (hardware keys) including a key 14g, a [shift] key 14h, etc., an audio output section (including a speaker) 15, an audio input section (including a microphone) 16, and the like are provided.

A touch panel type display unit 17 is provided on the surface of the lid case 12 . The touch panel type display unit 17 has a structure in which a touch position detection device for detecting a position touched by the user of the electronic dictionary 10 with a pen or finger and a display device are integrated, and a transparent touch panel is provided on a backlit liquid crystal screen. are laminated. In other words, the touch panel display unit 17 functions as an input unit that receives character images based on handwritten input operations.

A [Home] key 14a of the key input unit 14 is a key for causing the key input unit 14 to display a home screen. Although not shown, a plurality of icons registered according to initial settings of the electronic dictionary 10 or user operations are displayed. Each icon is a drawing or symbol for realizing a function corresponding to the notation of the icon. For example, it includes an application icon that directly activates a function (application) that uses dictionary content or learning content, and a group icon that displays a list screen of icons of a plurality of functions belonging to one category.

The function designation key 14b of the key input unit 14 is a key for directly designating dictionary contents written on each key. Function designation keys 14b include a [multiple dictionaries] key that dares not specify the category of dictionary content, and keys that specify the same category ([National] key, [Old Japanese] key, [Kanwa] key, [English-English] key, etc.). , a [content list] key for displaying a list of dictionary contents, and a [learning notebook] key, which is one category of tools.

Further, when the keys of the key input unit 14 are operated after the [Shift] key 14h is operated, they are not written without a frame on the key top, but are written with a frame. functions as a key. For example, if the [Delete] key is operated after the [Shift] key 14h is operated, it functions as a [Set] key instead of the [Delete] key.

In FIG. 1, [Japanese Dictionary] is selected, and in the search character string input section 41 located in the upper part of the touch panel type display section 17, the kana input tag of the kana input tag (Aiu) and the alphabet input tag (ABC) is Indicates selected state.

The character string [Nikko] has already been entered in the search character string input field 41 . In the candidate display area 42 below the search character string input area 41, for example, three headwords corresponding to the character string [Nikko] are displayed as a list. Further, a handwritten character input area 43 for two characters is displayed below the candidate display area 42, showing a blank state to wait for handwritten input of characters following the character string [Sunshine].

FIG. 2 is a block diagram showing the functional configuration of the electronic circuit of the electronic dictionary 10. As shown in FIG.
The electronic circuit of the electronic dictionary 10 includes a control section (CPU: Central Processing Unit) 21 which is a computer. The control section 21 controls the operation of each section of the circuit according to a control program pre-stored in the storage section 22 such as a flash ROM. The number of processors such as CPUs may be one or two or more.

Note that at least one of the control program and later-described dictionary data may be read from an external recording medium 23 such as a memory card by the recording medium reading unit 24 and stored in the storage unit 22 , or may be stored in the storage unit 22 via the communication unit 25 . It is also possible to store in the storage unit 22 those downloaded from a web server or the like on a network (not shown).

The control unit 21 is connected to a storage unit 22, a recording medium reading unit 24, and a communication unit 25 via a data bus and a control bus. Connect the display unit 17 .

The storage unit 22 stores a system program that controls the overall operation of the electronic dictionary 10, a communication program that communicates with an external device via the communication unit 25, a search processing program storage area 22a, and a dictionary data storage area 22b. , a search history storage area 22c, a work data storage area 22d, etc., are secured for storing programs and data for executing various functions of the electronic dictionary 10. FIG.

The search processing program storage area 22a is based on various dictionary contents (English-English dictionary/English-Japanese dictionary/Japanese-English dictionary/English-English dictionary/Japanese dictionary/encyclopedia/...) stored as dictionary data in the dictionary data storage area 22b. , a control program for retrieving and displaying descriptive information such as a user-desired headword and translations, meanings, examples, and explanations corresponding to the headword, and executing searches according to inputs other than character input of headwords. This is an area for storing various table storage areas 22a1 and the like used when

The various table storage area 22a1 stores a plurality of tables including a partial table that defines in advance how the constituent radicals of each character data of Chinese characters can be divided.

In the search history storage area 22c, when the headwords and their description information are displayed as the search results according to the search according to the user's operation, the headwords to be searched are stored as the search history together with the information of the number of searches. be done.

In the work data storage area 22d, various data acquired or generated by the control unit 21 and data input according to user operations are stored in accordance with the control of the operation of each circuit unit according to the control program by the control unit 21. Data is temporarily stored (held) as needed.

The communication unit 25 wirelessly connects to similar external devices such as electronic dictionaries that exist in the vicinity based on, for example, the BLE (Bluetooth (registered trademark) Low Energy) standard, which is one of wireless PAN (Personal Area Network) technologies. In addition, it wirelessly connects to a web server or the like on an external network (not shown) via a wireless router or the like to download a control program or the like.

[motion]
Next, the operation of this embodiment will be described.
In this embodiment, the operation of correction processing when the result of recognizing a character image input by handwriting at the time of function selection of the Japanese dictionary is not the kanji characters desired by the user will be described.

Here, for example, a character image of a character string [Sunlight] is input by handwriting input as a search character string, and is recognized as desired. A case where the desired character [Yu] is not found in the character candidates of the recognition result of the character image obtained will be described.

FIG. 5A shows that the user of the electronic dictionary 10 writes and inputs the character image of the character [bath] on the handwritten character input unit 43 with the stylus pen P from the display state of the touch panel type display unit 17 shown in FIG. Shows the screen when

As shown, the handwritten character input section 43 has an input area for two characters. On the other hand, for example, after inputting handwriting on the left side, the stylus pen P is used to instruct execution of recognition processing for the input character on the right side.

In response to an instruction to execute the recognition process with the stylus pen P, the control unit 21 executes the character recognition process, and displays a list of character candidates as recognition results in the order in which the degree of similarity is evaluated as high. That is, the control unit 21 performs recognition processing on a character image received by the input unit, and has a character derivation unit that derives the first character from the character image, and the first character derived by the character derivation unit. is displayed as a character candidate desired by the user.

FIG. 5(B) shows a list of Kanji candidates evaluated as having high similarity in the candidate character display section 44 . Since the desired Chinese character [Yu] is not included in the candidate character display section 44, the user needs to perform an operation to correct the handwritten input character.

FIG. 3 is a flow chart showing the details of the process performed by the control unit 21 on handwritten input characters.

At the beginning of the process, the control unit 21 acquires information on candidate characters as recognition results (step S101), and displays a list of these candidate characters on the candidate character display unit 44 as shown in FIG. 5B. .

From the state in which this list of Chinese character candidates is displayed, the control unit 21 determines whether or not one candidate that seems to be the closest has been long-pressed (step S103), whether or not one candidate has been selected (step S107). By repeatedly determining whether or not an operation to cancel the display has been performed (step S109), it waits for any of these inputs.

If it is determined in step S107 that the operation to cancel the list display has been performed (YES in step S109), the control unit 21 ends the processing of FIG.

FIG. 7(A) shows a state in which the user long-presses the Chinese character candidate [洽] in the handwritten character input unit 43 with the stylus pen P on the screen of the touch panel display unit 17 shown in FIG. 5(B). is posted.

In step S103, when it is determined that a long press operation has been performed on one candidate, the control unit 21 determines the character shape of the candidate kanji selected as having the highest similarity to the original input stroke data handwritten. , stroke data correction processing is executed to derive a plurality of corrected stroke data (step S104).

FIG. 6 is a diagram illustrating the process of deriving a plurality of corrected stroke data. In accordance with the stroke data of the handwritten input character shown in FIG. 6A and the shape of the character [洽] selected by the user as shown in FIG. derives corrected stroke data 1 shown in FIG. 6(C) and corrected stroke data 2 shown in FIG. 6(D).

FIG. 4 is a flowchart of a subroutine showing details of the stroke data correction process executed by the control unit 21 in step S104. Initially, the user's input stroke data is scanned to derive glyph analysis data including outlines, blank information, and clustering information (step S201).

Based on the derived character shape analysis data, the control unit 21 refers to the biased type table stored in the various table storage area 22a1, and derives biased type candidates for the stroke data input by the user (step S202).

FIG. 9 is a diagram illustrating a part of the biased table stored in the various table storage area 22a1. As shown in FIG. 9, the radical structure of a Chinese character is composed of the han and ji shown in FIG. 9(A), the crown and base shown in FIG. 9(D), 9(E) and other radicals shown in FIG. 9(F) can be classified into things that cannot be divided into

10A and 10B are diagrams for explaining the process of deriving biased kanji candidates from stroke data input by the user. As shown in FIG. 10A, the stroke data input by the user shown in FIGS. 5A and 6A is sequentially scanned vertically and horizontally in one direction.

FIG. 10B shows the result of deriving the stroke data outline OF, blank information SI, and density information CI based on the density of the character image from the scanning result. From these derivation results, as shown in FIG. 10(C), it is recognized that the radical Rix1 and Rix2 shown in FIG. Then, a biased candidate with a high degree of similarity is derived.

In FIG. 10(C), the stroke data input by the user is recognized as consisting of the left and right sides shown in FIG. 9(A). The Chinese character candidate [洽] in the input section 43 is also composed of angled and angled as shown in FIG. 9(A). In this way, when the eccentric type determined from the handwritten input character image matches the eccentric type of the character selected as having a closer character shape, the eccentric type candidate is limited to one. On the other hand, if the eccentric type determined from the handwritten input character image does not match the eccentric type of the character selected as having a closer character shape, each is derived as a eccentric type candidate. That is, the control unit 21 for deriving two biased candidates selects one unselected candidate from among the derived biased candidates (step S203). If the control unit 21 selects one of the unselected candidates, for example, the bias and the extreme shown in FIG. Next], [2] is derived (step S204).

Next, the control unit 21 selects one of the components of the user input, for example, [bias] (step S205). The control unit 21 selects one component of the recent character [洽] selected by the user, for example, [Sanzui (三水)], for the selected component [Ban] (step S206).

The control unit 21 further determines whether or not it is possible to omit processing such as replacement, which will be described later, for the selected component, for example, [Sanzui] (step S207). This is to reduce processing steps such as replacement of unnecessary user-inputted stroke data and each component of the latest character by setting restrictions such as not arranging a non-negative component to an adjacent component, for example. Treatment.

In step S207, for example, if the component selected by the user input stroke data is [Ban] and the component selected by the latest character [洽] is [A] on the [Close] side. etc., it is determined that it can be omitted (YES in step S207). Make a selection of the most recent glyph shape components.

If it is determined in step S207 that the selected component cannot be omitted (NO in step S207), the control unit 21 selects, for example, the [biased] side component selected by the user input stroke data. , is replaced with the same component [Sanzui (三水)] of the latest character [洽] (step S208). Then, Kanji candidates based on the replaced components are stored as corrected stroke data (step S209).

The control unit 21 determines whether or not all the recent constituent elements have been selected, so that there is an unselected recent character constituent element and all the recent constituent elements have not been selected. is confirmed (step S210).

If it is determined in step S210 that all the recent constituent elements have not been selected (NO in step S210), the process returns to step S206 to perform processing corresponding to other constituent elements of recent characters. Run.

In this way, the constituent element [close] side of the stroke data input by the user is also replaced with the constituent element [ai] on the [close] side of the latest character [洽] to obtain corrected stroke data.

If it is determined in step S210 that all recent character components have been selected and there is no unselected recent character component (YES in step S210), the control unit 21 selects the stroke data input by the user. By judging whether or not all constituent elements have been selected, it is confirmed that there are unselected constituent elements and that all constituent elements have not been selected (step S211).

If it is determined in step S211 that all the constituent elements of the user input stroke data have not been selected and there is an unselected constituent element (NO in step S211), the control unit 21 performs the Returning to the process, similar processing is performed for other components of the user-inputted stroke data.

If it is determined in step S211 that all the constituent elements of the user-inputted stroke data have been selected and there is no unselected constituent element (YES in step S211), the control unit 21 selects all the eccentric candidate By judging whether or not the selection of has been completed, it is confirmed that there are unselected biased candidates and that all the candidates have not been selected (step S212).

In step S212, if it is determined that the selection of all the obsessive-type candidates has not been completed (NO in step S212), the control unit 21 returns to the processing from step S203 and selects the unselected obsessive-type candidates. Execute similar processing based on

If it is determined in step S212 that the selection of all the bias type candidates has been completed (YES in step S212), the control unit 21 ends the subroutine relating to the stroke data correction process in FIG. return to the main routine of

As described above, when the eccentric type determined from the handwritten input character image matches the eccentric type of the character selected as having a closer character shape, the eccentric type candidate is limited to one.

On the other hand, if the biased type determined from the handwritten input character image does not match the biased type of the character selected as having a closer character shape, two candidates for the biased type are derived. Step S203 and subsequent steps are repeatedly executed.

In FIG. 11, in response to the character [洽] long-pressed by the user on the candidate character display section 44 of the touch panel display section 17, the user-inputted stroke data is replaced with the constituent elements of the most recent character of the eccentric type. 4 shows an example of corrected stroke data. FIG. 11(A) shows the most recent character shape Kanji candidate [洽] selected for the stroke data input by the user. The corrected stroke data 2 shown in FIG. 11(C) corresponds to [Sanzui], which is the biased Rix1, and [Go], which is the opposite Rix2, is shown in FIG. 11(B). is corrected stroke data 1 shown in . In FIG. 11, the final number of corrected stroke data is [2], and character recognition processing, which will be described later, is performed on them.

In FIG. 3, after stroke data correction processing is performed in step S104, handwriting recognition processing is sequentially performed on a plurality of correction data to derive corrected Chinese character candidates as recognition results for the plurality of correction data (step S105). .

The control unit 21 again displays the list of the derived corrected Chinese character candidates on the touch panel display unit 17 (step S106), and returns to the process from step S103 to wait for the operation on the displayed Chinese character candidates.

FIG. 7(B) shows a state in which the Chinese character [洽] is selected by a long-pressing operation with the stylus pen P in FIG. 7(A). It is a figure which illustrates the displayed state. In FIG. 7B, the center of the corrected kanji candidate display area 45 is the position of the selected kanji [洽], and two kanji candidates [哈] [恰] corresponding to 旁 [合] are listed on the left side 45A. Similarly, a list of two kanji candidates [Yu] [Yu] is displayed on the right side 45B with the kanji [洽] sandwiched therebetween. The two kanji candidates [哈] [恰] on the left side 45A are displayed as candidates derived by performing the handwriting recognition processing in step S105 on the corrected stroke data 1 shown in FIG. 6(C). It is. On the other hand, the two kanji candidates [Yu] [Yu] on the right side 45B are candidates derived by performing the handwriting recognition processing in step S105 on the corrected stroke data 2 shown in FIG. 6D. It is what was done.

In this case, kanji characters with the same eccentric type, such as [哈] and [恰], and [湯] and [纰], are displayed with a frame of the same color to indicate that they are the same eclectic type. You can

In addition, the user can easily understand the result of character recognition by performing a sorted display so as to visually distinguish not only the color but also the type and display position of the frame line for each of the same bias patterns.

When the user of the electronic dictionary 10 finds a desired Chinese character among the displayed Chinese character candidates, the user selects the desired Chinese character by touch operation.

As described above with reference to FIG. 3, the control unit 21 determines whether or not one candidate considered to be the closest has been long-pressed (step S103), whether or not one candidate has been selected (step S107). By repeatedly determining whether or not a cancel operation has been performed (step S109), it waits for any of these inputs.

Therefore, when one character desired by the user is selected by the touch operation, the control unit 21 determines that one candidate has been selected in step S107 (YES in step S107), and confirms the selected Chinese character candidate. , the character string that has already been entered is entered (step S108), and the process of FIG. 3 ends.

FIG. 8A shows a state in which a touch operation is performed on the Chinese character candidate [Yu] on the right side 45B of the corrected Chinese character candidate display section 45 from the display state of FIG. 7A. In response to this touch operation, the control unit 21 determines the Chinese character candidate [Yu] as a character following the character string [Nikko] already input in the search character string input unit 41 .

Therefore, as shown in FIG. 8(B), in the search character string input unit 41, the result of fixing with correction processing from the character string [Nikko Shin] including the erroneously recognized character [Shin], which is the provisional input state Replaces Sunbathing. At the same time, the handwritten character input unit 43 clears the displayed contents in order to prepare for the next handwritten input after confirming the kanji.

In this way, even if the desired kanji character is not recognized by handwriting input, an operation different from the normal touch operation, such as long-pressing another character that is considered to be the closest to the recognition result, is performed. Thus, the stroke data input by the user is decomposed into each radical of Chinese characters to obtain corrected stroke data, and character analysis is newly performed. Therefore, even if a part of the kanji to be handwritten is input in a slightly inaccurate form, it is possible to improve the possibility of obtaining the desired kanji by correcting it, which contributes to the efficiency of handwriting input. .

For example, when selecting a dictionary function such as a Japanese dictionary, the character strings that have already been input before and after the handwritten characters in the search character string that the user enters as part of the entry word are taken into account. By excluding characters that are considered unlikely to be candidates from the candidates, it is possible to avoid list display of a large number of candidates.

Further, on the display screen of the touch panel type display section 17 shown in FIGS. 7(B) and 8(A), the desired kanji characters are still displayed in both of the kanji candidates 45A and 45B of the corrected kanji candidate display section 45. If not, the character whose shape seems to be the closest is selected from among them and a long press operation is performed to repeat the stroke data correction process shown in FIG. 4 .

Furthermore, if the desired kanji characters are not displayed as candidates even after repeatedly selecting kanji characters that are considered to be similar in shape by long-pressing, the handwriting input unit 43 may be used to perform handwriting input again. be done. When such handwriting input is performed again, the accuracy of recognition is improved by performing a selection process that reduces the appearance rate of characters that were previously displayed as candidates but were not selected as desired characters as candidates. can.

[Effects of Embodiment]
As described in detail above, according to the present embodiment, it is possible to effectively utilize handwritten input content and accept selection of a desired character from a wide range of candidates.

In particular, in the present embodiment, stroke data handwritten input by the user is analyzed by referring to the eccentric table stored in the various table storage area 22a1 to see how the constituent elements of each radical can be divided. Based on the results, it was assumed that the correction stroke data was obtained by deriving the candidate for the bias type. By adopting such a processing process, for example, image processing for performing weighting based on learning in character recognition processing, machine learning data, etc. may also be executed. It is possible to reduce the burden of circuit processing in the , and obtain the recognition result more quickly.

Further, although not described in the present embodiment, when the user finally selects a desired character candidate, the selected character and the handwritten input character are each divided according to the eccentric type, The corresponding relationship for each divided part may be updated and stored in the various table storage area 22a1 as learning data. In this case, the various table storage areas 22a1 store information indicating the relationship between the parts obtained by dividing the handwritten characters and the corresponding parts of the characters that are determined, and the control unit 21 newly performs character recognition. It functions as a storage unit that stores information used when performing. If similar handwriting is included in character recognition of handwritten input from the next time onwards, by automatically correcting according to the learned content, the user's handwriting habits are learned the more the user uses it, The recognition rate can be further improved.

In addition, the present invention is not limited to the above-described embodiments, and can be variously modified in the implementation stage without departing from the scope of the invention. Moreover, each embodiment may be implemented in combination as much as possible, and in that case, the combined effect can be obtained. Furthermore, the above-described embodiments include inventions at various stages, and various inventions can be extracted by appropriately combining a plurality of disclosed constituent elements. For example, even if some constituent elements are deleted from all the constituent elements shown in the embodiments, the problems described in the column of problems to be solved by the invention can be solved, and the effects described in the column of effects of the invention is obtained, the configuration from which this constituent element is deleted can be extracted as an invention.

The invention described in the original claims of the present application is appended below.
[Claim 1]
an input unit that receives a character image based on a handwritten input operation;
a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image;
a display control unit for displaying the first character derived by the character derivation unit as a candidate for a character desired by a user;
with
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A character recognition device characterized by:
[Claim 2]
The character derivation unit further derives the second character by using a relationship with the character image received by the input unit.
2. The character recognition device according to claim 1, wherein:
[Claim 3]
The character derivation unit derives the second character according to a predetermined relationship with the corresponding part of the first character for each part divided according to the density of the character image,
3. The character recognition device according to claim 1 or 2.
[Claim 4]
The character derivation unit derives a plurality of the second characters having a predetermined relationship with the first character, corresponding to the parts divided according to the density of the character image,
The display control unit displays the plurality of derived second characters by dividing them corresponding to the parts divided according to the coarseness and fineness of the character image.
4. The character recognition device according to any one of claims 1 to 3, characterized in that:
[Claim 5]
The character derivation unit, when the character image received by the input unit is input following an already input character string, extracts the second character according to the relationship with the already input character string. to derive
5. The character recognition device according to any one of claims 1 to 4, characterized in that:
[Claim 6]
The input unit is capable of accepting a confirmation operation for the second character displayed as an additional candidate,
The character derivation unit derives the second character from information indicating the relationship between the part divided according to the density of the character image and the corresponding part of the second character for which the confirmation operation is received. Further comprising a storage unit for storing information used when
6. The character recognition device according to any one of claims 1 to 5, characterized in that:
[Claim 7]
an input unit that receives a character image based on an input operation in a handwritten format; a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image; A character recognition method in a device comprising: a display control unit that displays the first character derived by the character derivation unit as a candidate for a character desired by a user,
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A character recognition method characterized by:
[Claim 8]
an input unit that receives a character image based on an input operation in a handwritten format; a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image; and a display control unit for displaying the first character derived by the character derivation unit as a candidate for a character desired by a user.
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A program characterized by causing it to function as

DESCRIPTION OF SYMBOLS 10... Electronic dictionary 11... Main body case 12... Lid case 13... Hinge part 14... Key input part 14a... [Home] key 14b... Function designation key 14c... Character input key 14d... [Enter] key 14e... [Return] key 14f --- [BOX] key 14g --- Cursor movement key 14h --- [Shift] key 15 --- Voice output unit 16 --- Voice input unit 17 --- Touch panel type display unit 21 --- Control unit (CPU)
22 Storage section 22a Search processing program storage area 22a1 Table storage area 22b Dictionary data storage area 22c Search history storage area 22d Work data storage area 23 External recording medium 24 Recording medium reading section 25 Communication section 41 Search character string input unit 42 Candidate display unit 43 Handwritten character input unit 44 Candidate character display unit 45 Corrected Kanji candidate display unit 45A, 45B Kanji candidate P Stylus pen

Claims (8)

an input unit that receives a character image based on a handwritten input operation;
a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image;
a display control unit for displaying the first character derived by the character derivation unit as a candidate for a character desired by a user;
with
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A character recognition device characterized by: The character derivation unit further derives the second character by using a relationship with the character image received by the input unit.
2. The character recognition device according to claim 1, wherein: The character derivation unit derives the second character according to a predetermined relationship with the corresponding part of the first character for each part divided according to the density of the character image,
3. The character recognition device according to claim 1 or 2. The character derivation unit derives a plurality of the second characters having a predetermined relationship with the first character, corresponding to the parts divided according to the density of the character image,
The display control unit displays the plurality of derived second characters by dividing them corresponding to the parts divided according to the coarseness and fineness of the character image.
4. The character recognition device according to any one of claims 1 to 3, characterized in that: The character derivation unit, when the character image received by the input unit is input following an already input character string, extracts the second character according to the relationship with the already input character string. to derive
5. The character recognition device according to any one of claims 1 to 4, characterized in that: The input unit is capable of accepting a confirmation operation for the second character displayed as an additional candidate,
The character derivation unit derives the second character from information indicating the relationship between the part divided according to the density of the character image and the corresponding part of the second character for which the confirmation operation is received. Further comprising a storage unit for storing information used when
6. The character recognition device according to any one of claims 1 to 5, characterized in that: an input unit that receives a character image based on an input operation in a handwritten format; a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image; A character recognition method in a device comprising: a display control unit that displays the first character derived by the character derivation unit as a candidate for a character desired by a user,
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A character recognition method characterized by: an input unit that receives a character image based on an input operation in a handwritten format; a character derivation unit that performs recognition processing on the character image received by the input unit and derives a first character from the character image; and a display control unit for displaying the first character derived by the character derivation unit as a candidate for a character desired by a user.
The input unit is capable of accepting a designation operation indicating that the first character is not the character desired by the user but is similar to the character desired by the user,
The character derivation unit further derives a second character having a predetermined relationship with the first character when the input unit receives the designation operation,
The display control unit displays the second character derived by the character derivation unit as an additional candidate for the character desired by the user.
A program characterized by causing it to function as

Images