JP7670524B2 - Character recognition device, character recognition method and program - Google Patents

Description

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

A technology has been proposed that, for a series of handwritten input characters that have been recognized, displays candidate characters for each character to be corrected, allowing easy correction to the desired candidate character without the need for selection. (For example, Patent Document 1)

JP 2008-299431 A

Including the technology described in the patent literature, if the desired character is not among the multiple characters that are candidates for correction, it is necessary to perform character recognition processing again using handwritten characters.

The present invention has been made in consideration of the above-described circumstances, and an object of the present invention is to provide a character recognition device, a character recognition method, and a program that are capable of effectively utilizing the character image of handwritten input characters to derive candidates similar to characters recognized from handwritten input, and allowing a user to select a desired character from the derived character candidates.

According to one aspect of the present invention, there is provided an input unit that accepts a character image of a first character input by handwriting; a character derivation unit that performs a recognition process on the character image accepted by the input unit and derives character candidates in an order of evaluation of high similarity to the character image ; and a display control unit that displays the character candidates derived by the character derivation unit as candidates for a character desired by a user, wherein the input unit is capable of accepting a designation operation for designating the derivation of a character desired by the user from the character candidates displayed by the display control unit , and when the input unit accepts the designation operation, the character derivation unit obtains corrected stroke data of the stroke data of the character image of the first character from a character shape of a candidate selected as having the highest similarity to stroke data of the character image accepted by the input unit, and performs a recognition process on the character image based on the corrected stroke data to derive a second character, and 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.

According to the present invention, it is possible to effectively utilize the character image of handwritten input characters to derive candidates similar to characters recognized from handwritten input, and to accept the selection of a desired character from the derived character candidates .

1 is a diagram showing the external configuration of an electronic dictionary according to an embodiment of the present invention; FIG. 2 is a block diagram showing the functional configuration of an electronic circuit of the electronic dictionary according to the embodiment. 10 is a flowchart showing processing for handwritten input characters according to the embodiment. 4 is a flowchart of a subroutine showing detailed processing contents of the stroke data correction processing of FIG. 3 according to the embodiment; 6A and 6B are diagrams illustrating examples of screens showing handwritten character input and its recognition result according to the embodiment. 6A to 6C are diagrams showing a process of deriving a plurality of correction stroke data according to the embodiment; 4A to 4C are diagrams showing screen transitions of the touch panel display unit according to the embodiment. 4A to 4C are diagrams showing screen transitions of the touch panel display unit according to the embodiment. 13A and 13B are diagrams illustrating examples of some of the biased tables stored in the various table storage areas according to the embodiment. 11A to 11C are views for explaining a process of deriving radical-based kanji candidates from stroke data input by a user according to the embodiment; 11A and 11B are diagrams showing an example in which stroke data input by a user is replaced with recent components of a character shape according to the embodiment;

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

The electronic dictionary 10 is configured with a foldable case in which the main body case 11 and the cover case 12 can be opened/closed via a hinge section 13. On the surface of the main body case 11 when the foldable case is opened, there are provided a key input section 14 (hardware keys) including a [Home] key 14a, function designation keys 14b, character input keys 14c, [Decision] key 14d, [Back] key 14e, [BOX] key 14f, cursor movement keys 14g, and a [Shift] key 14h, an audio output section (including a speaker) 15, and an audio input section (including a microphone) 16, etc.

A touch panel display unit 17 is also provided on the surface of the cover case 12. The touch panel display unit 17 is an integrated structure of a display device and a touch position detection device that detects the position touched by the user of the electronic dictionary 10 with a pen or finger, and is constructed by laminating a transparent touch panel onto a backlit LCD screen. In other words, the touch panel display unit 17 functions as an input unit that accepts character images based on input operations in handwritten format.

The [Home] key 14a of the key input unit 14 is a key for displaying a home screen on the key input unit 14. Although not specifically shown, multiple icons are displayed that are registered according to the initial settings of the electronic dictionary 10 or user operations. 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 launches a function (application) that uses dictionary content or learning content, and a group icon that displays a list screen of icons of multiple functions belonging to one category.

The function specification keys 14b of the key input section 14 are keys for directly specifying dictionary content and the like indicated on each key. The function specification keys 14b include a [Multiple Dictionaries] key that does not specify a category of dictionary content, keys for specifying the same category ([Japanese] key, [Archaeological] key, [Chinese-Japanese] key, [English-English-Japanese] key, etc.), a [Content List] key that displays a list of dictionary content, and a [Study Notebook] key, which is a category of tools.

In addition, when a key on the key input unit 14 is operated after the [Shift] key 14h is operated, the key functions as a key with a frame on the key top, rather than as a key without a frame. For example, when the [Delete] key is operated after the [Shift] key 14h is operated, the key functions as a [Setting] key, not a [Delete] key.

In FIG. 1, [Japanese Dictionary] is selected, and the search string input section 41 located at the top of the touch panel display section 17 shows the state in which the kana input tag (aiu) and the alphabet input tag (ABC) are selected.

The character string [Nikko] has already been entered in the search character string input section 41. The candidate display section 42 below the search character string input section 41 shows a list of, for example, three entry words that correspond to the character string [Nikko]. Furthermore, below the candidate display section 42, a handwritten character input section 43 for two characters is displayed, which shows a blank state waiting for the handwritten input of the character following the character string [Nikko].

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 unit (CPU: Central Processing Unit) 21, which is a computer. The control unit 21 controls the operation of each part of the circuit in accordance with a control program prestored in a storage unit 22 such as a flash ROM. The number of processors such as a CPU may be one or two or more.

In addition, at least one of the control program and the dictionary data described later may be read by the recording medium reading unit 24 from an external recording medium 23 such as a memory card and stored in the memory unit 22, or may be downloaded via the communication unit 25 from a web server or the like on an external network (not shown) and stored in the memory unit 22.

The control unit 21 is connected to the memory unit 22, recording medium reading unit 24, and communication unit 25 via a data bus and a control bus, as well as to the key input unit 14, audio output unit 15, audio input unit 16, and touch panel display unit 17.

The memory unit 22 stores a system program that controls the overall operation of the electronic dictionary 10, a communication program for connecting to external devices via the communication unit 25, and other memory areas for storing programs and data for executing various functions by the electronic dictionary 10, such as a search processing program memory area 22a, a dictionary data memory area 22b, a search history memory area 22c, and a working data memory area 22d.

The search processing program memory area 22a is an area for storing a control program for searching and displaying a user-requested headword and its corresponding translation, meaning, usage example, explanation, and other explanatory information based on various dictionary contents (English-English-Japanese dictionary/English-Japanese dictionary/Japanese-English dictionary/English-English dictionary/Japanese dictionary/encyclopedia/...) stored as dictionary data in the dictionary data memory area 22b, as well as various table memory areas 22a1 used when performing searches in response to input other than character input of the headword.

The various table storage area 22a1 stores multiple tables, including a radical-component table that predefines how the constituent radicals can be divided for each piece of kanji character data.

When a search is performed in response to a user operation and a heading word and its explanatory information are displayed as search results, the search history storage area 22c stores the heading word that was the subject of the search as search history together with information on the number of times it was searched.

In the working data memory area 22d, various data input in response to user operations and data acquired or generated by the control unit 21 are temporarily stored (held) as necessary in accordance with the control of the operation of each part of the circuit according to the control program by the control unit 21.

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

[Action]
Next, the operation of this embodiment will be described.
In this embodiment, a correction process will be described in the case where the recognition result of the handwritten input character image when the Japanese dictionary function is selected is not the kanji desired by the user.

Here, we will explain a case where, for example, the character image of the character string [sunlight] is input by handwriting as a search string and is recognized as desired, and then the character image of the character [bath] is similarly input by handwriting, but the desired character [bath] is not found among the character candidates in the recognition result of the input character image.

Figure 5 (A) shows the screen when the user of the electronic dictionary 10 further inputs the character image of the character [bath] by handwriting using the stylus pen P in the handwritten character input section 43, from the display state of the touch panel display section 17 shown in Figure 1.

As shown in the figure, the handwritten character input unit 43 has an input area for two characters. After handwritten input is performed on the left side, for example, the stylus pen P is used on the right side to instruct the execution of recognition processing for the input characters.

In response to an instruction to execute a recognition process using the stylus pen P, the control unit 21 executes a character recognition process and displays a list of the character candidates that are the recognition results in the order of how highly similar they are evaluated to be. That is, the control unit 21 executes a recognition process on the character image received by the input unit, and functions as a character derivation unit that derives a first character from the character image, and as a display control unit that displays the first character derived by the character derivation unit as a candidate for the character desired by the user.

Figure 5 (B) shows a list of kanji candidates that have been evaluated as having a high degree of similarity in the candidate character display section 44. Since the desired kanji character [bath] is not included in the candidate character display section 44, the user needs to perform an operation to correct the handwritten input character.

Figure 3 is a flowchart showing the processing performed by the control unit 21 for handwritten input characters.

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

With the kanji candidates displayed as a list, the control unit 21 repeatedly determines whether a candidate that appears to be the closest has been pressed and held (step S103), whether a candidate has been selected (step S107), and whether a cancel operation has been performed on the list display (step S109), while waiting for any of these inputs to be made.

If it is determined in step S107 that a cancel operation has been performed on the list display (YES in step S109), the control unit 21 ends the processing in FIG. 3.

Figure 7 (A) shows the screen of the touch panel display unit 17 shown in Figure 5 (B) in which the user is pressing and holding the kanji candidate [洽] in the handwritten character input section 43 with the stylus pen P.

If it is determined in step S103 that a long press operation has been performed on one candidate, the control unit 21 executes a stroke data correction process to derive multiple pieces of corrected stroke data from the original handwritten input stroke data and the character shape of the kanji character of the candidate selected as having the highest similarity (step S104).

Figure 6 is a diagram illustrating the process of deriving multiple pieces of correction stroke data. Based on the stroke data of the handwritten input character shown in Figure 6 (A) and the shape of the character [洽] selected by the user as being the closest as shown in Figure 6 (B), the control unit 21 derives correction stroke data 1 shown in Figure 6 (C) and correction stroke data 2 shown in Figure 6 (D).

Figure 4 is a flowchart of a subroutine showing the details of the stroke data correction process executed by the control unit 21 in step S104. First, the stroke data input by the user is scanned, and character shape analysis data including outline, white space information, and crowding information is derived (step S201).

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

Figure 9 is a diagram showing an example of a part of the radical-component type table stored in the various table storage area 22a1. As shown in the figure, the radical configuration of kanji can be classified into those consisting of radicals and components as shown in Figure 9(A), those consisting of crowns and feet as shown in Figure 9(B), those including 繞 (nyou) as shown in Figure 9(C), those including 垂 (tare) as shown in Figure 9(D), those including other structures as shown in Figure 9(E), and those that cannot be divided into other radicals as shown in Figure 9(F).

Figure 10 is a diagram explaining the process of deriving radical-type kanji candidates from stroke data input by the user. As shown in Figure 10 (A), the stroke data input by the user shown in Figures 5 (A) and 6 (A) is sequentially scanned in one direction, vertically and horizontally.

Figure 10 (B) shows the results of deriving the outline frame OF, white space information SI, and density information CI of the stroke data based on the density of the character image from the scanned results. From these derived results, as shown in Figure 10 (C), it is recognized as consisting of two radicals, radical Rix1 and side radical Rix2, shown in Figure 9 (A), and taking into account the kanji candidate that was pressed and held, a side radical candidate with a high degree of similarity is derived.

In Fig. 10C, the stroke data input by the user is recognized as being composed of the radical and radicals shown in Fig. 9A, while in Fig. 7A, the user uses the stylus pen P to input the kanji candidate [洽] in the handwritten character input unit 43, which is also composed of the radical and radicals shown in Fig. 9A. In this way, when the radical type determined from the handwritten input character image matches the radical type of the character selected as being more similar in character shape, the radical type candidates are limited to one. On the other hand, when the radical type determined from the handwritten input character image does not match the radical type of the character selected as being more similar in character shape, each of them is derived as a radical type candidate. That is, the control unit 21 derives two radical type candidates. The control unit 21 selects one of the derived radical type candidates that has not been selected (step S203). When the control unit 21 selects one of the unselected candidates, for example the radical and side character shown in FIG. 9A, it derives the number of components of the stroke data for the selected radical and side character candidate, for example [2] from [radical] and [side character] (step S204).

Next, the control unit 21 selects one of the components of the user input, for example, [radical] ( step S205). The control unit 21 selects one of the components of [洽], for example, [三水], from the most recent character selected by the user (the character selected by determining that it is closest to the stroke data of the handwritten input character shown in FIG. 6(A) and the user selected character shown in FIG. 6(B)) for the selected component [radical] (step S206).

The control unit 21 further judges whether it is possible to omit processing such as replacement, which will be described later, for the selected component, for example [sanzui (three water)] (step S207). This is a measure to reduce processing steps such as replacing unnecessary user-input stroke data with each component of the nearest character by imposing a constraint, for example, that a radical component cannot be placed in a side component.

In step S207, for example, if the component selected in the stroke data input by the user is [Ren] and the component selected in the most recent character [Kaku] is [Go] on the [Han] side, it is determined that processing such as replacement can be omitted (YES in step S207), and the control unit 21 omits processing such as replacement for the component selected at that time, and returns to the processing from step S206 to select a component of the shape of the next most recent character .

If it is determined in step S207 that the selected component cannot be omitted (NO in step S207), the control unit 21 replaces, for example, the component on the [Ren] side selected in the stroke data input by the user with the same component [Sanzui (three water)] of the most recent character [洽] (step S208). Then, the control unit 21 saves a kanji candidate based on the replaced component as corrected stroke data (step S209).

The control unit 21 determines whether or not the selection of all the most recent character components has been completed, thereby confirming that there are unselected most recent character components and that the selection of all the most recent character components has not yet been completed (step S210).

In step S210, if it is determined that the selection of all the components of the nearest character has not been completed (NO in step S210), the process returns to step S206 and executes processes corresponding to other components of the nearest character .

In this way, the process is also performed for the [side character] component of the stroke data entered by the user, replacing it with the [side character] component [combined] of the most recent character [洽] to create corrected stroke data.

In step S210, if it is determined that selection of all recent character components has been completed and there are no unselected recent character components (YES in step S210), the control unit 21 determines whether selection of all components of the stroke data input by the user has been completed, thereby confirming that there are unselected components and that selection of all components has not yet been completed (step S211).

If it is determined in step S211 that selection of all components of the user-input stroke data has not been completed and that there are unselected components (NO in step S211), the control unit 21 returns to the process from step S205 and performs similar processing on the other components of the user-input stroke data.

In addition, in step S211, if it is determined that the selection of all components of the stroke data input by the user has been completed and there are no unselected components (YES in step S211), the control unit 21 checks whether the selection of all the side-type candidates has been completed, thereby confirming that there are unselected side-type candidates and that the selection of all the candidates has not been completed (step S212).

If it is determined in step S212 that selection of all side-group candidates has not been completed (NO in step S212), the control unit 21 returns to the process from step S203 and executes the same process based on the side-group candidates that have not been selected.

Also, in step S212, if it is determined that the selection of all bias type candidates has been completed (YES in step S212), the control unit 21 ends the subroutine related to the stroke data correction process in FIG. 4 and returns to the main routine in FIG. 3.

As mentioned above, if the radical type determined from the handwritten input character image matches the radical type of the character selected as having a closer character shape, the radical type candidates are limited to one.

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

11 shows an example of corrected stroke data in which stroke data input by a user is replaced with the components of a radical-type recent character corresponding to the character [洽] that is long-pressed by the user on the candidate character display section 44 of the touch panel display section 17. FIG. 11(A) shows the kanji candidate [洽] with the shape of the most recent character selected from the stroke data input by the user. The data corresponding to the radical Rix1 [三水 (sanzui)] is the corrected stroke data 2 shown in FIG. 11(C), and similarly the data corresponding to the radical Rix2 [合] is the corrected stroke data 1 shown in FIG. 11(B). In FIG. 11, the final number of corrected stroke data is [2], and character recognition processing is performed on these data, which will be described later.

In FIG. 3, after performing stroke data correction processing in step S104, handwriting recognition processing is sequentially performed on multiple pieces of corrected data to derive corrected kanji candidates as recognition results for the multiple pieces of corrected data (step S105).

The control unit 21 displays the derived correction kanji candidates again in a list on the touch panel display unit 17 (step S106), and then returns to the process from step S103 to wait for an operation on the displayed kanji candidates.

Figure 7 (B) is a diagram illustrating a state in which the kanji character [洽] is selected by long pressing the stylus pen P in Figure 7 (A), and kanji candidates are displayed by referring to the stroke data input by handwriting through the above-mentioned series of processes. In Figure 7 (B), the center of the corrected kanji candidate display section 45 is the position of the selected kanji character [洽], and two kanji candidates [哈] and [恰] corresponding to the side character [合] are displayed in a list on the left side 45A, and two kanji candidates [湯] and [行] are similarly displayed in a list on the right side 45B, sandwiched between the kanji character [洽]. The two kanji candidates [哈] and [恰] on the left side 45A are displayed as candidates derived by executing the handwriting recognition process in step S105 on the corrected stroke data 1 shown in Figure 6 (C). On the other hand, the two kanji candidates on the right side 45B, [Bath] and [Align], are displayed as candidates derived by performing the handwriting recognition process in step S105 on the corrected stroke data 2 shown in FIG. 6(D).

In this case, kanji characters with the same radical type, for example [哈] and [恰], [湯] and [行], may be displayed in frames of the same color to indicate that they have the same radical type.

In addition to colors, the type of border and display position can be used to visually distinguish between characters with the same radical type, allowing users to easily understand the results of character recognition.

When a user of the electronic dictionary 10 finds a desired kanji among the kanji candidates displayed in the list, the user selects the desired kanji by a touch operation.

As described above in FIG. 3, the control unit 21 waits for any of the following inputs by repeatedly determining whether or not a long press has been performed on one of the candidates that appears to be the closest (step S103), whether or not a candidate has been selected (step S107), and whether or not a cancel operation has been performed on the list display (step S109).

Therefore, when a single character desired by the user is selected by a touch operation, the control unit 21 determines in step S107 that one candidate has been selected (YES in step S107), confirms the selected kanji candidate, and inputs it following the character string that has already been input (step S108), thus completing the processing in FIG. 3.

Fig. 8 (A) shows a state in which the kanji candidate [bath] on the right side 45B of the corrected kanji candidate display section 45 is touched from the display state of Fig. 7 (A). In response to this touch operation, the control section 21 confirms the kanji candidate [bath] as the character following the character string [sunlight] already input in the search character string input section 41.

Therefore, as shown in FIG. 8(B), in the search string input section 41, the character string [nikkoshin], which includes the erroneously recognized character [shin], which is in a provisional input state, is changed to the confirmed result [nikkoyu] after correction processing. At the same time, in the handwritten character input section 43, the display content is cleared in preparation for the next handwritten input after the kanji has been confirmed.

In this way, even if the desired kanji is not recognized through handwritten input, an operation other than a normal touch operation, such as long pressing another character that is thought to be closest to the recognition result, can be performed to break down the stroke data entered by the kanji radical, obtain corrected stroke data, and perform new character analysis. Therefore, even if part of the kanji to be handwritten input is input somewhat inaccurately, it is possible to correct it and improve the possibility of obtaining the desired kanji, which contributes to the efficiency of handwritten input.

For example, when selecting a dictionary function such as a Japanese dictionary, the system takes into account the characters already entered before and after the handwritten characters in the search string that the user enters as part of the headword, and excludes characters that are deemed unlikely to be candidates from the list of candidates, thereby avoiding the display of an unnecessarily large number of candidates.

In addition, on the display screen of the touch panel display unit 17 shown in Figures 7 (B) and 8 (A), if the desired kanji is still not displayed in either of the kanji candidates 45A, 45B in the correction kanji candidate display section 45, the character that is thought to be closest in shape is again selected from among them and pressed and held down, thereby repeatedly executing the stroke data correction process shown in Figure 4.

Furthermore, if the desired kanji is not displayed as a candidate even after repeatedly selecting kanji that appear to be similar in shape by using a long press operation, it is possible to perform handwritten input again using the handwritten character input unit 43. When performing such handwritten input again, a selection process is performed that reduces the appearance rate as candidates of characters that were previously displayed as candidates but were not selected as the desired character, thereby improving the accuracy of recognition.

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

In particular, in this embodiment, stroke data handwritten by the user is analyzed by referring to the radical type table stored in the various table storage area 22a1 to analyze how the components of each radical can be divided, and corrected stroke data is obtained by deriving radical type candidates based on the results. By adopting such a processing process, other image processing such as weighting based on learning in character recognition processing or machine learning data may also be performed, but in any case, the burden on the circuit processing in the control unit 21 can be reduced and recognition results can be obtained more quickly.

Although not described in this embodiment, when the user finally selects a desired character candidate, the selected character and the handwritten input character may each be divided according to the radical type, and the correspondence between each divided portion may be updated and stored as learning data in the various table storage area 22a1. In this case, the various table storage area 22a1 functions as a storage unit that stores information indicating the relationship between the divided portions of the handwritten input character and the corresponding portions of the finalized character, and stores the information as information to be used when the control unit 21 performs new character recognition. If a similar handwriting is included during character recognition of the handwritten input from the next time onwards, automatic correction is performed according to the learned content, and the user's handwriting habits are learned the more it is used, thereby further improving the recognition rate.

In addition, the present invention is not limited to the above-mentioned embodiment, and various modifications can be made in the implementation stage without departing from the gist of the invention. Furthermore, the embodiments may be implemented in combination as appropriate as possible, in which case the combined effects can be obtained. Furthermore, the above-mentioned embodiment includes inventions at various stages, and various inventions can be extracted by appropriate combinations of the multiple constituent elements disclosed. For example, even if some constituent elements are deleted from all the constituent elements shown in the embodiment, if the problem stated in the "Problem to be Solved by the Invention" column can be solved and the effect stated in the "Effect of the Invention" column can be obtained, the configuration from which the constituent elements are deleted can be extracted as the invention.

The invention as originally claimed in the present application is set forth below.
[Claim 1]
an input unit that accepts character images based on an input operation in handwriting format;
a character deriving unit that executes a recognition process on the character image received by the input unit and derives a first character from the character image;
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;
Equipped with
the input unit is capable of accepting a designation operation indicating that the first character is not a character desired by the user but is similar to the character desired by the user;
the character deriving unit further derives a second character having a predetermined correlation with the first character when the specifying operation is received by the input unit;
The display control unit displays the second character derived by the character derivation unit as an additional candidate for a character desired by the user.
A character recognition device comprising:
[Claim 2]
The character deriving unit further derives the second character by using a correlation with the character image received by the input unit.
2. The character recognition apparatus according to claim 1.
[Claim 3]
the character derivation unit derives the second character for each portion divided according to density of the character image in accordance with a predetermined correlation with a corresponding portion of the first character;
3. The character recognition device according to claim 1.
[Claim 4]
the character derivation unit derives a plurality of second characters having a predetermined correlation with the first character in correspondence with portions divided according to density of the character image;
The display control unit displays the derived second characters in a divided manner corresponding to the portions divided according to the density of the character image.
4. The character recognition device according to claim 1, wherein the character recognition device further comprises:
[Claim 5]
the character derivation unit, when a character image received by the input unit is input following a previously input character string, derives the second character in accordance with a relevance to the previously input character string.
5. The character recognition device according to claim 1, wherein the character recognition device further comprises a first input unit.
[Claim 6]
the input unit is capable of accepting a confirmation operation for the second character displayed as an additional candidate,
a storage unit configured to store information indicating a relationship between a portion divided according to density of the character image and a corresponding portion of the second character for which the confirmation operation has been received, as information used by the character derivation unit when deriving the second character,
6. The character recognition device according to claim 1, wherein the character recognition device further comprises:
[Claim 7]
A character recognition method for a device including an input unit that accepts a character image based on an input operation in a handwritten format, a character derivation unit that executes a recognition process on the character image accepted by the input unit and derives a first character from the character image, and 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 a character desired by the user but is similar to the character desired by the user;
the character deriving unit further derives a second character having a predetermined correlation with the first character when the specifying operation is received by the input unit;
The display control unit displays the second character derived by the character derivation unit as an additional candidate for a character desired by the user.
A character recognition method comprising:
[Claim 8]
A program executed by a computer having a device including: an input unit that accepts a character image based on an input operation in a handwritten format; a character derivation unit that executes a recognition process on the character image accepted by the input unit and derives a first character from the character image; and 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 program being executed by the computer:
the input unit is capable of accepting a designation operation indicating that the first character is not a character desired by the user but is similar to the character desired by the user;
the character deriving unit further derives a second character having a predetermined correlation with the first character when the specifying operation is accepted by the input unit;
The display control unit displays the second character derived by the character derivation unit as an additional candidate for a character desired by the user.
The program is characterized by causing the program to function as follows.

10... Electronic dictionary 11... Main body case 12... Lid case 13... Hinge section 14... Key input section 14a... [Home] key 14b... Function designation key 14c... Character input key 14d... [Decision] key 14e... [Back] key 14f... [BOX] key 14g... Cursor movement key 14h... [Shift] key 15... Audio output section 16... Audio input section 17... Touch panel display section 21... Control section (CPU)
22...Memory unit 22a...Search processing program memory area 22a1...Various table memory area 22b...Dictionary data memory area 22c...Search history memory area 22d...Work data memory area 23...External recording medium 24...Recording medium reading unit 25...Communication unit 41...Search 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 (6)

an input unit that accepts a character image of a first character input by handwriting;
a character derivation unit that executes a recognition process on the character image received by the input unit and derives character candidates in the order of the degree of similarity evaluated to the character image ;
a display control unit that displays the character candidates derived by the character derivation unit as character candidates desired by a user;
Equipped with
The input unit is capable of receiving a designation operation for designating derivation of a character desired by the user from character candidates displayed by the display control unit ,
the character derivation unit, when receiving the designation operation by the input unit, acquires corrected stroke data of the stroke data of the character image of the first character from a character shape of a candidate selected as a candidate having the highest similarity to the stroke data of the character image received by the input unit, and derives a second character by performing a recognition process on the character image based on the corrected stroke data;
The display control unit displays the second character derived by the character derivation unit as an additional candidate for a character desired by the user.
A character recognition device comprising: the character image of the first character is an image of a first Chinese character having a radical composition;
2. The character recognition device according to claim 1, wherein, when the designation operation is accepted by the input unit , the character derivation unit determines a radical type of the first Chinese character to be recognized from the image of the first Chinese character depending on density, and acquires stroke data of a character image corresponding to a radical of the determined radical type as corrected stroke data of the stroke data of the image of the first Chinese character. the display control unit displays the derived second Chinese characters, which are the plurality of second characters, in a manner corresponding to the determined radicals;
3. The character recognition apparatus according to claim 2. The character recognition device according to any one of claims 1 to 3, characterized in that, when the first character accepted by the input unit is one of a string of characters consisting of a plurality of characters, the character derivation unit excludes, from the plurality of second characters to be added as candidates, a second character that is considered unlikely to be a candidate included in the string, based on a relationship with other characters in the string other than the first character. A character recognition method for a device including an input unit and a display unit that accepts a character image of a first character input by handwriting, a character derivation unit that executes a recognition process on the character image accepted by the input unit and derives character candidates in an order of evaluation of high similarity to the character image , and a display unit that displays the character candidates derived by the character derivation unit as character candidates desired by a user,
receiving, by the input unit, a designation operation for designating derivation of a character desired by the user from character candidates displayed on the display unit;
acquiring corrected stroke data of the stroke data of the character image of the first character from a character shape of a candidate selected as a candidate having the highest similarity to the stroke data of the character image accepted by the input unit when the input unit accepts the specifying operation, and executing a recognition process on the character image based on the corrected stroke data to derive a second character;
displaying the derived second character on the display unit as an additional candidate for a character desired by the user;
A character recognition method comprising: A computer includes an input unit and a display unit that accepts a character image of a first character input by handwriting, a character derivation unit that executes a recognition process on the character image accepted by the input unit, and derives character candidates in an order of evaluation of high similarity to the character image , and a device that displays the character candidates derived by the character derivation unit as character candidates desired by a user on the display unit,
receiving, via the input unit, a designation operation for designating derivation of a character desired by the user from character candidates displayed on the display unit;
acquiring corrected stroke data of the stroke data of the character image of the first character from a character shape of a candidate selected as a candidate having the highest similarity to the stroke data of the character image accepted by the input unit when the input unit accepts the specifying operation, and executing a recognition process on the character image based on the corrected stroke data to derive a second character;
displaying the derived second character on the display unit as an additional candidate for a character desired by the user;
A program to achieve this.