JP2015043145A - Handwritten character input device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a handwritten character input device such that a document in which a plurality of languages are mixed can be smoothly input without requiring any complicated operation.SOLUTION: A handwritten character input device 20 includes: a contact operation input unit 21; an image display unit 22; a template image display control unit 51 which makes the image display unit 22 display a character input area; an area sectioning unit 34 which sections the character input area into plural areas; a dictionary data storage unit 41 which stores dictionary data 41a, 41b of different languages while associating the dictionary data to the respective areas; a trace information generation unit 35 which generates trace information on a handwritten character; a character position specifying unit 36 which specifies a determination reference position for the handwritten character on the basis of the trace information; an area determination unit 37 which determines the area that the determination reference position belongs to; a character recognition processing unit 38 which performs a character recognizing process using the dictionary data associated with the area so as to extract a recognition candidate; and a recognition candidate display control unit 53 which makes the image display unit display the extracted recognition candidate.

Description

  The present invention relates to a handwritten character input device for inputting characters by handwriting.

  In recent years, electronic devices equipped with a touch interface, such as smartphones and tablet PCs (Personal Computers), have been widely used. The touch interface is a user interface that can be operated by touching a display using a touch panel and a GUI (Graphical User Interface) for input and output, and using a finger or a stylus as a pointing device. The touch interface has an advantage that it can be operated intuitively by pointing an operation target displayed on a screen such as icons and buttons.

  Such electronic devices are equipped with a character input application for inputting characters when using applications such as Notepad, Mail, and Web Browser. The character input application uses a software keyboard to input characters. That can switch between an input mode for inputting characters and an input mode for inputting characters by handwriting have become widespread. Hereinafter, an apparatus configured to be able to input characters by handwriting will be referred to as a handwritten character input apparatus.

  Conventionally, some handwritten character input devices are compatible with a plurality of languages. Such an apparatus recognizes characters input by handwriting by holding dictionary data for each supported language. For example, when a Japanese sentence is input, characters input by handwriting are collated with dictionary data of kana and kanji, and those having similar shapes are extracted as recognition candidates. On the other hand, when English sentences are input, dictionary data including English words is used.

  As described above, in a handwritten character input device that supports a plurality of languages, if one input is checked against dictionary data of all languages, it takes a lot of processing time to output recognition candidates. End up. In this case, many recognition candidates unnecessary for the user are output, and it is difficult to accurately extract the recognition candidates in the language that the user wants to input.

  Therefore, for example, Patent Document 1 proposes a conventional technique for solving such a problem. According to Patent Document 1, it is possible to switch between a Japanese mode in which an input frame for Japanese input is displayed and an English mode in which an input frame for English input is displayed by operating a button. By performing character recognition processing according to the language mode, it is possible to smoothly input and create a sentence in which a plurality of languages are mixed, and to realize high recognition performance.

  Further, in Patent Document 1, when the time set in the English mode reaches a predetermined time, the mode is automatically switched from the English mode to the Japanese mode, and the input frame for Japanese input and the English input mode are switched. It has also been proposed to display an input frame in the same input area and perform character recognition processing in accordance with the input frame in which handwritten characters are input.

Japanese Patent Laid-Open No. 11-15918

  However, when inputting a sentence in which a plurality of languages are mixed using the method of Patent Document 1, there are the following problems. In the method of switching the language mode by operating the button, an operation for switching the language mode is required during the input of the sentence, and the user is forced to perform a troublesome operation. Further, in the method of automatically switching the language mode when the predetermined time is reached, there is a possibility that the language mode is switched at a timing not intended by the user.

  In addition, in the case of a method of providing an input frame for each language, for example, in a device with a small screen size such as a smartphone, if an attempt is made to secure a size that allows text input without problems for each input frame, the input frame group However, if the size of the input frame is too large, and if the layout is limited, it will not be possible to ensure that each input frame is large enough to allow text input without problems. There is a problem of end. Furthermore, by providing an input frame for each language separately, the input frame must be changed according to the language to be input, and there is a problem that smooth input of text is hindered.

  The object of the present invention is to enable a text input mixed with a plurality of languages to be smoothly input without requiring a complicated operation, and to have a sufficient size to allow a character input area to be input without any problems. It is providing the handwritten character input device which can ensure.

The present invention includes an operation surface that receives a contact operation by an operator, and outputs an operation position information indicating an operation position on the operation surface on which the operator performs a contact operation.
An image display unit for displaying an image on the operation surface of the contact operation input unit;
A template image display control unit that causes the image display unit to display a template image including a character input region instruction image indicating a character input region in which the operator inputs a handwritten character by a contact operation;
An area dividing section for dividing the character input area into a plurality of areas;
Dictionary data storage unit for storing dictionary data of different languages in association with each region partitioned by the region partitioning unit;
Based on the operation position information output from the contact operation input unit, a trajectory information generation unit that generates trajectory information of handwritten characters input by handwriting in the character input area;
A character position specifying unit that specifies a determination reference position for the handwritten character based on the track information generated by the track information generating unit;
An area determination unit that determines which of the plurality of areas the determination reference position belongs to;
A character recognition processing unit that performs character recognition processing on the trajectory information generated by the trajectory information generation unit using dictionary data associated with the region to which the determination reference position belongs, and extracts recognition candidates;
A handwritten character input device comprising: a recognition candidate display control unit for displaying a recognition candidate image representing a recognition candidate extracted by the character recognition processing unit on the image display unit.

  The present invention further includes a lane line display control unit that causes the image display unit to display a lane line image indicating a lane line when the area division unit divides the character input area into a plurality of areas. And

  According to the present invention, the character position specifying unit calculates a character region for the handwritten character based on the locus information of the handwritten character, and sets a predetermined position in the character region as the determination reference position. Features.

In the present invention, the character input area is a horizontally long rectangular area.
The area partitioning section partitions the character input area by line segments extending parallel to the horizontal direction of the character input area at positions offset above or below the center position in the vertical direction of the character input area. ,
When the offset position is above the center position, the character position specifying unit uses the position of the upper end portion of the character area as the determination reference position, and the offset position is below the center position. In some cases, the position of the lower end of the character area is set as the determination reference position.

  According to the present invention, a sentence in which a plurality of languages are mixed can be smoothly input without requiring a complicated operation, and the character input area has a sufficient size that can be input without any problem. Can be secured.

It is a front view which shows the external appearance structure of the smart phone 10 which is an example of the electronic device to which the handwritten character input device which concerns on this invention was applied. It is a block diagram which shows the functional structure of the handwritten character input device 20 which concerns on one Embodiment of this invention. It is a figure which shows an example of a handwritten character input screen. It is a figure which expands and shows the character input area 61a contained in the template image 65. FIG. It is a figure for demonstrating an example of the identification method of the determination reference | standard position about the handwritten character input by handwriting. It is a figure for demonstrating the determination method of the area | region where the determination reference position belongs. It is a flowchart which shows the process sequence of the handwritten character input process performed in the handwritten character input device 20 which concerns on this embodiment. It is a figure which shows the state by which the text which mixed Japanese and English was input by handwriting in the character input area 61a.

  FIG. 1 is a front view showing an external configuration of a smartphone 10 as an example of an electronic apparatus to which a handwritten character input device according to the present invention can be applied. As shown in FIG. 1, the smartphone 10 has an operation surface 11 that receives a contact operation (touch operation) by an operator and is set with orthogonal coordinates having an X axis and a Y axis as coordinate axes. The contact operation input unit 21 that outputs coordinate data indicating the coordinates of the contact operation position on the operation surface 11 when the surface 11 is contacted with a finger or a stylus, and image data on the operation surface 11 of the contact operation input unit 21 And an image display unit 22 that displays an image corresponding to the input / output device 23, and an input / output device 23 that functions as a touch interface is mounted. The orthogonal coordinates set on the operation surface 11 of the contact operation input unit 21 are, for example, the origin at the lower left vertex toward the operation surface 11, the right direction being the positive direction of the X axis, and the upper direction being the positive direction of the Y axis. XY orthogonal coordinates.

  The contact operation input unit 21 is realized by a touch panel using a known method such as a resistive film method or a capacitance method, and the image display unit 22 is realized by a known display device such as a liquid crystal display device or an organic EL display device. Is done.

  The input / output device 23 may be realized by stacking the touch panel that is the contact operation input unit 21 on the display device that is the image display unit 22. It may be realized by being built in the display device 22.

  The electronic device to which the handwritten character input device according to the present invention can be applied is not limited to the smartphone 10, and any electronic device including the input / output device 23 that functions as a touch interface may be applied. Is possible. Examples of such electronic devices include tablet PCs, feature phones, PHS (Personal Handy-phone System) terminals, PDAs (Personal Digital Assistants), personal computers, portable music players, portable navigation devices, and portable game machines. Can be mentioned.

  FIG. 2 is a block diagram showing a configuration of the handwritten character input device 20 according to the embodiment of the present invention. The handwritten character input device 20 according to the present embodiment includes two different languages, specifically, Japanese and English dictionary data 41a and 41b for handwritten character input in Japanese and English. It shall be installed.

  As shown in FIG. 2, the handwritten character input device 20 is realized by a CPU (Central Processing Unit) or the like in addition to the input / output device 23 including the contact operation input unit 21 and the image display unit 22, and controls to control the entire device. The handwritten character input process is executed by executing a handwritten character input program that is configured to include the unit 24 and a storage unit 25 realized by a semiconductor memory or the like and stored in the storage unit 25. The handwritten character input program is configured as a part of a character input application, for example.

  The control unit 24 includes a display control unit 31, a setting change unit 32, a selection determination unit 33, an area partition unit 34, a trajectory information generation unit 35, a character position specification unit 36, an area determination unit 37, and a character. And a recognition processing unit 38. The storage unit 25 includes a dictionary data storage unit 41.

  The display control unit 31 includes a template image display control unit 51, a trajectory display control unit 52, a recognition candidate display control unit 53, an input character string display control unit 54, and a lane marking display control unit 55. The

  FIG. 3 is a diagram illustrating an example of a handwritten character input screen. The template image display control unit 51 is an area in which a character input area instruction image 61 indicating a character input area 61a for an operator to input a handwritten character by a touch operation and a character image 66 indicating an input character are displayed. A character string display area instruction image 62 indicating the target field 62a, a recognition candidate display area instruction image 63 indicating an area 63a in which a recognition candidate image 67 indicating one or more recognition candidates extracted by the character recognition processing unit is displayed, and A template image 65 including a button image 64 indicating various control buttons is generated and displayed on the image display unit 22. In the example shown in FIG. 3, the button image 64 includes a “setting” button image 64a, a “space” button image 64b, a “line feed” button image 64c, and a “delete” button image 64d.

  The trajectory display control unit 52 generates a trajectory image 68 indicating the trajectory of the contact operation based on the coordinate data output from the contact operation input unit 21 when the operator performs a touch operation in the character input area 61a. The image is displayed on the image display unit 22.

  Further, the trajectory display control unit 52 starts timing from the time when the character input area 61a is last touched, and when it reaches a predetermined time, it stops timing and is displayed in the character input area 61a. The locus image 68 is deleted.

  The recognition candidate display control unit 53 generates a recognition candidate image 67 based on the one or more recognition candidates extracted by the character recognition processing unit 38, and one or more recognition candidates are displayed in a predetermined order in the region 63a. The images are displayed on the image display unit 22 so as to be lined up. In the example illustrated in FIG. 3, the recognition candidate display control unit 53 displays the recognition candidate images 67 so that they are arranged in a line from the left side of the region 63 a in the order in which the character recognition processing unit 38 determines that the shapes are close. Further, the recognition candidate display control unit 53 displays an instruction image 69 for showing the recognition candidate to the operator for the recognition candidate determined to have the closest shape.

  The input character string display control unit 54 generates a character image 66 indicating the input character and causes the image display unit 22 to display the character image 66. Specifically, when the recognition candidate image 67 is displayed in the region 63a, a character image 66 indicating the recognition candidate character with the instruction image 69 is generated and arranged next to the right of the character input immediately before. Further, the cursor image 70 is displayed on the right side of the character image 66.

  When the recognition candidate image 67 is displayed in the region 63a and the recognition candidate different from the recognition candidate with the instruction image 69 is selected by the touch operation, the input character string display control unit 54 A character image 66 indicating the selected recognition candidate character is generated, and the character image 66 is replaced with the character image 66 displayed on the left side of the cursor image 70 and displayed.

  Furthermore, when the “space” button is selected by the touch operation, the input character string display control unit 54 moves the cursor image 70 to the right by one character to display it, and the “line feed” button is selected by the touch operation. When the cursor image 70 is moved to the top position of the next line and displayed, and the “delete” button is selected by the touch operation, the character image 66 displayed on the left side of the cursor image 70 is deleted. The cursor image 70 is moved to the left by one character and displayed.

  The lane line display control unit 55 causes the image display unit 22 to display a lane line image 71 indicating the lane line when the area division unit divides the character input area 61 a into a plurality of areas 81 and 82. In the example shown in FIG. 3, a broken line image 71 is displayed.

  When the “setting” button is selected by the touch operation, the setting changing unit 32 displays a setting menu screen for setting the operation of the handwritten character input device 20 on the image display unit 22, and is set according to the input by the operator. To change.

  Based on the coordinate data output from the contact operation input unit 21, the selection determination unit 33 makes contact with various buttons, recognition candidates different from the recognition candidates to which the instruction image 69 is attached, and items included in the setting menu screen. It is determined whether or not it has been selected by an operation.

  FIG. 4 is an enlarged view of the character input area 61a included in the template image 65. As shown in FIG. As shown in FIG. 4, the character input area 61a is a horizontally long rectangular area. The area partitioning section 34 partitions the character input area 61a into a number of areas equal to the number of languages that the handwritten character input device 20 supports. In the present embodiment, since the handwritten character input device 20 is compatible with two languages, Japanese and English, the character input area 61 a is divided into two areas 81 and 82.

  In the present embodiment, the area partitioning section 34 is a line segment (partition line 71a) extending parallel to the horizontal direction of the character input area 61a at a position offset below the center position M in the vertical direction of the character input area 61a. Thus, the character input area 61a is divided into two areas 81 and 82. Therefore, as shown in FIG. 4, the region 81 arranged on the upper side of the lane marking 71a has a larger size in the vertical direction than the region 82 arranged on the lower side of the lane marking 71a.

  The dictionary data storage unit 41 stores Japanese dictionary data 41a and English dictionary data 41b, which are stored in association with the regions 81 and 82 partitioned by the region partition unit 34, respectively. In the present embodiment, the Japanese dictionary data 41 a is stored in association with the area 81, and the English dictionary data 41 b is stored in association with the area 82.

  The trajectory information generation unit 35 generates trajectory information about handwritten characters input by handwriting based on the coordinate data output from the contact operation input unit 21 when the operator performs a touch operation in the character input area 61a.

  When a handwritten character is input into the character input area 61a by a touch operation, the character position specifying unit 36 specifies a determination reference position for the handwritten character based on the trajectory information generated by the trajectory information generating unit 35. .

  FIG. 5 is a diagram for explaining an example of a method for specifying a determination reference position for a handwritten character input by handwriting. In the present embodiment, when a handwritten character is input into the character input area 61a by a touch operation, the character position specifying unit 36 calculates the character area 91 for the handwritten character based on the trajectory information about the handwritten character. To do. In this embodiment, the character area 91 is an area surrounded by a circumscribed rectangle of the handwritten character, as shown in FIG. The circumscribed rectangle is determined such that each side thereof extends along the vertical direction or the horizontal direction of the character input area 61a.

  When the character area 91 is calculated, the character position specifying unit 36 sets a predetermined position in the character area 91 as a determination reference position. In the present embodiment, as shown in FIG. 4, the position of the partition line 71a is set to a position that is offset below the center position M in the vertical direction of the character input area 61a. As shown in FIG. 5B, the position of the lower end portion 91a of the character area 91 is set as the determination reference position.

  In addition, when the position of the division line 71a is set to a position offset above the center position M in the vertical direction of the character input area 61a by the area dividing section 34, the character position specifying section 36 The position of the upper end portion 91 is set as a determination reference position.

  The region determination unit 37 determines which of the two regions 81 and 82 that the determination reference position specified by the character position specification unit 36 for the handwritten character input by the touch operation is divided by the region partition unit 34. Determine if it belongs.

  FIG. 6 is a diagram for explaining a method of determining an area to which the determination reference position belongs. As shown in FIG. 6A, when the position of the lower end 91a, which is the determination reference position, is above the lane marking 71a, it is determined that the determination reference position belongs to the region 81, and FIG. As shown in b), when the position of the lower end portion 91a which is the determination reference position is below the lane marking 71a, it is determined that the determination reference position belongs to the region 82.

  The character recognition processing unit 38 performs character recognition processing on the trajectory information generated by the trajectory information generation unit 35 using dictionary data associated with the region to which the determination reference position belongs, and extracts recognition candidates.

  Specifically, for a handwritten character input by a touch operation, as shown in FIG. 6A, when it is determined that the determination reference position belongs to the region 81, the handwritten character is associated with the region 81. Character recognition processing is performed on the trajectory information generated by the trajectory information generation unit 35 using the Japanese dictionary data 41a, and recognition candidates are extracted. On the other hand, as shown in FIG. 6B, when it is determined that the determination reference position belongs to the region 82, the trajectory information generation unit is used using the English dictionary data 41 b associated with the region 82. Character recognition processing is performed on the trajectory information generated by 35 to extract recognition candidates.

  FIG. 7 is a flowchart showing a processing procedure of handwritten character input processing executed in the handwritten character input device 20 according to the present embodiment. In an electronic device to which the handwritten character input device 20 according to the present embodiment is applied, when an application such as a memo pad, mail, and web browser is activated and the character input mode is enabled, that is, the character input mode is set. When the mode is switched to the input mode for inputting characters by handwriting, the process is started. When the handwritten character input screen is displayed based on the template image 65, the process proceeds to step s1.

  When the operator performs a contact operation in the character input area 61a in step s1, the trajectory display control unit 52 causes the trajectory image 68 to be displayed on the image display unit 22 based on the coordinate data output from the contact operation input unit 21. Display. When a handwritten character is input into the character input area 61a, the trajectory information generation unit 35 generates trajectory information about the handwritten character input by handwriting based on the coordinate data output from the contact operation input unit 21. Then, the process proceeds to step s2.

  In step s2, the character position specifying unit 36 specifies the determination reference position for the handwritten character based on the trajectory information generated by the trajectory information generating unit 35, and the process proceeds to step s3.

  In step s 3, the region determination unit 37 determines to which region of the two regions 81 and 82 that the determination reference position specified by the character position specification unit 36 is partitioned by the region partition unit 34 belongs. . If the determination reference position belongs to the area 81, the language of the handwritten character is assumed to be Japanese, and the process proceeds to step s4. If the determination reference position belongs to the area 82, the language of the handwritten character is English. The process proceeds to step s5.

  In step s4, the character recognition processing unit 38 performs character recognition processing on the trajectory information generated by the trajectory information generation unit 35 using the Japanese dictionary data 41a for the handwritten character input by the contact operation, and recognizes it. Candidates are extracted, and the process proceeds to step s6.

  In step s5, the character recognition processing unit 38 performs character recognition processing on the trajectory information generated by the trajectory information generation unit 35 using the English dictionary data 41b for the handwritten character input by the contact operation, and the recognition candidate. Is extracted and the process proceeds to step s6.

  In step s6, the recognition candidate display control unit 53 generates a recognition candidate image 67 based on the one or more recognition candidates extracted by the character recognition processing unit 38, and one or more recognition candidates are found in the region 63a. The images are displayed on the image display unit 22 so as to be arranged in a predetermined order. In addition, the input character string display control unit 54 selects a recognition candidate determined to have the closest shape, that is, a character image 66 indicating a recognition candidate character to which the instruction image 69 is attached in the target field 62a. The display is made at a predetermined position, and the process proceeds to step s7.

  In step s7, based on the coordinate data output from the contact operation input unit 21, the selection determination unit 33 selects a recognition candidate different from the recognition candidates to which various buttons and the instruction image 69 are attached by the contact operation. If it is not selected, the process proceeds to step s8. If it is selected, the process proceeds to step s9.

  In step s8, when the control unit 24 determines that the character input mode has been terminated or has been switched to another input mode by the operator, the handwriting character input process is terminated, and the character input mode is continuing. If it is determined that the input mode has not been switched, the process returns to step s1.

  In step s9, processing corresponding to the object selected in step s7 is performed, and the process returns to step s1. For example, when the “delete” button is selected by the touch operation, the input character string display control unit 54 deletes the character image 66 displayed on the left side of the cursor image 70 in the target field 62a, and The cursor image 70 is moved to the left by one character and displayed.

  When a recognition candidate different from the recognition candidate to which the instruction image 69 is attached is selected by the touch operation, the character image 66 of the selected recognition candidate is displayed on the left side of the cursor image 70. It is replaced with the character image 66 and displayed.

  FIG. 8 is a diagram illustrating a state in which a sentence in which Japanese and English are mixed is input by handwriting in the character input area 61a. As shown in FIG. 8, within one character input area 61a, the position of the lower end 91a of the character area 91, which is the determination reference position, is positioned above the lane marking 71a, such as “right”. If so, the character recognition process is performed using the Japanese dictionary data 41a, and the position of the lower end 91a of the character area 91, which is the determination reference position, is lower than the lane marking 71a, as in “FAQ”. If it is located, character recognition processing is performed using the English dictionary data 41b.

  As described above, according to the present embodiment, since an operation for switching the recognition language during the input is not required, while performing a highly accurate recognition in the target language without hindering the flow of the input operation, It is possible to input easily, and the operation efficiency can be remarkably improved.

  Furthermore, since the operation is performed within the range of one input frame without using multiple input frames corresponding to the recognition language, the ratio of the input unit can be reduced even in a limited screen size such as a smartphone. Even when characters in different languages are mixed in a series of input character strings, only one input frame is used, so that a smooth input operation can be performed.

  Further, according to the present embodiment, as shown in FIG. 3, the character input area 61 a has a lane line image 71 showing a lane line when the area partition unit 34 divides the character input area 61 a into a plurality of areas. Since it is configured to be displayed, the operator inputs handwritten characters into the character input area 61a so that the character recognition processing is performed using dictionary data in a desired language using the marking line image 71 as a mark. Can do. That is, the operability by the operator can be improved.

  Further, according to the present embodiment, when the position of the partition line 71a is set to a position offset downward from the center position M in the vertical direction of the character input area 61a, The position specifying unit 36 uses the position of the lower end 91a of the character area 91 as the determination reference position, and the area dividing unit 34 offsets the position of the dividing line 71a above the center position M in the vertical direction of the character input area 61a. In the case where the position is determined, the character position specifying unit 36 is configured so that the position of the upper end portion of the character region 91 is set as the determination reference position. As a result, in any language, a sufficiently large area (vertical dimension) that allows character input without problems is ensured, and the operator can easily input characters by handwriting.

  In the present embodiment, the handwritten character input device 20 on which dictionary data of two different languages is installed is taken as an example, but handwritten characters on which dictionary data of three or more languages different from each other are installed. The present invention can also be applied to an input device.

DESCRIPTION OF SYMBOLS 11 Operation surface 20 Handwritten character input device 21 Contact operation input part 22 Image display part 23 Input / output device 24 Control part 25 Storage part 31 Display control part 34 Area division part 35 Trajectory information generation part 36 Character position specification part 37 Area determination part 38 Character recognition processing unit 41 Dictionary data storage unit 51 Template image display control unit 52 Trajectory display control unit 53 Recognition candidate display control unit 54 Input character string display control unit 55 Parcel line display control unit

Claims (4)

A contact operation input unit that has an operation surface that receives a contact operation by an operator and outputs operation position information indicating an operation position on the operation surface on which the operator performs a contact operation;
An image display unit for displaying an image on the operation surface of the contact operation input unit;
A template image display control unit that causes the image display unit to display a template image including a character input region instruction image indicating a character input region in which the operator inputs a handwritten character by a contact operation;
An area dividing section for dividing the character input area into a plurality of areas;
Dictionary data storage unit for storing dictionary data of different languages in association with each region partitioned by the region partitioning unit;
Based on the operation position information output from the contact operation input unit, a trajectory information generation unit that generates trajectory information of handwritten characters input by handwriting in the character input area;
A character position specifying unit that specifies a determination reference position for the handwritten character based on the track information generated by the track information generating unit;
An area determination unit that determines which of the plurality of areas the determination reference position belongs to;
A character recognition processing unit that performs character recognition processing on the trajectory information generated by the trajectory information generation unit using dictionary data associated with the region to which the determination reference position belongs, and extracts recognition candidates;
The handwritten character input device characterized by including the recognition candidate display control part which displays the recognition candidate image showing the recognition candidate extracted by the said character recognition process part on the said image display part.   2. The lane marking display control unit that causes the image display unit to display a lane line image indicating a lane line when the area partition unit divides the character input area into a plurality of areas. The handwritten character input device described in 1.   The character position specifying unit calculates a character region for the handwritten character based on trajectory information of the handwritten character, and sets a predetermined position in the character region as the determination reference position. The handwritten character input device according to 1 or 2. The character input area is a horizontally long rectangular area,
The area partitioning section partitions the character input area by line segments extending parallel to the horizontal direction of the character input area at positions offset above or below the center position in the vertical direction of the character input area. ,
When the offset position is above the center position, the character position specifying unit uses the position of the upper end portion of the character area as the determination reference position, and the offset position is below the center position. 4. The handwritten character input device according to claim 3, wherein a position of a lower end portion of the character region is set as the determination reference position.