JPH0773176A - Information processing equipment - Google Patents

Abstract

(57) [Abstract] [Purpose] To improve the character recognition rate of uppercase and lowercase letters input by handwriting and improve the input efficiency of documents. [Structure] The recognition processing unit 23 includes a character coordinate data buffer 3
The handwritten character in 2 is character-recognized and the recognition result is stored in the input character buffer 33. However, the overwriting detection unit 25 determines whether a character code after recognition already exists in the input frame in which the handwritten character is input. If so, the upper / lower case detection unit 26 determines whether or not the character code stored in the input character buffer 33 is a character code having an upper case character or a lower case character. Then, the character comparison unit 27 determines whether the character code newly recognized and the character code already recognized are equal, and if they are equal,
If the newly recognized character code is uppercase, it is replaced with lowercase, and if it is lowercase, it is replaced with uppercase, and the replacement result is stored in the character code string storage buffer 33 and displayed in the input frame of the display device 3.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing apparatus such as a document creating apparatus for recognizing characters input by handwriting to create a document, and more particularly to improving the recognition rate of handwritten characters.

[0002]

2. Description of the Related Art In recent years, with advances in handwriting recognition technology, characters input by handwriting with a stylus pen or the like are recognized on an input display device in which a transparent tablet and a display are laminated and integrated, and kanji and kana mixed kana conversion is performed. A document creation device or the like that creates a document by applying the above has been put into practical use. However, in reality, there is a problem in recognition accuracy when recognizing handwritten characters, and characters input by handwriting are not always always correctly recognized. In particular, recognition of uppercase and lowercase letters, for example, erroneous recognition of “a” and “a”, “yo” and “yo” tends to occur relatively frequently. Each time such misrecognition occurs, the user has to re-input the characters by handwriting, and since there is a high probability that such misrecognition will occur even after re-entry, it takes time to input the document. Therefore, further improvement of character recognition is required.

[0003]

In a conventional information processing apparatus such as a document preparation apparatus which recognizes input handwritten characters and inputs a document, the accuracy of the character recognition is not always at a satisfactory level. Recognition of uppercase and lowercase letters, for example, erroneous recognition of "a" and "a" and "yo" and "yo" tends to occur relatively frequently. Each time such misrecognition occurs, the user has to re-input the characters by handwriting, and since there is a high probability that such misrecognition will occur even after re-entry, it takes time to input the document. Therefore, further improvement of character recognition is required.

The present invention has been made in consideration of such circumstances, and provides an information processing apparatus capable of improving the character recognition rate of uppercase and lowercase letters input by handwriting and improving the input efficiency of a document. Is intended.

[0005]

SUMMARY OF THE INVENTION The present invention provides an information processing apparatus for character-recognizing a character handwritten by a user in an input box and displaying the recognition result in the input box.
First deciding means for deciding whether or not a character code obtained by handwriting input in the input frame and character recognition is already present when the character handwritten in the input frame is recognized. If it is determined by the first determining means that the character code already recognized and obtained exists, the character recognition result of the handwritten character newly input in the input box has a capital letter or a lowercase letter. If it is determined that the character code obtained by newly recognizing by the second judging means is a character code having an uppercase letter or a lowercase letter, A third determination means for determining whether or not the character code obtained by recognizing the character code and the character code already recognized are equal to each other;
When the third determination means determines that the two character codes are equal, the newly recognized character code is replaced with a lower case when the character code is an upper case character, and when the character code is a lower case character, with a upper case character. The character obtained by the replacing means is displayed in the input frame and input into the apparatus.

[0006]

In the information processing apparatus of the present invention, when the first determination means character-recognizes a character handwritten in the input frame, the character code obtained by handwriting-input in the input frame and character recognition is obtained. Determine if it already exists.
When it is determined that the character code obtained by being recognized by the first determining means is present, the second determining means determines that the character recognition result of the handwritten character newly input in the input box is capitalized. Alternatively, it is determined whether the character code has a lower case character. If the third determination means determines that the character code newly recognized by the second determination means is a character code having an uppercase letter or a lowercase letter, it is determined that the newly recognized character code is obtained. It is determined whether the character codes already recognized and obtained are equal. The replacing means replaces the character code newly recognized by the third judging means when the both character codes are equal to each other with an uppercase character when the character code is newly obtained, and with a lowercase character when the character code is lowercase. . The characters obtained by the replacing means are displayed in the input frame and input into the device. As a result, the recognition rate of uppercase and lowercase letters of handwritten characters can be improved.

[0007]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of an information processing apparatus (a document creating apparatus in this example) of the present invention. The document creation device comprises a coordinate input device 1, a control device 2, a display device 3 and an external storage device 4. The coordinate input device 1 includes, for example, a transparent tablet and a stylus pen, and the transparent tablet is stacked on a display device 3 such as a liquid crystal display to form an input display device. The input display device is integrated with the control device 2. There is. The transparent tablet and the liquid crystal display have the same coordinate plane, and the coordinate values on the liquid crystal display can be directly specified by the stylus pen through the transparent tablet, and the information displayed on the liquid crystal display is presented to the operator through the transparent tablet, and the operator Allows you to see the locus of input characters. The control device 2 includes an initialization unit 21, a coordinate input unit 22, a recognition processing unit 23, a character display unit 24, an overwriting detection unit 25,
A processing unit including an upper / lower case detection unit 26, a character comparison unit 27, a replacement character creation unit 28, an input end processing unit 29, and a display control unit 30, a coordinate data buffer 31, a character coordinate data buffer 32, an input character buffer 33, The character code string storage buffer 34, the recognition dictionary buffer 35, the screen area coordinate data buffer 36, the screen image buffer 37, and the document buffer 38 constitute a memory unit. The display device 3 is, for example, a liquid crystal display as described above. The external storage device 4 is composed of a recognition dictionary 41, screen area coordinate data 42, a screen image 43, an upper / lower case correspondence table 44, a document 45, and a magnetic disk device storing data for initializing the system and the like. Some are integrated with the control device 2.

Next, the operation of this embodiment will be described. The initialization unit 21 of the control device 2 clears the coordinate data buffer 31, the character coordinate data buffer 32, the input character buffer 33, and the character code string storage buffer 34, and then the recognition dictionary buffer 35, the screen area coordinate data buffer 36, the screen image. The recognition dictionary 41, the screen area coordinate data 42, the screen image 43, and the document 45 stored in the external storage device 4 in the buffer 37 and the document buffer 38, respectively.
, The initial screen image stored in the screen image buffer 37 is displayed on the display device 3, and the coordinate input unit 22 is activated. At this time, the screen image buffer 37 stores screen area coordinate data 42 showing the correspondence between the area coordinate range in which the area is represented by a diagonal line of two points and the area name as shown in FIG. The screen area coordinate data 42 is displayed on the screen of the display device 3 as shown in FIG. 4, and the input frame has a frame name and the input end has a function name. The character code string storage buffer 34 is composed of character code buffers (not shown) corresponding to the number of input frames, and the characters input into the input frame shown in FIG. 4 become character codes after recognition and correspond to the input frames. Stored in the character code buffer.

The coordinate input section 22 stores the coordinate data input via the coordinate input device 1 in the coordinate data buffer 31, and the input coordinate values in the screen area coordinate data buffer 36 on the screen. When the coordinate value is within the input frame, the contents of the coordinate data buffer 31 are transferred to the character coordinate data buffer 32, and then the recognition processing unit 23
To start. If the coordinate value is in the input end button, the coordinate input unit 22 activates the input end processing unit 29.

The recognition processing unit 23 refers to the recognition dictionary 41 stored in the recognition dictionary buffer 35 to perform character recognition on the coordinate value string stored in the character coordinate data buffer 32, and as a result of this recognition. After storing the obtained character code in the input character buffer 33, the overwriting detection unit 2
Start 5. The character display unit 24 is controlled by the display control unit 30, reads a character pattern corresponding to the character code stored in the input character buffer 33 from the screen image buffer 37, displays it in the input frame, and stores it in the document buffer 38. The character pattern corresponding to the specified character code is read from the screen image buffer 37 and displayed in the document area shown in FIG.

The overwriting detection section 25 compares the coordinate values stored in the coordinate data buffer 31 with the screen area coordinate data 42 stored in the screen area coordinate data buffer 36, and stores them in the coordinate data buffer 31. Whether or not the character code already exists in the input box indicated by the coordinate value is checked by the presence or absence of the character code in the corresponding character code buffer in the character code string storage buffer 34. As a result, when the character code does not exist, the overwriting detection unit 25 determines that overwriting is not performed, and the character code stored in the input character buffer 33 is input by handwriting. After storing in the character code buffer in the character code string storage buffer 34 corresponding to the input frame, the display control unit 30 is activated, and the recognized character corresponding to the character code stored in the input character buffer 33 is displayed. Display in the input frame. If the character code exists,
The overwriting detection unit 25 determines that overwriting is performed, and activates the uppercase / lowercase detection unit 26.

The upper / lower case detector 26 compares the character code stored in the input character buffer 33 with each character code stored in the upper / lower case correspondence table 44 in the external storage device 4 shown in FIG. Then, it is checked whether there is a match. If there is no match, the uppercase / lowercase detection unit 26 determines that the recognized character is a character code having no uppercase or lowercase, and determines the character code stored in the input character buffer 33 as the input frame. After storing the character code in the character code buffer of the character code string storage buffer 34, the display control unit 30 is activated to display the character code. If there is a matching character code,
The uppercase / lowercase detection unit 26 determines that the newly recognized character code is a character code having uppercase or lowercase, and activates the character comparison unit 27.

The character comparison unit 27 compares the character code stored in the input character buffer 33 and the character code stored in the character code buffer of the character code string storage buffer 34 corresponding to the input frame into which the handwritten character is input. Compare to see if they are equal. As a result, if they are not equal, the character comparison unit 27 stores the character code stored in the input character buffer 33 in the character code buffer of the character code string storage buffer 34 corresponding to the input frame in which the handwritten character is input. The display control unit 30 is activated. However, if they are equal, the character comparison unit 27 determines that the replacement character creation unit 28
To start.

The replacement character creating section 28 searches the upper / lower case correspondence table 44 of the external storage device 4 for the character code stored in the input character buffer 33, and if the character code is upper case, the corresponding lower case character is used. If the character code is lowercase, the corresponding uppercase character code is stored in the input character buffer 33. After that, input character buffer 3
After storing the character code stored in No. 3 in the character code buffer in the character code string storage buffer 34 corresponding to the input box in which the handwritten character is input, the display control unit 30 is activated to input the input character buffer 33. The character code stored in is displayed in the input frame.

The input end processing unit 29 additionally stores the contents of the corresponding character code buffer in the character code string storage buffer 34 in the document buffer 38, and then clears the corresponding character code buffer in the character code string storage buffer 34. After that, when the display control unit 30 is activated, the display control unit 30 controls the character display unit 24 to display the character string corresponding to the character code in the document buffer 38 in the document area of FIG.

Next, the operation of each processing unit described above will be described with reference to the flow chart shown in FIG. First, the initialization unit 21
After clearing the coordinate data buffer 31, the character coordinate data buffer 32, the input character buffer 33, and the character code string storage buffer 34 by the initialization work of step 201, the recognition dictionary buffer 35, the screen area coordinate data buffer 36, the screen image Buffer 37, document buffer 38
The recognition dictionary 41, the screen area coordinate data 42, the screen image 43, and the document 45 stored in the external storage device 4 are read into each.

Subsequently, the coordinate input unit 22 causes the step 202.
After storing the coordinate data input through the coordinate input device 1 in the coordinate data buffer 31, at step 203, it is checked whether the input coordinate value is within the input frame or the input end frame. The determination is made in step 204. If it is within the input frame, the process proceeds to step 205, and if it is not within the input frame, the process proceeds to step 215.

The coordinate input unit 22 determines in step 215 whether or not the coordinate value is within the end of input. If the coordinate value is not within the frame, the process returns to step 202, and if it is within the frame, the process proceeds to step 216. Since the coordinate input unit 22 activates the input end processing unit 29 in step 216, the input end processing unit 29 additionally stores the content of the character code string storage buffer 34 in the document buffer 38, and proceeds to step 217. The coordinate input unit 22 clears the character code string storage buffer 34 in step 217, and then proceeds to step 218. In step 218, the display control unit 30 controls the character display unit 24 to clear the inside of the input frame and displays the contents of the document buffer 38 in the document area of FIG.

If the coordinate value is within the input box, step 20
If the process proceeds to step 5, the coordinate input unit 22 stores the contents of the coordinate data buffer 31 in the character coordinate data buffer 32, and then activates the recognition processing unit 23 in step 206 to perform character recognition. The recognition processing unit 23 stores the recognition result in the input character buffer 33 in Step 207, and then activates the overwriting detection unit 25 to determine in Step 208 whether or not a character code already exists in the input frame. Find out.

When it is determined in step 208 that the character code does not exist in the input box in which the handwritten character is input, the recognition processing unit 23 determines the contents of the input character buffer 33 in the input box in which the handwritten character is input. To the character code buffer in the character code string storage buffer 34 corresponding to
After storing at 14, the display control unit 30 displays the character display unit 24.
Is controlled to display the contents of the input character buffer 33 in the input frame in step 218.

When it is determined in step 208 that the character code already exists in the input box into which the handwritten character has been input, the recognition processing unit 23 activates the uppercase / lowercase detection unit 26 and stores it in the input character buffer 33. In step 209, it is checked whether the stored character code is an uppercase character or a lowercase character code. When it is determined in step 209 that the character code has no uppercase or lowercase letters, the uppercase / lowercase detection unit 26 stores the content of the input character buffer 33 in the character code string corresponding to the input frame in which the handwritten character is input. After storing in the character code buffer in the buffer 34 in step 214, the display control unit 30 controls the character display unit 24 in step 218 to display the contents of the input character buffer 33 in the input frame.

When it is determined in step 209 that the character code has uppercase or lowercase letters, the uppercase / lowercase detection unit 26 activates the character comparison unit 27 to input the handwritten character to the character code of the input character buffer 33. In step 210, the character code in the character code buffer of the character code string storage buffer 34 corresponding to the selected input frame is compared,
In step 211, it is checked whether the two are equal.

When it is determined in step 211 that the two are not equal, the character comparison unit 27 sets the contents of the input character buffer 33 to the characters in the character code string storage buffer 34 corresponding to the input box in which the handwritten character is input. After storing in the code buffer in step 214, the display control unit 30 controls the character display unit 24 to display the contents of the input character buffer 33 in the input frame on the display device 3 in step 218.

When it is determined in step 211 that the two character codes are the same, the character comparison unit 27 activates the replacement character creation unit 28, and when the character code is upper case, it is changed to lower case, and when it is lower case, changed to upper case. Replace in step 212. After that, the replacement character creation unit 28 stores the replacement result in the input character buffer 33 and the character code buffer of the character code string storage buffer 34 corresponding to the input box in which the handwritten character is input in step 213, and proceeds to step 218. . The display control unit 30 controls the character display unit 24 to display the contents of the input character buffer 33 in the input frame.

Next, the handwriting character recognition operation will be described in more detail using a specific example. When the device shown in FIG. 1 is activated, the screen of the display device 3 is initialized and the screen image as shown in FIG. 7 is displayed. Here, it is assumed that the characters "Asuha rain" have already been displayed in the input frame displayed on the screen of the display device 3 as shown in FIG. Now, when the user inputs a character as shown in FIG. 9 by handwriting from the coordinate input device 1 into the input frame in which "a" is displayed, the recognition processing unit 23 performs character recognition on this character, The recognition result is replaced with "a", and this "a" is displayed in the input frame as shown in FIG. Here, when the user inputs a character as shown in FIG. 11 into the input frame in which "A" is displayed again, the recognition processing unit 23 performs character recognition on this character, and the recognition is performed. If the result is "bright", "bright" is displayed in the input frame without being replaced with the lowercase letter "a" as shown in FIG. After further inputting and performing kana-to-kanji conversion on the characters in the input box, the user instructs the end of input with a stylus pen as shown in FIG. 13, and the characters in the input box are changed as shown in FIG. It is displayed as a document in the document area.

According to the present embodiment, when a handwritten character is already input and a handwritten character is further input into the input frame in which character recognition has been performed for this character, the character code which is the recognition result of this character. If the character code already entered has the same uppercase and lowercase letters, the character code entered later shows the same uppercase letter or lowercase letter as the already entered character code. By adopting lower case when the character code is upper case and using upper case as the character recognition result when it is lower case, even if the upper case and lower case are misrecognized during character recognition, correct recognition can be done by re-inputting once. The result can be obtained. As a result, the character recognition rate of uppercase and lowercase characters can be improved, and the operability of the device can be improved accordingly.

The present invention is not limited to the above embodiment. For example, although the hiragana replacement is performed in this embodiment, the replacement target character may be katakana or an alphabetic character. In short, the present invention can be implemented with various modifications without departing from the scope of the invention.

[0028]

As described above, according to the information processing apparatus of the present invention, it is possible to improve the character recognition rate of uppercase and lowercase letters input by handwriting and improve the input efficiency of a document.

[000]

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of an information processing apparatus of the present invention.

FIG. 2 is a flowchart showing a handwriting character recognition process by the apparatus shown in FIG.

FIG. 3 is a diagram showing an example of screen area coordinate data.

FIG. 4 is a diagram showing an example of an input display screen of a display device.

FIG. 5 is a diagram showing an example of data in a character code string storage buffer when a character code is given to an input box.

FIG. 6 is a diagram showing an example of an uppercase / lowercase correspondence table.

FIG. 7 is a diagram showing a display example of a screen at the end of initialization processing.

FIG. 8 is a diagram showing a display example of a handwritten character recognition result.

FIG. 9 is a diagram showing an example in which handwriting input is performed in an input frame for which recognition processing has already been completed.

FIG. 10 is a diagram showing a display example of a result after the replacement process is completed.

FIG. 11 is a diagram showing an example in which handwriting input is performed in an input frame in which a result after completion of replacement processing is displayed.

FIG. 12 is a diagram showing an example of displaying a handwritten character recognition result.

FIG. 13 is a diagram showing an example of instructing the end of input.

FIG. 14 is a diagram showing an example in which the characters in the input box after the input is turned into a document.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Coordinate input device 2 ... Control device 3 ... Display device 4 ... External storage device 21 ... Initialization unit 22 ... Coordinate input unit 23 ... Recognition processing unit 24 ... Character display unit 25 ... Overwrite detection unit 26 ... Uppercase letters
Lowercase character detection unit 27 ... Character comparison unit 28 ... Substitution character creation unit 29 ... Input end processing unit 30 ... Display control unit 31 ... Coordinate data buffer 32 ... Character coordinate data buffer 33 ... Input character buffer 34 ... Character code string storage buffer 35 ... Recognition dictionary buffer 36 ... Screen area coordinate data buffer 37 ... Screen image buffer 38 ... Document buffer 41 ... Recognition dictionary 42 ... Screen area coordinate data 43 ... Screen image 44 ... Upper case /
Lower case correspondence table 45 ... Document

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Yuichi Inoue 1381 Shinmachi, Ome-shi, Tokyo Within Toshiba Computer Engineering Co., Ltd. (72) Inventor Toshiya Goto 1381 Shinmachi, Ome-shi, Tokyo 1 Toshiba Computer Within Ta Engineering Co., Ltd. (72) Koji Kinoshita 1381 Shinmachi, Ome-shi, Tokyo Inside Toshiba Computer Engineering Co., Ltd. (72) Hirofumi Tsujimoto 1381 Shinmachi, Ome-shi, Tokyo Toshiba Computer Engineering (72) Inventor Yoshiteru Tanaka 1381 Shinmachi, Ome-shi, Tokyo 1 Toshiba Computer Engineering Co., Ltd. (72) Inventor Kenichi Koga 1381 Shinmachi, Ome-shi, Tokyo Toshiba Computer Engineering Co., Ltd. Within

Claims (1)

[Claims] 1. An information processing apparatus for recognizing a character handwritten by a user in an input frame and displaying the recognition result in the input frame, recognizing the character handwritten in the input frame. At this time, the first determination means for determining whether or not the character code obtained by handwriting input and character recognition in the input frame already exists, and the first determination means.
If it is determined that the character code that has already been recognized and obtained by the determining means of, the character recognition result of the handwritten character newly input in the input frame is a character code having an uppercase letter or a lowercase letter. Second determining means for determining whether or not, and when it is determined that the character code newly obtained by the second determining means is a character code having an uppercase letter or a lowercase letter, it is newly recognized. A third judging means for judging whether or not the character code obtained by recognizing the character code and the character code already recognized are equal to each other, and when the third character judging means judges that the both character codes are equal. When the newly recognized character code is an uppercase character, the character code is replaced with a lowercase character, and when the character code is a lowercase character, a replacing means is provided for replacing the character code with an uppercase character, and the character obtained by this replacing means is displayed in the input frame. Device The information processing apparatus characterized by entering into.