JPH0737039A - On-line handwritten character recognizing device - Google Patents

Abstract

PURPOSE:To provide an on-line handwritten character recognizing device which can easily input the characters and can correct the errors by a simple instructions of uses. CONSTITUTION:The characters are supplied from a tablet 1. A character segmenting part 2 segments a single character based the distance moved while a pen is kept a part from the tablet 1. The segmented character is sent to a character recognizing part 5 and recognized there. At the same time, the segmented character is stored in a data buffer 3. A display part 4 shows the input data and the character recognizing results set corresponding to each other. A gesture recognizing part 6 analyzes the gestures that are pointed by users about their misrecognition. An instruction analyzing part 7 analyzes the instructions of users.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an on-line handwritten character recognition apparatus for recognizing characters in real time while inputting strokes constituting handwritten characters.

[0002]

2. Description of the Related Art Conventionally, a keyboard has been mainly used to input character data into a computer or the like.
However, in order to use the keyboard, the user has to learn and get used to it to some extent, and therefore,
It has been desired to realize a simpler input device.

In response to the above-mentioned demands, the recent high performance and high speed of a computer responds to the above demands, and an online handwritten character recognition for recognizing a handwritten character in real time as a simpler input device replacing a keyboard and converting it into character data. It was possible to realize the device.

The realized on-line handwritten character recognition device basically has a tablet for inputting a coordinate sequence forming a character and a display means for displaying the input character overlaid on the tablet as it is. , And a character recognition unit that is realized by a program and recognizes input handwritten characters and converts them into character data.

Strokes written on the tablet using the pen are displayed as they are on the display means overlaid on the tablet as handwriting and are sent to the character recognition section.
Converted to data that represents a character.

In the on-line handwritten character recognition device, when a plurality of characters are continuously input, it is necessary to cut out one by one from the plurality of input characters for recognition.

Conventionally, an input frame is set in the recognition device in order to eliminate the process of cutting out one character, and the user is required to write each character in the input frame.

[0008] In order to allow the user to input characters more freely, input without an input frame is also realized. In this case, however, the recognition device cuts out one character at the input coordinates and when the pen is away. Was determined from.

When the result of character recognition after input is displayed and the result is incorrect, a candidate is displayed,
If it was re-selected from the candidates, or if it was still incorrect, it would rewrite the letters.

[0010]

If there is an input frame, it imposes a constraint on the user when writing, which is a heavy burden.

In the case of inputting without a frame, especially when a Chinese character is input, and when it is not clear whether the input character is a partial character or a character independent of each other, the input coordinates and the time when the pen is apart It is difficult to determine whether the character entered by just one character or a plurality of characters is input, and the character cutout portion may be erroneous. For example, FIG. 4 shows a case where handwriting input of "moving" is performed. In this example, the bias and the urine are separated from each other, and it is not clear whether the input is "moving" or "gravity", and the conventional method cannot correctly recognize the input. Such misrecognition can occur not only in Kanji but also in Hiragana and Katakana.

Regarding correction of erroneous recognition, selection from candidates and redoing of input are complicated operations for the user, and simpler correction is desired.

It is an object of the present invention to provide an on-line handwritten character recognition device which enables character recognition with less erroneous recognition and can correct an error by a simple instruction even if there is a recognition error.

[0014]

The on-line handwritten character recognition device of the present invention is an on-line handwritten character recognition device for collating characters based on the position information of the pen sent from the tablet, and the pen is separated from the tablet. A means for cutting out one character based on the distance traveled sometimes and the time the pen is away from the tablet; a means for performing recognition after cutting out the character and displaying the result in correspondence with the input data; When there is a cutting error, it is characterized in that it is provided with a means for carrying out re-recognition based on the position information of the pen in the specified range and making a correction.

[0015]

The on-line handwritten character recognizing device of the present invention has a moving distance when the pen is away from the tablet,
1 based on how long the pen is away from the tablet
Cut out characters. After cutting out the characters, recognition is performed,
The result and the input data are displayed in association with each other.
If there is an error in cutting out, recognition is performed again by pointing with a pen and correction is made.

[0016]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 shows a basic block diagram according to this embodiment. The online handwritten character recognition device of FIG. 1 includes a tablet 1 for inputting characters, a character cutout unit 2 for cutting out one character from data sent from the tablet 1, a data buffer 3 for storing input data, an input data and characters. A display unit 4 for displaying corresponding recognition results, a character recognition unit 5 for performing character recognition on input data, a gesture recognition unit 6 for analyzing a gesture instructing erroneous recognition from a user,
Further, it is composed of an instruction analysis unit 7 which analyzes the instruction of the user. The character cutout unit 2, the character recognition unit 5, the gesture recognition unit 6, and the instruction analysis unit 7 are realized by a CPU (not shown).

The character cutout unit 2 cuts out one character of the data sent from the tablet 1 and sends it to the character recognition unit 5. At this time, it is simultaneously stored as data for each stroke in the data buffer 3.

On the other hand, the character cutout unit cuts out characters according to the flowchart shown in FIG. The character is cut out based on the distance traveled when the pen is away from the tablet and the time when the pen is away from the tablet. For example, when inputting “computer” as shown in FIG. 3, point A, which is the end point of “K”, is input.
When the pen moves from the tablet to the point B which is the point of writing "n", the pen is apart from the tablet for a certain time, and when the pen moves from character to character, there is a certain amount of blank space. . Utilizing this, the character is cut out in this embodiment.

The flowchart of the character cutting process shown in FIG. 2 will be described in detail below. In this embodiment, the characters are written from right to left.

The value of the movement time of the pen between strokes within the first character is input to tmax as an initial value.

In step S21, stroke data is input.

In steps S22 and S23, i-1
Let Ti be the time taken for the pen to move from the end point of the th stroke to the i-th start point, and let Si be the lateral distance. A rightward movement is a positive value, and a leftward movement is a negative value.

In step S24, when the movement distance Si between strokes is a negative value, the i-th stroke and the (i + 1) -th stroke are strokes of the same character.
Return to S21. If the inter-stroke movement distance Si is not a negative value, the process proceeds to step S25.

In step S25, it is determined that the movement distance Si between strokes is larger than twice the width of the entire stroke of the (n-1) th character, for example, when the nth character is currently cut out. , Is a positive value and is sufficiently large, it is determined that the i-th stroke and the (i + 1) -th stroke are strokes of different characters, and step S27 is performed.
Proceed to. When the inter-stroke movement distance Si is a positive value but not sufficiently large, the process proceeds to step S26.

In step S26, when cutting out the nth character, the maximum value tmax of the movement time between strokes of the n-1th character is referred to, and 0.
With a margin d of about 5 seconds, travel time T between strokes
When i is larger than tmax + d, it is determined that the i-th stroke and the i + 1-th stroke are different character strokes,
Go to step 27. If not larger, step S21
Return to.

In step S27, tmax is changed according to the movement time of the pen between strokes of the character cut out for cutting out the next character.

In step S28, one character is output. After the process of cutting out one character is completed, step S
Return to 21.

When the data of all characters are input, the result of the character recognition unit 5 is sent to the display unit 4 and the result is displayed on the screen.

The display unit 4 displays the input data (handwritten characters themselves) and the recognition result in association with each other. FIG. 5 shows an example of the display. In this example, handwriting input "shisute" is judged as "single", "shi", and "ta", and cut out, and the recognition results are "ho", "shi", and "ta".
And the result is displayed. The recognition result is displayed below a stroke or a stroke group cut out as one character.

When there is an error in the recognition result, particularly when there is an error in cutting out one character, the user corrects the cut-out position of the character by performing a predetermined gesture input through the tablet 1 and correct recognition is performed. The result can be obtained.

When the user inputs a gesture instructing erroneous recognition, data is sent from the tablet 1 to the gesture recognizing unit 6, and the gesture recognizing unit 6 recognizes the input gesture and recognizes its meaning. , And passes it to the instruction analysis unit 7. In the instruction analysis unit 7, the recognition result of the gesture recognition unit 6 is analyzed in relation to the input stroke group, and one character is cut out again.

A correction flowchart is shown in FIG.

First, in step S81, the designated position for gesture input is extracted. A character or a character string to be corrected is specified from the extracted position.

Next, in step S82, a stroke group to be newly made into one character is specified from the meaning of the gesture and its position in the specified character, and these are cut out as one character.

The processing up to this point is performed by the instruction analysis unit 7.

Next, the control is transferred to the character recognition section 5, and first,
In step S83, the data of the corresponding image is extracted and recognized from the data buffer 3 based on the cutout result.

Then, in step S84, the new recognition result is replaced with the previous recognition result.

In step S85, it is determined whether or not the remaining strokes remain. If it remains, the process proceeds to step S82. If not, step S
Proceed to 86.

In step S86, redisplay is performed.

Here, when an excessively combined error occurs as shown in FIG. 5, "shi" and "as shown in FIG.
The gesture recognition unit determines that they are to be separated, and the instruction analysis unit uses the position of the gesture and the result of the gesture recognition unit to analyze the first and second strokes. It is determined that each character is independent of the characters up to the eye, and the process shown in the flowchart of FIG. 8 is performed.

First, by extracting the designated position, the first character is separated, the first stroke is judged to be one character, and the character is cut out as one character. The data of the corresponding image is taken out from the data buffer and recognized as one character and is recognized and replaced with the previous recognition result. Then, because the data of the 2nd to 4th strokes remain unrecognized, the same process is performed from the cut-out of one character, and when all the data is recognized again, it is redisplayed. Become.

In addition, as shown in FIG.
Is recognized as the recognition result “11” and an error of excessive separation is caused, it is determined that the gesture recognition unit integrates by the integrated gesture connecting “1” and “1” shown in the figure, 1 from the gesture position and recognition result
It is determined that the first character and the second character are integrated by combining the first character and the second character, and the process shown in FIG. 8 is performed as in the case of excessive integration. First, the first stroke and the second stroke are cut out as one character, the data of the corresponding stroke is taken out from the data buffer 3 and recognized by the recognition unit, and is replaced with the previous recognition result. Therefore, since there is no remaining data, it is redisplayed as it is.

[0044]

As described above, the online handwritten character recognition device of the present invention cuts out one character based on the distance that the pen moves when the pen is away from the tablet and the time when the pen is apart from the tablet. A means, a means for displaying the input data in association with the result after recognizing after cutting out the character, and again recognizing by the position information of the pen in the specified range when there is an error in cutting out, Since it has a means to make corrections,
Character recognition with few erroneous recognitions is possible, and even if there is a recognition error, the error can be corrected by a simple instruction.

[Brief description of drawings]

FIG. 1 is a block diagram according to an embodiment of the present invention.

FIG. 2 is a flowchart of character segmentation. .

FIG. 3 is an example of character segmentation.

FIG. 4 is an example of a clipping error.

FIG. 5 is an example of display of a recognition result.

FIG. 6 is an example of excessive integration of cutouts. .

FIG. 7 is an example of excessive separation of cutouts.

FIG. 8 is a flowchart of correction.

[Explanation of symbols]

 1 tablet 2 character cut-out part 3 data buffer 4 display part 5 character recognition part 6 gesture recognition part 7 instruction analysis part

Claims (1)

[Claims] 1. An online handwritten character recognition device for collating characters based on position information of a pen sent from a tablet, the distance traveled when the pen is away from the tablet and the time when the pen is away from the tablet. Based on and, a means for cutting out one character, a means for recognizing after cutting out the character and displaying the result in correspondence with the input data, and a pen for the specified range An online handwritten character recognition device comprising means for re-recognizing and correcting the position information.