JPS5842513B2 - Real-time handwritten character recognition device - Google Patents

Description

[Detailed Description of the Invention] The present invention provides a real-time handwritten character recognition device that automatically switches to Kanji-hiragana mode when the number of strokes is large and uses a Kanji-hiragana dictionary as a recognition dictionary. This invention relates to a handwriting recognition device.

Since Japanese sentences use a wide variety of characters such as kanji, hiragana, katakana, and alphanumeric characters, it is extremely difficult to recognize a mixture of these characters.

For example, the kanji character ``工'' and the katakana character ``工'' cannot be distinguished.

Therefore, in order to recognize these characters without error, it is necessary to tell the recognition unit in advance the type of character to be input using a function key or the like.

In the present invention, teaching the type of character to be input is called recognition mode.

However, since changing the recognition mode is a very unnatural action for humans, they often forget this action and input a different type of character to achieve recognition.

Such input errors usually cannot be recovered from until the operator notices the input error.

The present invention focuses on the fact that Japanese sentences contain more kanji characters than katakana or alphanumeric characters, and the number of input strokes for non-kanji characters is 6 or less. The object of the present invention is to provide a real-time handwritten character recognition device in which the recognition mode is automatically switched to the kanji hiragana mode.

Therefore, the real-time handwritten character recognition device of the present invention
a tablet input device, an input means for specifying a recognition mode for handwritten input characters inputted by the tablet input device to one of a kanji hiragana mode, a katakana mode, and an alphanumeric mode; and a kanji hiragana mode. a dictionary, a katakana dictionary, an alphanumeric dictionary, a feature creation means for creating features of handwritten input characters, a stroke number detection means for detecting the number of strokes of the handwritten input characters, and handwriting detected by the stroke number detection means. a comparison means for checking whether the number of strokes of the input character is equal to or greater than a predetermined value; a recognition mode holding means for storing the recognition mode designated by the input means; and a comparison means for determining whether the number of strokes of the handwritten input character is a predetermined value. mode change control means for changing the recognition mode stored in the recognition mode holding means to a kanji hiragana mode when it is determined that the recognition mode holding means is above; and a matching means; A groove is configured to match the characteristics of the handwritten input characters created by the means with a dictionary corresponding to the recognition mode stored in the recognition mode holding means among the kanji hiragana dictionary, katakana dictionary and alphanumeric dictionary. It is characterized by being bottomed out.

Hereinafter, the present invention will be explained with reference to the drawings.

FIG. 1 is a diagram showing an example of the tablet input surface used in the present invention, FIG. 2 is a diagram showing an actual example of handwritten character input, and FIG.
The figure is a block diagram of one embodiment of the present invention, and FIG. 4 is a diagram showing an example of automatic recognition mode change.

In the figure, 1 is a tablet, 2 is a manuscript paper, 3 is a recognition mode change key, 4 is a stylus pen, 5 is an input control circuit, 6 is a relative position matrix creation circuit, 7 is a matching circuit, and 8 is a mode change control circuit. , 9 is a recognition mode holding circuit;
10 is a stroke number detection circuit, 11 is a stroke number table, 12 is a comparison circuit, and 13 is a dictionary.

As shown in FIG. 1, when inputting characters, a manuscript paper 2 is placed on the input surface of a tablet 1, and Japanese characters are input using an attached stylus pen 4.

At this time, coordinate point series information and up/down information corresponding to the movement of the stylus pen are sent to the recognition device.

FIG. 2 shows an example of actual character input, such as, ``We are faced with the need to input Japanese into a computer.

”, the operator must perform the following operations.

(1) At point P1, press the kanji/kana part of the recognition mode change key 3.

(ii) Write "We Japanese".

(111) At point P2, press the katakana part of the recognition mode change key 3.

(V) Write “computer”.

M At point P3, press the kanji/kana part of recognition mode change key 3.

(vi) I am faced with the need to input Japanese into r.

”. Characters are input into the recognition device as described above, but in actual character input operations, points P1. P2
Input errors at point 23 are far more common than input errors at point 23, and all sentences with "less than a computer" are recognized and processed in katakana mode, often resulting in misreading.

The present invention has been made to prevent such misreading.

FIG. 3 is a block diagram of one embodiment of the present invention.

The input control circuit 5 performs operations such as cutting out characters, extracting representative points, and detecting recognition modes.

The relative position matrix creation circuit 6 creates a relative position matrix between representative points.

The matching circuit 7 compares the characteristics of the character type in the dictionary with the characteristics created by the relative position matrix creation circuit 6 to determine the type of input character.

The dictionary 13 is divided into a kanji hiragana group, a katakana group, and an alphanumeric group, and each group is further divided into subgroups according to the number of strokes.

When the recognition mode information and stroke count information are input, the characteristics of all the corresponding character types are sent to the matching circuit 7 and compared with the characteristics of the input character.

The mode change control circuit 8 is for forcibly changing the recognition mode to the kanji hiragana mode when receiving the mismatch signal.

The recognition shade holding circuit 9 holds the previous recognition mode until a new recognition mode is input or until change information is received from the mode change control circuit 8.

The stroke number detection circuit 10 detects the number of strokes of an input character.

The stroke count table 11 stores the upper limit of the number of strokes for katakana and alphanumeric characters.

The comparison circuit 12 compares the output of the stroke number detection circuit 10 and the output of the stroke number table 11, and if the two do not match, outputs a mismatch signal and activates the mode change control circuit 8.

To be more specific, the stroke count table 11 outputs the numerical value 6 when the recognition mode is katakana mode or alphanumeric mode.

In this case, the comparison circuit 12 outputs a mismatch signal when the output from the stroke number detection circuit 10 is a numerical value of 7 or more.

FIG. 4 is a diagram showing an example of automatic recognition mode change according to the present invention.

The operator said, ``We Japanese people need to input Japanese into computers...''

'', as shown in Figure 2, first set the recognition mode to kanji hiragana mode and enter ``J'' for us Japanese.

During this time, kanji hiragana mode information is input to the dictionary 13 as the recognition mode, and the kanji hiragana group is set as the recognition dictionary.

If the operator fills in one computer after another,
Press the katakana part of the recognition mode change key 3 and write "computer".

In this case, the katakana mode is input to the dictionary 13 as the recognition mode, and the katakana group becomes the recognition dictionary.

Originally, it would be the point P where the entry for “computer” ended.
In step 3, press the kanji/kana part of recognition mode change key 3 to switch to kanji mode, but if you forget this, the character ``nihon'' will be recognized using the katakana group as a recognition dictionary, and as a result, Misreading occurs.

However, when the character "word" is input, this character becomes 7
Since the number is larger than a stroke, the recognition mode is automatically switched to kanji hiragana mode, and characters below "word" are read correctly.

As is clear from the above explanation, the present invention has the remarkable effect of significantly reducing misreading of input characters, since most Japanese sentences are written in kanji flat letters. I can play.

[Brief explanation of the drawing]

FIG. 1 is a diagram showing an example of a tablet input surface used in the present invention, FIG. 2 is a diagram showing an actual example of handwriting input, FIG. 3 is a block diagram of one embodiment of the present invention, and FIG. The figure is a diagram showing an example of automatic recognition mode change. 1...tablet, 2...manuscript paper,
3... Recognition mode change key, 4... Stylus pen, 5... Human control circuit, 6...
... Relative position matrix creation circuit, 7 ... Matching circuit, 8 ... Mode change control circuit, 9 ...
...Recognition mode holding circuit, 10... Stroke number detection circuit, 11... Stroke number table, 12...
...Comparison circuit, 13... Dictionary.

Claims (1)

[Claims] 1 The tablet input device and the recognition mode for handwritten input characters input by the tablet input device are set to one of Kanji hiragana mode, katakana mode, and alphanumeric mode.
an input means for specifying a recognition mode, a kanji hiragana dictionary, a katakana dictionary, an alphanumeric dictionary, a feature creation means for creating features of handwritten input characters, and detecting the number of strokes of handwritten input characters. a number of strokes detection means, a comparison means for checking whether the number of strokes of the handwritten input character detected by the number of strokes detection means is greater than or equal to a predetermined value, and a recognition mode holding means for storing the recognition mode specified by the input means. and a mode change control means for changing the recognition mode stored in the recognition mode holding means to a kanji hiragana mode when the comparison means determines that the number of strokes of the handwritten input character is equal to or greater than a predetermined value; means, and the matching means stores the features of the handwritten input characters created by the feature creation means and the kanji-hiragana dictionary, the katakana dictionary, and the alphanumeric dictionary, which are stored in the recognition mode storage means. A real-time handwritten character recognition device characterized in that it is configured to perform matching with a dictionary corresponding to a recognition mode.