JP3270590B2 - Character recognition device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a character recognition apparatus for optically reading and recognizing characters written on an object to be read, such as a form or a general document.

[0002]

2. Description of the Related Art A character recognition device comprising an OCR or the like optically reads and recognizes characters written on an object to be read such as a form or a general document. This is to improve efficiency. FIG. 3 is a configuration diagram illustrating a conventional character recognition device. That is, the character recognition device 1 mainly includes a reading unit 2 for reading characters described on an object to be read, a control unit 3 that receives a character code obtained as a recognition result and outputs the character code, and a control unit. And a result output unit 4 for receiving the character code output from the unit 3 and informing the operator of the recognized character.

In order to use this character recognition device 1 to recognize characters written on an object to be read, first, a reading unit 2
For example, a form, which is an object to be read, is input to the input unit 21 of the printer, and a reflected light based on characters written on the form is converted into an electric signal by a photoelectric conversion unit 22 including a CCD sensor or the like. Next, the recognizing unit 23 cuts out an image of a certain area composed of the electric signal, extracts the characteristics of characters in the image, and compares the characteristics with a dictionary stored in advance to perform character-by-character recognition.

[0004] The recognition result is converted into a character code by the control unit 3.
The character code is sent to the result output unit 4 by the recognition result sending unit 33. The result output unit 4 receives this character code and outputs the character code as a character through a display unit 42 such as a display. Further, the character recognized by the character output unit 41 is output to paper or the like as necessary.

[0005] If, for example, the characters displayed on the display section 42 are erroneously recognized, the operator finds them and inputs the correct characters from the keyboard section 35 to rewrite the display on the display section 42. . For example, JP
In the optical character reading device disclosed in Japanese Patent Application Laid-Open No. 9-36878, an image signal of a read character and a result of character determination are combined and displayed on a display or the like so that an operator can easily find a portion that is erroneously recognized by the device. Has become.

[0006]

However, such a character recognition device has the following problems. That is, in this character recognition device, since the images of the recognized characters are displayed on a screen such as a display in an order corresponding to the scanning order, it is necessary for the operator to search for erroneously recognized characters that need to be corrected from the screen with the naked eye. There is.

In the optical character reading apparatus disclosed in Japanese Patent Application Laid-Open No. Sho 59-36878, an image signal of a read character and a result of character determination are combined and displayed on a display or the like. Although it is easy to find out whether or not it was recognized as a character, for example,
Characters of the same shape but different character types, such as katakana “ka” and kanji “power” (chichi), are similar in display, so that even if they are erroneously recognized, there is a good chance that the operator will miss it.

For this reason, it is necessary for the operator to visually check the display on the display to determine whether or not the character can be discriminated, and also to check the difference in the character type. Will be required. Therefore, an object of the present invention is to provide a character recognition device that can easily find misrecognized characters.

[0009]

SUMMARY OF THE INVENTION The present invention relates to such a section.
This is a character recognition device made to solve the problem.

That is, this character recognition device is
Optically read the characters written on the
A reading unit for performing character recognition based on
Outputs the recognition result obtained by the
Corrected characters input by the operator at the time of recognition
As a voice signal corresponding to the character in the recognition result.
A control unit having an audio signal generating means for generating a signal;
Notify the operator of the recognition result sent from the
Output the audio signal sent from the signal generator as audio
And a result output unit having an audio output unit for
And if the operator enters a correction character,
The signal generating means detects a punctuation mark immediately before the corrected character, and
Words starting with the character following the punctuation of
Voice from beginning of character string in clause or paragraph
The signal is output again as audio.

[0011]

An audio signal corresponding to the recognized character is transmitted from an audio signal generation means provided in the control unit to the result output unit, and the audio signal is output as a sound in the audio output unit provided in the result output unit. Thus, the recognized character can be notified to the operator as voice. Further, the voice signal containing the corrected character input by the operator, that is , the punctuation mark immediately before the corrected character is detected, and the character next to the punctuation character is detected.
From the beginning of the word, phrase, or paragraph
The sound signal is played again from the beginning of one of the character strings.
By outputting as a voice, it is possible to include
Character strings can be easily checked and efficient
It will be possible to carry out regular work.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the character recognition device of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram illustrating a character recognition device according to the present invention. The character recognition device 1 mainly includes a reading unit 2 for reading a character written on an object to be read, a control unit 3 that obtains a recognition result from the reading unit 2 and outputs a character code, and a character code from a control unit 3. Result output unit 4 that informs the operator of the character that has been received and recognized
The control unit 3 further includes an audio signal generation unit 3
4 is provided, and the sound output unit 43 is provided in the result output unit 4.

The same reference numerals in FIG. 1 as those in FIG. 3 denote the same components, and the following description will focus on new components. That is,
The control unit 3 of the character recognition device 1 includes a readable and writable memory 31 for temporarily storing a character recognition result sent from the recognition unit 23 of the reading unit 2. Thus, the recognition result is sent to the recognition result sending unit 33 and the audio signal generating unit 34, respectively.

The correction unit 32 of the control unit 3
A character which needs to be corrected is detected from the character string data stored in No. 1 and this character is corrected and the corrected character string data is sent to the audio signal generator 34.

The audio signal generator 34 receives the character string data stored in the memory 31, generates an audio signal corresponding to the character, and sends it to the result output unit 4. The sound output unit 43 provided in the result output unit 4 is composed of, for example, a speaker, and converts the sound signal sent from the sound signal generation unit 34 into sound to notify the recognized character to the operator as sound. . For this reason, the operator can check the recognized character by looking at the display unit 42 including the display of the result output unit 4 and at the same time, can hear the character as voice.

For example, if a character cannot be read due to incomplete reading, the character is not displayed on the display or a display indicating that reading is not possible is performed, and the operator finds this and determines erroneous recognition. Also, for example, katakana “ka” and kanji “power” (chikara)
Since it is difficult to determine characters having the same shape but different character types only by displaying on the display, the determination is made based on the voice from the voice output unit 43 generated simultaneously with the display.

As described above, the operator operates the character recognition device 1
Is confirmed by the voice from the voice output unit 43 together with the display on the display unit 42, and corrects by inputting the correct character from the keyboard unit 35 when the recognized character is incorrectly recognized. I do. The corrected character is displayed on the display unit 42, and an audio signal including the corrected character is output again as audio from the audio output unit 43.

Next, a series of operations of the character recognition device 1 will be described with reference to the flowchart of FIG. Note that FIG.
Reference numerals not shown in FIG. 1 refer to FIG. First, the recognition result by the reading unit 2 is stored in the memory 31, and the character string data of the recognition result is sent to the recognition result sending unit 33 and the audio signal generating unit 34.

The character string data is sent from the recognition result sending unit 33 to the display unit 42, so that the recognized characters are displayed on a display or the like. At the same time as the display, the audio signal generator 34 generates an audio signal corresponding to the character string data and sends it to the audio output unit 43 so that the character is output from a speaker or the like as audio.

The operator confirms the recognized characters based on the display display and the voice from the speaker, and sends a signal to the control unit 3 to stop the voice output by operating the keyboard unit 35 when there is an erroneous recognition. The control unit 3
When this signal is received, the determination in step 2a is changed to "Y
As es, the audio output in the next step 2b is interrupted.

Thereafter, in the next step 2c, the operator corrects the erroneously recognized character by using the keyboard unit 35. With this correction, the correction unit 32 rewrites the erroneously recognized portion of the character string data stored in the memory 31 and sends the character corrected in step 2d to the audio signal generation unit 34.

Next, in step 2e, the voice signal generator 34 extracts character string data after the corrected character from the memory 31 with the sent corrected character as a starting point. In addition, as the extraction of the character string data, a punctuation mark immediately before the correction character is detected, and character string data including the correction character is extracted starting from the character following the punctuation mark, or a sentence including the correction character, Any of a word, a phrase, and a paragraph may be extracted.

Next, in the next step 2f, the previously extracted character string data is converted into a corresponding audio signal, and the audio signal is sent to the audio output unit 43. And step 2g
As a resumption of the voice output, the voice output unit 43 outputs a voice based on the voice signal, displays the corrected character on a display, and outputs a voice signal including the corrected character again to notify the operator.

Thus, the operator confirms the corrected character, and after confirming, confirms the next recognized character string. By repeating this series of flows, recognition of recognized characters and correction of erroneous recognition can be performed accurately.

[0025]

As described above, according to the character recognition device of the present invention, the following effects can be obtained. That is, the recognition result is displayed on a display unit such as a display, and is output as voice from a voice output unit such as a speaker, so that an erroneously recognized character can be easily found. In particular, when confirming characters having the same shape but different character types, even if the characters cannot be easily found only on the display, they can be reliably found by listening to the voice. In addition, when the operator inputs a correction character, the character string immediately before that includes the correction character is output again by voice, so that the operator can check the correction character without having to read back the character string himself, thereby improving efficiency. Good correction work can be performed.

[Brief description of the drawings]

FIG. 1 is a configuration diagram illustrating a character recognition device of the present invention.

FIG. 2 is a flowchart illustrating a series of operations of the character recognition device of the present invention.

FIG. 3 is a configuration diagram illustrating a conventional character recognition device.

[Description of Signs] 1 Character recognition device 2 Reading unit 3 Control unit 4 Result output unit 34 Audio signal generation unit 35 Keyboard unit 42 Display unit 43 Audio output unit

──────────────────────────────────────────────────続 き Continuation of the front page (56) References JP-A-5-189600 (JP, A) JP-A-59-216286 (JP, A) JP-A-63-136289 (JP, A) 72643 (JP, U) (58) Fields investigated (Int. Cl. ⁷ , DB name) G06K 9/00 G06K 9/03 G10L 13/00

Claims (1)

(57) [Claims] A reading unit for optically reading a character written on an object to be read and performing character recognition based on the read image; outputting a recognition result obtained by the reading unit; At this time, the correction character input by the operator is output as the recognition result, and the character corresponding to the character in the recognition result is
A control unit having an audio signal generating unit for generating an audio signal , and a recognition result sent from the control unit is notified to the operator, and the audio signal sent from the audio signal generating unit is transmitted to the operator.
A character output device having a voice output unit for outputting the voice as a voice.
The number generating means detects a punctuation mark immediately before the correction character, and
Words and phrases containing modified characters starting from the character following the reading
Or the sound from the beginning of any character string in the paragraph
A character recognition device for outputting a signal as voice again .