JPS6223351B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention relates to an optical character reading device, and more particularly to an optical character reading device in which rejects and errors during reading can be easily corrected.

Conventionally, there have been two main types of reject and error processing:

A method of making immediate corrections by keying in or re-entering the form at the stage of inputting it into an optical character reader (hereinafter abbreviated as OCR).

Reject: Even if an error occurs, it is stored in the output data and corrected at a later time.

However, with these methods, both the OCR output data and the reject image on the form or display device must be visually checked and corrected, which is inconvenient. The present invention was made in view of the above-mentioned drawbacks, and an object of the present invention is to accurately and efficiently perform OCR reject and error correction operations.

Next, the present invention will be explained in detail with reference to the drawings.

The drawing is a block diagram showing one embodiment of the present invention. 1 in the figure is a form. Form 1 has characters to be read written on it. 2 is OCR. OCR
2 is a device that optically reads handwritten or printed letters, numbers, and kana characters. 3 is Batsuhua. This buffer 3 temporarily stores data read by the OCR 2. 4 is a sound generating means. The voice generating means 4 is composed of a voice synthesizer 41 and a speaker 42, and generates a voice corresponding to the output data from the buffer 3 and also notifies rejects. 5 is a data input means. This data input means 5 is composed of a keyboard, key mat, or voice input device, and is used to correct rejects and errors. 6 is an editing means. This editing means 6 synthesizes and edits the data from the buffer 3 and data input means 4. 7 is an output terminal. 8 is
A signal line from the OCR 2 to the buffer 3, 9 a signal line from the buffer 3 to the audio generating means 4, 1
0 is a signal line from the buffer 3 to the editing means 6;
11 is a signal line from the data input means 5 to the editing means 6, and 12 is a signal line from the editing means 6 to the buffer 3.

Next, the operation of the above-mentioned device will be explained. First, all characters written on form 1 are read by OCR 2 for one page. This data is stored in buffer 3 via signal line 8. This data is then sent via signal line 9 to the sound generating means 4 according to a preset mode. The modes at this time are (1) character by character, (2) field by field, and (3) line by line. The speech synthesizer 41 drives the speaker 42 to produce a sound corresponding to the read data in one of the modes described above. At this time, the operator has the already read form 1 in hand, listens to the voice, and visually checks the form 1. If there is a reject or an error in the read data, the following operation is performed. First, when there is a redirect, the sound generating means 4 outputs a specific alarm sound (for example, beep (different from P)), and the editing means 6 enters a key-in waiting state. After confirming the form 1, the operator uses the data input means 5 to key in the corresponding data. The keyed-in data is uttered via the signal line 11, the editing means 6, the signal line 12, the buffer 3, and the signal line 9, and then proceeds to the next utterance. If an error occurs, follow the three modes described above and input all correct data from the data input means 5 after the unit is completed. That is, in the case of a field unit, after the utterance for one field is completed, if it is correct, the data input means 5
Press the "Correct" key provided on the screen to proceed to the next step.
Also, if there is an error, press the "Error" key,
Modify all the data in that field, such as ``Aiueo,'' and then press the ``End'' key to correct the data and proceed to the next field. The corrected data is edited by the editing means 6 and outputted from the output terminal 7.

According to the present invention, the operator only needs to concentrate his/her eyes on the form 1 and can listen to the read information, making confirmation quick and reliable. In addition, since there is less movement of the viewpoint, operator fatigue is reduced and it is convenient. In addition to reading characters, the system has a wide range of applications, such as being able to vocalize the pattern processing results of graphic processing and use them for confirmation and correction. In the above-described embodiment of the present invention, confirmation after reading was performed using a form, but it is also possible to display the information on a display device and compare it with audio. Furthermore, in this case, it is also possible to read and correct one character at a time, one field at a time, or one line at a time.

[Brief explanation of the drawing]

The drawing is a block diagram showing one embodiment of the present invention. 1...Form, 2...OCR, 3...Basshua,
4... Sound generation means, 5... Correction means, 6... Editing means.

Claims (1)

[Scope of Claims] 1. A buffer for temporarily storing read data read from a form, a sound generating means for generating sound corresponding to the read data, a data input means for inputting correction data, and An optical character reading device comprising: editing means for creating correct data by combining read data and corrected data. 2. The sound generating means generates an alarm sound when the read data includes rejects, and at that time, the editing means enters a state of waiting for data input from the data input means. The optical character reading device according to item 1. 3. The optical character reading device according to claim 1, wherein the data input means includes means for specifying whether the read data uttered is correct or incorrect.