JPS63279387A - Character recognizing device - Google Patents

Abstract

PURPOSE:To easily recognize and correct the character of a same form which are difficult to be discriminated, through the use of attribute information by displaying recognition candidate characters and corresponding attribute information together. CONSTITUTION:A storage means 8 storing attribute information of the character for recognition is provided. When a recognition result differs from a correct word, or its is not discriminated to be the correct character or not due to the character of the same form, an operator uses an input means 6 and instructs a control means 7 of the display of the recognition candidate characters to a display means 5. The control means 7 reads attribute information 12 corresponding to the recognition candidate characters from the storage means 8 and transmits them to the display means 5 with the recognition candidate characters. Consequently, the operator uses displayed attribute information 12 and he can select and input the correct character from the recognition candidate characters 11.

Description

[Detailed Description of the Invention] [Industrial Application Field] This invention relates to a character recognition device that recognizes many types of characters, and particularly to a character recognition device that can easily correct unrecognized characters and misread characters. It is.

[Prior Art] FIG. 2 is a block diagram showing a conventional character recognition device shown in, for example, "Mitsubishi OCRM2483-N Overview".
In the figure, (1) is a form, (2) is a scanning means, and (3)
(4) is a recognition dictionary storing reference patterns of characters to be recognized; (5) is a display means; (6) is an input means; and (7) is a control means.

FIG. 4 is an explanatory diagram of the screen display when the recognition result of the conventional character recognition device is corrected. In FIG. 4, (9)
is the recognition result, (10) is the pattern of the character to be corrected, (1
1) is a recognition candidate character for a character to be corrected.

Next, the operation will be explained. The characters on the form (1) are photoelectrically converted by the scanning means (2), and the input character pattern is sent from the scanning means (2) to the recognition means (3). Recognition means (3)
Then, the input character pattern is compared with the reference pattern in the recognition dictionary (4) to recognize the character, and the recognition result is sent to the control means (7).
).

If the recognition result is different from the correct character in 22, the recognition candidate character is displayed on the display means (5), and the operator selects and inputs the correct character using the input means (6).

However, when the types of characters to be recognized include kanji, hiragana, katakana, symbols, etc., multiple characters with exactly the same shape (hereinafter referred to as homomorphic characters) may be included.

Words including the preceding and following characters, without using grammatical information,
Correct recognition from only a single character pattern information requires a high level of skill, if not impossible.

Therefore, when a character recognition device recognizes such isomorphic characters, there is a high probability that the characters will not be recognized or will be misread, and correction input will be performed using recognition candidate characters.

Examples of isomorphic characters are “power” (kanji) and “power”.

(katakana), “工” (kanji) and “工” (katakana), “−” (ichi) and “−” (hyphen) and “−”
(negative sign) and “-” (long sound symbol), “he” (hiragana) and “he” (katakana), etc.

Figure 4 shows that the recognition result (9) for “power” (kanji) is unrecognizable (◆ in the figure), and the pattern of the character to be corrected (10) is unrecognizable (◆ in the figure).
) and recognition candidate characters (11) “Character” (Kanji) and “Power”
(Katakana) is displayed.

In this case, although there are subtle differences in the display fonts of the recognition results and recognition candidate characters, it would take a high level of skill, if not impossible, for the operator to identify all of these and manually select them correctly. I need.

[Problems to be Solved by the Invention] Conventional character recognition devices are configured as described above. This has the problem of causing extreme fatigue and making it easy to make incorrect inputs.

This invention was made to solve the above-mentioned problems, and aims to provide a character recognition device that can improve the operability of correction work and significantly reduce operator fatigue. do.

[Means for Solving the Problems] The character recognition device according to the present invention includes a storage device that stores attribute information of characters to be recognized, and displays recognition candidate characters and their corresponding attribute information on a display device. This is how it was done.

[Operation] The character recognition device according to the present invention displays isomorphic characters that are difficult to distinguish only from the font of the recognition candidate characters displayed on the display means by displaying the recognition candidate characters and the attribute information corresponding thereto. It can be easily identified, reducing operator fatigue and reducing human error.

[Embodiment] An embodiment of the present invention will be described below with reference to FIG. 1, in which the same parts as in FIG. 1 are given the same reference numerals.

In FIG. 1, (8) is a storage means that stores attribute information corresponding to each type of character to be recognized.

In addition, the attribute information (12) includes subset information such as "Kanji", "Katakana 1", "Hiragana 1", etc., as well as readings such as kanji consonance and symbol names such as "minus sign" and "hyphen". Can be done. In addition, by storing the attribute information of general characters that are not isomorphic characters as "none" so that they are not displayed on the screen, it is not necessary to determine whether or not they are isomorphic characters when displaying them, and the screen display is simplified. I can do it.

Ru.

FIG. 2 is an explanatory diagram of a screen display when correcting recognition results according to the present invention. In Figure 2, (9) to (11)
are the same as those in FIG. 4, and (12) is attribute information corresponding to the recognition candidate character (11).

Next, the operation will be explained based on FIGS. 1 and 2.

Since the operation up to displaying the recognition result on the display means (5) is the same as that of the conventional apparatus shown in FIGS. 3 and 4, the explanation will be omitted.

Here, if the recognition result is different from the correct character, or if it is isomorphic and it is unclear whether the character is correct or not, the operator uses the input means (6) to display the display means (5).
The control means (7) is instructed to display the recognition candidate characters on the screen.

At this time, the control means (7) reads attribute information (12) corresponding to the recognition candidate character from the storage means (8) and sends it to the display means (5) together with the recognition candidate character.

Then, the operator selects and inputs the correct character from the recognition candidate characters (11) using the displayed attribute information (12).

Figure 2 shows that the recognition result (9) for “power” (kanji) is unrecognizable (◆ in the figure), and the pattern of the character to be corrected (10)
, the recognition candidate characters (11) “power” (kanji) and “power#”
(Katakana) and attribute information (12) corresponding to these are displayed.

Here, the correct recognition candidate character (11) has attribute information (12).
), so you can easily select and input the characters.

In the above embodiment, the case where the recognition candidate character (11) and the attribute information (12) are displayed side by side has been explained, but the attribute information (12) can be expressed in color and the color of the recognition candidate character can be made to correspond to the attribute information. You can change it by

Furthermore, in the above embodiment, when displaying recognition candidate characters, attribute information is displayed side by side. This can speed up the discovery of unrecognizable isomorphic characters.

[Effects of the Invention] As described above, according to the present invention, recognition candidate characters and their corresponding attribute information are displayed together, and this attribute information is used to identify isomorphic characters that are difficult to identify. can be easily recognized and corrected, which has the effect of reducing operator fatigue and erroneous input.

[Brief explanation of the drawing]

Fig. 1 is a block diagram showing a character recognition device according to an embodiment of the present invention, Fig. 2 is an explanatory diagram of a screen display when the recognition result is corrected by the character recognition device, and Fig. 3 shows a conventional character recognition device. The block diagram in FIG. 4 is an explanatory diagram of a screen display when the recognition result is corrected by the conventional device. In the figure, (1) is a form, (2) is a scanning means, and (3)
is a recognition means, (4) is a recognition dictionary, (5) is a display means, (
6) is the input means, (7) is the control means, (8) is the storage means, (9) is the recognition result, (10) is the pattern of the character to be corrected, (11) is the recognition candidate character, and (12) is the attribute. It is information. In addition, in the figures, the same reference numerals indicate the same or equivalent parts. Agent Patent attorney Masuo Oiwa (and 2 others) Figure 1 Figure 2 Figure 12: Attribute information Figure 3 Figure 4 Procedure amendment (voluntary) 1. Indication of case Patent application No. 115127/1986 2
, Name of the invention Character recognition device 3, Person making the correction Representative Moriya Shiki 5, Target of correction Fig. 3

Claims (1)

[Claims] A scanning means for scanning and photoelectrically converting characters recorded on a form, a recognition dictionary storing a reference pattern of characters to be recognized, and character recognition by comparing an input character pattern from the scanning means with the reference pattern. a display means for displaying recognition results and recognition candidate characters by the recognition means, an input means for selecting and inputting characters from among the recognition candidate characters displayed on the display means, and the recognition results or recognition candidates. A character recognition device comprising a storage means storing attribute information to be displayed corresponding to each character when displaying the characters.