JPH03268084A - Optical character reader - Google Patents

Abstract

PURPOSE:To read an undefined document with high accuracy by outputting the read undefined document after laying out in a prescribed format. CONSTITUTION:A control part 1 is provided together with a scanner part 2, a recognizing part 3, a recognizing result store part 4, a layout processing part 5, a key word dictionary part 6, a layout information store part 7, a CRT 8, a key input part 9, and a printer 10. Then a key word necessary for layout of a read document is previously registered together with the priority corresponding to the key word and the layout information. A read undefined document is automatically laid out and outputted in a prescribed format. Thus it is possible to omit the editing processing to be carried out by an operator and to improve the reading efficiency of the undefined document.

Description

DETAILED DESCRIPTION OF THE INVENTION 5. OBJECTS OF THE INVENTION (Industrial Application Field) The present invention relates to an optical character reading device for reading documents on a form, and particularly relates to a formatting process for a read document.

(Prior Art) Conventionally, the format of a document read by an optical character reading device is determined in advance, and the document is written within a frame printed on a form. Therefore, when an optical character reading device reads a document formatted in this way, it formats the read document as described above.
It was supposed to be output in .

When such a conventional optical character reading device reads an irregularly shaped document with no fixed format, it is not possible to output the irregularly shaped document with characters placed at the scanned image position. .

(Problems to be Solved by the Invention) As mentioned above, when a conventional optical character reading device reads an amorphous document with no fixed format, the output document is evil. It remained nothing more than a document. Therefore, in order to convert the document into a predetermined format, the operator had to read the document into a virgin computer or the like and then perform key operations or the like to read it again.

SUMMARY OF THE INVENTION In order to eliminate the above-mentioned drawbacks, the present invention aims to provide an optical character reading device that can layout and output a read irregularly shaped document in a predetermined format.

[Structure of the invention]

(Means for Solving Problems with Problems) The present invention provides an optical character reading device that photoelectrically converts characters on a form to read and recognize the characters. a registration means, a layout information registration means for registering layout information for determining the format of the read and recognized document, and editing the read and recognized document based on editing information registered in the registration means; The document editing means includes a document editing means for setting the position, columns, and format of a text so as to have a predetermined format based on the layout information registered in the layout information registration means.

(Operation) In the optical character reading device of the present invention, the editing information registration means registers editing information for editing the read and recognized document. The layout information registration means registers layout information for determining the format of the read and recognized document. The document editing means edits the read and recognized document based on the editing information registered in the registration means, and edits the document so that it has a predetermined format based on the layout information registered in the layout information registration means. Set the position, columns, and format.

(Example) Hereinafter, an example of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of the optical character reading device of the present invention. Reference numeral 1 denotes a control unit that controls various parts of the apparatus described below to read documents, control layout processing of the read documents, and the like. 2 is a scanner unit that photoelectrically converts and reads a document on a form; 3 is a recognition unit that recognizes characters from the character image read by the scanner unit 2; 4
5 is a recognition result storage unit that stores the recognition results for one sheet recognized by the recognition unit 3, and 5 is a layout processing unit that searches the recognition result storage unit 4, extracts a keyword, and sets the priority of this keyword. After searching for keywords from the keyword dictionary section 6, the recognized document is laid out and edited into a predetermined format based on the search priority and layout information input from the layout information storage section 7. 6 is a keyword dictionary section that stores the relationship between keywords (a type of editing information) and priorities, and 7 is a layout information storage that stores layout information such as horizontal writing, vertical writing, columns, number of characters in one line, and line spacing. 8 is a CRT that displays various information such as read images, recognition results, and layout results; 9 is a key input unit that manually inputs various setting information; and 10 is a printer that outputs the read document edited in a predetermined format. There is.

Here, the key human power section 9, layout processing section 5, and keyword dictionary section 6 function as editing information registration means, the key human power section 9, layout processing section 5, and layout information storage section 7 function as layout information registration means, The unit 5 constitutes a document editing means.

Next, the operation of this embodiment will be explained. The scanner unit 2 reads a document in which a document is written in an irregular form, such as the one shown in FIG. The recognition unit 3 extracts and recognizes character parts from the input image information, and stores the recognition results for one sheet in the recognition result storage unit 4. Next, the layerer I processing unit 5 searches the recognition result storage unit 4 to find characters (words) that serve as keywords. However, it is assumed that this keyword is set in advance from the key personnel section 9 to the layout processing section 5. Next, the layout processing section 5 refers to the keyword dictionary section 6 and specifies the priority order of the found keywords. That is, when reading the example form shown in FIG.
is extracted, and with reference to the stored contents of the keyword dictionary section 6 as shown in FIG. Search for

After that, the layout processing unit 5 reads the recognition results including the keyword from the recognition result storage unit 4 in units of sentences (for example, "weather overview"), and displays the priority order of the keywords included in the sentences as shown in FIG. 2(B). In addition to rearranging the sentences as shown in FIG. After that, it is output to the printer 10.

The printer 10 prints and outputs one sheet of the read document, which has been formatted and read in a predetermined format, as shown in FIG. 2(B), for example, on recording paper. The layout processing section 5 displays the amorphous document stored in the recognition and recognition result storage section on the CRT 8, and also displays the processing results applied to this document on the CRT 8 as appropriate.

Here, it is assumed that keywords and their priorities are registered in advance in the keyword dictionary section 6 from the key personnel section 9 by the operator via the layout processing section 5, for example, as shown in FIG. Further, it is assumed that various layout processing sections such as horizontal writing, vertical writing, columns, number of characters in ] lines, and line spacing are stored in advance in the layout information storage section 7 from the key manual section 9 by the operator. It should be noted that the registered keywords, their priorities, and information on Layer 1 to Layer 1 are appropriately displayed on CRT 8 by Layer 1 and processing section 5 so that the operator can confirm them.

FIG. 4 is a flowchart showing the operation of the apparatus shown in FIG. First, in step 401, a single document is read by scanner section 2, and in step 402, the read characters and images are recognized by recognition section 3, and the recognition result is stored in recognition result storage section 4. Next step 4
At step 03, the layerer 1-processing unit 5 extracts keywords from the stored recognition results and determines whether the keywords exist or not.
It outputs 0 and proceeds to step 405, and if there is, proceeds to step 404. In step 404, the layerer 1 to processing unit 5 lay out the recognition results based on the priority order of the extracted keywords and the layout information, convert them into a predetermined format, output them to the printer 10, and proceed to step 405 in nine steps. With the knob 405, the printer 10 converts the given take into print data, and then prints it on recording paper and outputs it. Thereafter, the process returns to step 401 to read the next form.

FIG. 5 is a diagram showing an example of the output result by another former when the apparatus shown in FIG. 1 reads the irregular document shown in FIG. 2(A). (A> is an example of horizontal writing and multi-column designation, and (B) in the figure is an example of vertical writing and multi-column designation.

According to this embodiment, if a keyword for reading a document and the corresponding priority order and selection information are registered in advance in the device, the read irregular-form document can be automatically transferred to the layerer. Thus, a read document in a predetermined format can be output, the editing process by an operator that is previously required can be omitted, and the reading efficiency of irregularly shaped documents can be significantly improved.

〔Effect of the invention〕

As described above, according to the optical character reading device of the present invention, it is possible to output a read irregularly shaped document in a predetermined format as a layerer.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of the optical character reading device of the present invention, and FIG. 2 shows an irregularly shaped document read into the device shown in FIG. Figure 3 is a diagram showing a document example; Figure 3 is a schematic diagram showing the relationship between keywords registered in the keyword dictionary section shown in Figure 1 and their priorities; FIG. 5 is a diagram showing another example of a read document having a predetermined format output from the apparatus of FIG. 1. 1... Control unit 2... Scanner unit 3... Recognition unit 4... Recognition result storage unit 5... Layout processing unit 6... Keyword dictionary unit 7... Information Storage section 8...CRT 9...Key human power section 10...Printer

Claims (1)

[Claims] In an optical character reading device that photoelectrically converts and reads characters on a form, the editing information registration means registers editing information for editing the read and recognized document, and determines the format of the read and recognized document. layout information registration means for registering layout information for
The read and recognized document is edited based on the editing information registered in the registration means, and the position and column of the text are changed to have a predetermined format based on the layout information registered in the layout information registration means. 1. An optical character reading device comprising: document editing means for setting a set and format.