JPS6180477A - Fair-copying device of document - Google Patents

Abstract

PURPOSE:To obtain a fiar copy having the same layout as input characters by storing the picture of an input document once to a picture memory part to display it, segmenting an optional character out of a displayed picture and replacing a pattern with the area of the segmented character. CONSTITUTION:A handwrittern document is binary coded at a picture input part 5 and stored in the picture memory part 6 and then displayed at a picture display part 7. A character segmenting part 8 segments the rectangular patterns successively from the part 6 as the character patterns to be recognized. A character recognizing part 9 checks whether or not >=N pieces of picture elements are continuously including a noticed picture element for each picture element of the character pattern to be recognized and segmented by the part 8. Then the part 9 sets the direction codes. The coupling property of each picture element is checked for each direction code for the extraction of strokes. Then the characters are recognized from the features such as the number of strokes, the length and position of the direction code, etc. The result of this character recognition and the character pattern are replaced with the position of the character pattern to be recognized and segmented from the part 6. Then the contents of the part 6b is displayed at the part 7.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention recognizes each character of a document printed in type or handwritten, and replaces the recognition target character with the recognition result character. This invention relates to a document formatting device that can format documents.

Configuration of conventional examples and their problems Conventional document inscription devices recognize character patterns to be recognized cut out from documents, send the recognition results to a display device,
Display devices display information in a fixed display area. An example is shown in FIG.

Reference numeral 1 is an image input unit for inputting a document containing characters to be recognized.

2 is a character cutting section which cuts out the character pattern to be recognized inputted in 1 into a rectangular shape. Figures 2a and b show the cut out characters. 3, for each pixel of each character extracted by the character recognition unit, determine whether or not N or more pixels (N is a preset source) including the pixel of interest are connected in the direction indicated by the arrow in FIG. 2 C. Then, the connectivity of each pixel is checked for each set direction code, strokes are extracted, and character recognition is performed using features such as the number of strokes, direction code, length, and position.

The numbers in FIG. 2a and b indicate the extraction results of each stroke and direction code.

A display section 4 displays the recognition results obtained by the character recognition section 3 at a predetermined location.

The document formatting device configured as described above has the disadvantage that it is difficult to format the input document according to the layout because the recognition result is displayed on the display device regardless of the position of the recognized character.

OBJECTS OF THE INVENTION The present invention improves the above-mentioned drawbacks of conventional document formatting devices, and an object of the present invention is to provide a document formatting device capable of formatting in the same layout as the character layout of an input document.

Structure of the Invention The document fairing device of the present invention stores an image of an input document once in an image storage unit and displays it, cuts out and recognizes arbitrary characters in the displayed image from the image, and recognizes the character pattern cut out from the recognized character area. The above purpose is achieved by replacing it with .

DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 3 is a block diagram of an embodiment of a document fairing device according to the present invention. Reference numeral 5 denotes an image input section, into which a document to be transcribed is inputted as binary data. Reference numeral 6 denotes an image storage section, which temporarily stores image data input from the image input section 6. 7
An image display section displays image data stored in the image storage section 6. A character cutting section 8 cuts out a rectangular character to be recognized from the image data stored in the image storage section 6. Reference numeral 9 denotes a character recognition unit which performs character recognition using the recognition target character pattern obtained by the character cutting unit 8, and replaces and displays the recognition result at the position of the recognition target character pattern cut out from the character pattern image storage unit 6. By doing this, you can make a fair copy.

The document fairing device configured as described above will be explained in detail using a handwritten document shown in FIG.

The handwritten document is binarized by the image input section 5, stored in the image storage section 6, and displayed on the image display section 7 as shown in FIG. The character cutting section 8 sequentially cuts out rectangular patterns R from the image storage section 6 as character patterns to be recognized, as shown in FIGS. 6a and 6b.

In the character recognition unit 9, for each pixel of the recognition target character pattern cut out by the character cutting unit 8, N or more (N is preset) pixels including the pixel of interest are detected in the direction indicated by the arrow C in FIG. 6. Check whether they are continuous, set a direction code, check the connectivity of each pixel for each set direction code, extract strokes, and use characteristics such as the number of strokes, direction code, length, position, etc. The recognition result character pattern is replaced with the position of the recognition target character pattern cut out from the image storage section 6, and the contents of the image storage section 6 are displayed on the image display section 7 as shown in FIG. indicate.

In the document fairing device configured as described above, image data of a document inputted from the image input section 6 is once stored in the image storage section 6 and displayed, and a character pattern to be recognized is cut out from the stored image data and recognized. However, since the recognition result character pattern is replaced with the recognition target character pattern, the layout of the document does not change at all before and after cleansing, and the document can be cleansed while maintaining the image of the document before cleansing.

Although this embodiment has only described the fair copying of characters, this embodiment can also be applied to the fair copying of graphs, Table 2 figures, etc. by replacing the fair copy results with the graphs, Table 9 figures, etc. that are the subject of fair copying. It goes without saying that the same effect can be obtained.

Effects of the Invention According to the present invention, in a document formatting device that cuts out and recognizes each character pattern of a handwritten or printed document and formats it,
By replacing the character pattern resulting from character recognition with the character pattern to be recognized, the document can be formatted without changing the layout of the document to be formatted.

[Brief Description of the Drawings] Figure 1 is a block diagram of an example of a conventional document inscription device;
FIG. 2 is an explanatory diagram of a conventional document formatting device, FIG. 3 is a block diagram of the structure of a document formatting device according to an embodiment of the present invention, and FIG. 4 is a diagram showing an example of a document to be formatted that is input to the device. , FIG. 5 is a diagram showing the display screen in the image display section of the above document, FIG. 6 is a diagram showing a cutout of the character pattern in the same example, and FIG. 7 is a diagram showing the result of the fair copying of the document in the same example. be. 6... Image input section, 6... Image storage section, 7... Image display section, 8... Character cutting section, 9......・Character recognition section. Name of agent: Patent attorney Toshio Nakao and 1 other person No. 1
Figure 1? 3 4 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7

Claims (1)

[Claims] an image input unit that inputs an image including printed or handwritten characters; an image storage unit that stores the input image data; a character cutting unit that cuts out a rectangular character pattern to be recognized from the stored image; and the character cutting unit. a character recognition unit that recognizes the recognition target character pattern obtained by the recognition target character pattern and replaces the recognition result character pattern in the position of the recognition target character pattern in the image storage unit; and a display unit that displays the image storage unit. A document formatting device characterized by: