JPH04106670A - Document picture processor - Google Patents

Abstract

PURPOSE:To reduce the processing manpower required by the title processor by recognizing characters and graphics which have been handled as image information and converting the characters and graphics into suitable code data. CONSTITUTION:An area dividing section 105 divides inputted image information into a character area, graphic area, and image area by finding the black picture element density of the areas of an inputted picture other than the blank area extracted by means of a blank area extracting section 104. A character area processing section 106 performs extraction of character strings, segmentation of one character, and recognition of a segmented character in the divided character area and a graphic area processing section 107 performs recognition after extracting geometrical figures and characters. Then an image area processing section 108 leaves the image area as image information or performs a compressing or contracting process on the image information and a reconstituting section 109 reconstitutes the area converted into the code data and the area of the image data on paper. In addition, a picture outputting section 110 outputs the reconstituted document information. Therefore, a document can be preserved without manual aid.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention separates and extracts character areas, figure areas, and image areas from document information captured in the form of image information,
The present invention relates to a document image processing device that converts information included in each area into code data suitable for the information, then reconfigures and outputs the code data.

[Prior Art] Generally, when document information written on paper is stored, an image captured by an image scanner or the like is treated as image information and is stored in an external storage device or the like. Also,
If only a character region is extracted, then the character region is subjected to character recognition, character coded, and saved, the user needs to manually specify the character region for the input document image.

[Problems to be Solved by the Invention] As described above, the type that saves in the form of image information requires a huge amount of storage capacity, and also cannot perform editing work such as rewriting part of the document. The type that specifies areas requires a human being to be present at all times and give instructions, which is time-consuming.

SUMMARY OF THE INVENTION The present invention aims to solve the above-mentioned problems by separating an inputted document image into a text area, a diagram area, and an image area without relying on humans. In this area, the object is to provide a device that recognizes characters and geometric figures, converts them into code data suitable for each type of information, and stores the document.

[Means for Solving the Problems 1] The document image processing device of the present invention includes an image processing unit that captures as image information a document including at least one of text, diagrams, and image areas, and a A preprocessing unit removes noise from image information and binarizes it, a blank area extraction unit extracts blank areas from the data processed by this preprocessing unit, and a black pixel density is calculated for areas other than blank areas. an area dividing unit that divides the image information into a character area, a diagram area, and an image area; a character area processing unit that recognizes characters in the character area;
A diagram area processing unit that recognizes geometric figures and characters in the diagram area, an image area processing unit that processes image information in the image area, a reconstruction unit that reconstructs the data from each of these processing units, and a reconstruction unit that processes the image information in the image area. The present invention is characterized by comprising an image output unit that outputs structured document information.

[Example] The present invention will be explained below based on the drawings.

FIG. 1 is a block diagram showing the configuration of a document image processing apparatus according to the present invention. An image input unit 101 inputs a document image as image information, and uses a scanner, a camera, or the like. When using an optical disk or the like on which images are stored in advance, the playback device is compatible with this. 1
02 is an image memory that temporarily stores captured image information. 103 is a preprocessing unit that removes noise contained in image information and binarizes it. To remove noise,
Remove isolated noise using a median filter or the like. If the human image is tilted, the tilt angle is corrected in this part to make later processing easier. Reference numeral 104 denotes a blank area extracting unit that extracts a blank area that normally separates these areas in order to separate and extract the character area, figure area, and image area. The method for extracting the blank space will be described later.

Reference numeral 105 denotes an area dividing unit that divides the input image information into a character area, a diagram area, and an image area by determining the black pixel density of areas other than the blank area extracted by the blank area extracting unit 104. It is. 106
is a character area processing unit that extracts a character string, cuts out a - character, and recognizes the cut out characters within the divided character area. Reference numeral 107 is a diagram area processing unit that performs recognition after extracting geometric figures and characters in the diagram area. Reference numeral 108 denotes an image area processing unit that processes a portion determined to be an image area as image information or compresses it. 10
Reference numeral 9 denotes a reconstruction unit that reconstructs the area converted into code data and the area of image data on the paper. Reference numeral 110 denotes an image output unit that outputs reconstructed document information, and specifically includes a printing device, a display device, and an external storage device.

Next, a method for extracting blank areas from input image information will be explained using FIG. 2.

In FIG. 2, 21 is image information after passing through the preprocessing section 103. Now, as shown in the figure, a rectangle of m×n pixels is created, sequentially scanned in the direction of the arrow (horizontal direction), and the number of black pixels existing within the rectangle is counted. The results at this time are shown in 22. In part a, since there is only a blank area within the rectangle, the counted number of black pixels is 0. Next, in part b, the number of black pixels increases because it covers an area where characters exist. In C, the number of black pixels is even greater since all of the areas are text areas. In this way, when transitioning from a blank area to, for example, a character area, the number of black pixels within the rectangle changes from 0 to a certain value.

A region boundary line exists within this changing rectangle (portion b). Next, in order to accurately find the position of the boundary line of the area,
Move the rectangle b to the left and find the location where the number of black pixels in the rectangle is O. As a method of movement, it is sufficient to move one pixel at a time to the left. The position of the right side of the rectangle when the number of black pixels in the rectangle reaches O is stored as the boundary. Similar scanning is performed for the transition area (xyz) from the character area to the blank area to determine the boundary line.

The shape of the rectangle to be scanned is generally as follows. For horizontal scanning, use the value of m that satisfies m≧n and that includes multiple lines or multiple characters within the rectangle; for vertical scanning, use the value of m that satisfies m≦n and includes multiple lines or multiple characters. Use the value of n that falls within the rectangle. By doing this, it is possible to extract with high sensitivity the blank parts separating each area even in a document in which there are columns or the like.

The above operations are performed horizontally and
The results obtained in the vertical direction are shown in FIG. As seen in FIG. 3, the position of the boundary line is somewhat uneven depending on the state of the input image. If this continues, subsequent processing will be difficult, so by taking a circumscribed rectangle, this area is separated and extracted from the input image. In this way, blank areas and other areas are separated from the input image. Next, by the above processing, the number of black pixels in the separated and extracted portion (rectangle shown in FIG. 3) other than the blank area is counted and divided by the area to obtain the density.

Now, we are in the realm of images such as photographs.

The black pixel density of the text area and diagram area is Dl-D, respectively.
2.D3, the relational expression Di>02>D3 generally holds true. Therefore, by setting an appropriate threshold value, each area can be separated and extracted.-0 FIG. 4 is a block diagram showing details of the character area processing section 106. 41 is a character string extraction unit that extracts a character string within a text and character area; 42 is a character extraction unit that extracts one character from the extracted character string; 43 is a character string extraction unit that extracts a character string from the extracted character string; This is a character recognition unit that performs recognition. Characters that could not be recognized here are sent as image data to the next word matching section 45. In the word matching section,
A word dictionary 46 is checked to see if the recognized characters have meaning as words, and if meaningless words exist due to misrecognition of characters, those that can be corrected are converted into correct words. Characters that cannot be recognized by the character recognition unit but can be determined by referring to the word dictionary are determined in this part. Characters that cannot be determined by the word matching section are left as images. 47 is a character encoding unit that encodes recognized characters. 48 is a true format addition section that adds information necessary for reconstructing the character string converted into code data in the above section on paper. For example, as shown in FIG. 5, when the origin is the upper left of the paper, the
, yl) and (x2, y2). At this time, the true format indicating this area is as shown in FIG. 6(a), for example. In this example, “
"Char" indicates that this area is a character area, that the position of the character area is within a rectangle surrounded by (xl, yl) and (x2, y2), and that the character type is Mincho typeface. This indicates that the font size is 10 points, and that the recognized character string is the content shown by 1@@・・・・・・・・・・・・@@).This information Based on this, information in the character area is output to a printing device or display device, or stored in an external storage device.

FIG. 7 is a block diagram showing details of the chart area processing section 107. Reference numeral 71 denotes a geometric figure extraction unit that extracts geometric figures within the diagram area, and uses Hough transformation, connected component extraction of black pixels, etc. as an extraction method.

72 is a character extraction unit that extracts characters included in the diagram area;
Reference numeral 73 denotes a character recognition unit that refers to the character recognition dictionary 74 to recognize the extracted characters. Characters that could not be recognized here are sent as image data to the next word matching section 75.

The word matching section refers to the word dictionary 76 to determine whether the recognized characters have meaning as words, and if there are meaningless words due to misrecognition of characters, the words that can be corrected are corrected. Convert to word. Characters that cannot be recognized by the character recognition unit but can be determined by referring to the word dictionary are determined in this part. For characters that could not be confirmed by the word matching section,
Leave the image as is. 77 is a character encoding unit that encodes recognized characters. 7
Reference numeral 8 denotes a page format adding section that adds information necessary for reconstructing the character string converted into code data in the above section on paper. For example, as shown in Figure 5, when the origin is at the top left of the paper, the X axis is vertically, and the Y axis is horizontally, the straight line connecting (x3, y3) and (x4, y4) is Suppose it exists. At this time, the page format showing this straight line is
For example, it becomes as shown in FIG. 6(b). In this example,
"Line" indicates that this figure is a straight line, that the position of the straight line is in the area connecting (x3, y3) and (x4, y4), that the type of line is a solid line, and that the width of the line is 0.
Each indicates that it is 5 mm. In FIG. 7, portions 72 to 78 may be shared with those included in the character area processing section 106.

The following can be considered as application examples of the present invention. In electronic filing systems, data can be compressed by dividing the input image into regions and coding.
Storage capacity can be reduced. By combining it with desktop publishing, it can be used to rewrite text and graphics in an input image to create another document.

When performing machine translation, it is possible to automate document input, which was previously done by humans using a keyboard. Conventionally, when copying machines repeatedly reproduce image information, characters and figures become unclear due to noise and other factors, and eventually become unreadable.
By coding the parts that can be coded,
No matter how many times the coded part is copied, a clear image can always be obtained. Furthermore, for the same reason, when used to process facsimile input images, the images become clearer and the transmission capacity is reduced.

[Effects of the Invention] As described above, when the document image processing device of the present invention is used, characters and figures that were conventionally treated as image information are recognized and converted into code data suitable for them, so that it is possible to save data. In this case, less storage capacity is required.

Also, since it has been converted to code data, editing work such as changing or reusing a portion of characters, figures, etc. can be performed. Furthermore, text, diagrams, and image areas are automatically separated and extracted, which not only saves processing time, but also allows you to set the program in advance.
You can also perform trick plays such as erasing the logo mark that exists in the margin, or saving only text or shapes.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of the document image processing device of the present invention, FIG. 2 is a diagram explaining the principle of the blank area extraction method of the present invention,
FIG. 3 is a diagram showing the result when the method shown in FIG. 2 is applied to a document, FIG. 4 is a block diagram of the character area processing section of the present invention, and FIG. 5 is a diagram showing an example of an input image. Figure 6 is the 5th
FIG. 7, which represents a diagram in page format, is a block diagram of the diagram area processing section of the present invention. 101... Image input section, 102... Image memory, 1
03... Preprocessing unit, 104... Feature extraction unit, 105
...Area dividing section, 106...Character area processing section, 10
7... Chart area processing unit, 108... Image area processing unit, 109... Reconstruction unit, 110... Image output unit, 21... Input image information, 22... Number of black pixels Distribution diagram, 41... Character string extraction section, 42.72... Character extraction section, 43.73... Character recognition section, 44.74.
...Character recognition dictionary, 45.75...Word matching section, 4
6.76...Word dictionary, 47.77...Character encoding section, 48.78...Page format addition section, 71...Geometric figure extraction section Applicant Seiko Epson Co., Ltd. Agent Patent attorney Suzu Flood Damage 3 (1 other person) -111111. SUMMARY OF THE INVENTION The present invention aims to solve the above-mentioned problems by separating an inputted document image into a text area, a diagram area, and an image area without relying on humans. The purpose of the present invention is to provide a device that recognizes characters and geometric figures in the domain, converts the information into food data suitable for each type of information, and stores the document. 1i! ! [Means for Solving the Problem] A document image processing device of the present invention includes an image input section that captures a document containing at least one of characters, diagrams, and image areas as image information, and an image input section that captures an image captured by the image input section. A preprocessing unit that removes noise from information and binarizes it; a feature extraction unit that extracts the features of text, diagrams, and image regions in image information; and a feature extraction unit that extracts the features of characters, diagrams, and image areas in image information, and extracts the aforementioned image information based on the features extracted by this feature extraction unit. Character area Figure 2 Figure 6 (b)

Claims (1)

[Claims] an image input unit that captures a document containing at least one of text, diagrams, and image areas as image information; a preprocessing unit that removes noise from the image information captured by the image input unit and converts it into binarization; and the preprocessing. a blank area extraction unit that extracts a blank area from the data processed by the blank area, and an area division unit that divides the image information into a character area, a diagram area, and an image area by determining the black pixel density for areas other than the blank area. a character area processing unit that recognizes characters in the character area; a diagram area processing unit that recognizes geometric figures and characters in the diagram area; and an image area processing unit that processes image information in the image area. , a reconstruction unit that reconstructs the data from the three processing units;
1. A document image processing device, comprising: an image output unit that outputs reconstructed document information.