JP2002077598A - Method and device for processing image, and computer- readable recording medium on which image processing program is recorded - Google Patents

Abstract

PROBLEM TO BE SOLVED: To output a quality character image at enlargement/reduction of an image. SOLUTION: In an image process, an image data is inputted and its variable power rate is set. A character is recognized in an input image data by character recognition, and then the size of the recognized character is recognized. By referencing a storage part in which the font data in a plurality of different sizes is stored, a coded character data is converted into a set magnification. Here, a font size corresponding to the character size and power variable rate is calculated and a corresponding font data is read out of a font storage part for setting, compositing outputting an image containing the magnified character region.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to image data processing using a character recognition function.

[0002]

2. Description of the Related Art In a conventional digital copying machine or the like,
When performing an enlarged copy, the image data obtained by reading the original is subjected to interpolation processing of the image data according to the scaling factor. In addition, the thinning process of the image data according to the magnification is performed.

[0003]

However, in the conventional enlarged copy and reduced copy simply performing interpolation and thinning of image data, outlines of character images are disturbed (enlarged jagged outlines) at the time of enlargement, and reduced at the time of reduction. Characters sometimes collapsed. Due to the deterioration of the character quality due to such enlargement or reduction, there is a problem that the copied character feels strange or the character cannot be read.

An object of the present invention is to provide an apparatus, a method, and a recording medium for image processing capable of outputting a high-quality character image in image scaling processing.

[0005]

An image processing apparatus according to the present invention comprises: an image input unit to which image data is input; and a character recognition unit that recognizes and extracts characters in the image data input to the image input unit. A character size recognizing unit for recognizing the size of the character recognized by the character recognizing unit, a scaling unit for enlarging or reducing the size of the image data according to the scaling factor, and a scaling factor for setting the scaling factor of the scaling unit. A setting unit, a storage unit for storing a plurality of font data of different sizes, and a storage unit for storing font data of a size corresponding to the character size recognized by the character size recognizing unit and the scaling ratio set by the scaling setting unit. A font data setting unit that sets the font data with reference to the font data setting unit, and an output unit that outputs the font data set by the font data setting unit.

Preferably, the image processing apparatus further includes an image reading unit that reads the original and outputs image data.
The image reading section outputs the image data to the image input section. Preferably, the image processing apparatus further includes an image forming unit that forms an image on a sheet based on the font data output from the output unit. Preferably, the image processing apparatus further includes a communication unit for communicating with an external device, and the font data setting unit can input and set font data stored in the external device from the communication unit. . Preferably, the image processing device further includes a font size for correcting the size of the font data based on the character size recognized by the character size recognition unit and the scaling ratio set by the scaling ratio setting unit. A correction unit is provided. In the image processing apparatus, preferably, when the font data corresponding to the recognized character does not exist in the storage unit, the scaling unit scales the character in the image data according to the scaling factor.

The image processing method according to the present invention comprises the steps of inputting image data, recognizing and extracting characters in the input image data, recognizing the size of the extracted characters, A step of setting a scaling factor; a step of enlarging / reducing the size of image data according to the set scaling factor; and referring to a storage unit for storing a plurality of font data of different sizes to determine a recognized character size. And setting the font data of a size corresponding to the set scaling factor, and outputting the set font data.

[0008] A computer-readable recording medium according to the present invention comprises a step of inputting image data; a step of recognizing and extracting characters in the input image data;
A step of recognizing the size of the extracted character, a step of setting a magnification of the image, a step of enlarging / reducing the size of the image data according to the set magnification, and a step of retrieving font data of a plurality of different sizes. An image processing program comprising a step of setting font data of a size corresponding to a recognized character size and a set scaling factor with reference to a storage unit to be stored, and a step of outputting the set font data. Record.

[0009]

Embodiments of the present invention will be described below with reference to the accompanying drawings. In the drawings, the same reference symbols indicate the same or equivalent ones. FIG. 1 shows the configuration of a system according to an embodiment of the present invention. In this system, a scanner 100 that reads an image of a document and outputs image data and a printer 200 that receives the image data and forms an image on a predetermined sheet are connected via a network 300. Network 300
In addition, an external device 500 such as a personal computer and a network printer, and a stand-alone digital copying machine 400 are connected to the. In the embodiment described below, the printer 200 has a character recognition function. However, the character recognition function is
0, the external device 500 or the digital copier 400 may have it. Further, instead of the scanner 100, a device such as a digital camera and a film scanner may be connected. Further, instead of the printer 200, a device such as a display for displaying image data may be connected.

FIG. 2 shows a block diagram of the system shown in FIG. The scanner 100 includes a reading unit 110 and a scanner controller 120 that controls the reading unit 110. The scanner controller 120 is the scanner controller 12.
CPU 122 for controlling the entire system, ROM 124 for storing programs and the like, and RAM 12 for temporarily storing data.
6. Non-volatile RAM 128, scanner interface 130 as a connection to reading unit 110, and communication interface 132 as a connection to network 300
Consists of The printer 200 includes an image forming unit 210.
And a printer controller 220 for controlling the same. The printer controller 220 includes a CPU 222 for controlling the entire printer controller 120, a ROM 224 for storing programs and the like, a RAM 226 for temporarily storing data, a nonvolatile RAM 228, an image processing unit 230 having a character recognition function, and an image forming unit 210. A printer interface 232 as a connection unit, and a communication interface 2 as a connection unit with the network 300
34.

FIG. 3 is a block diagram showing the configuration of the image processing section 230 in the printer 200. Image input unit 4
At 00, image data is input from the bus, and a magnification corresponding to the magnification input from the operation panel of the scanner 100 or the like is set by the magnification setting unit 402. The area extracting unit 404 divides the input image data into a character area and another picture area. In the area division, for example, the number of pixels determined to be edges in a certain area is calculated. If the number of pixels exceeds a threshold, the area is set as a character area, and if not, a picture area is set. As shown in FIG. 4, both the character area and the picture area are recognized as rectangles.

The image data of the character area obtained by the division is input to a binarizing section 406 and binarized. From the character image in the image data of the character area, the OCR processing unit 408
The character code and character size are recognized. The character scaling unit 412 selects a predetermined font from font data of a plurality of sizes stored in the font storage unit 410 in advance based on the recognized character code, character size, and set scaling factor. This enlarges or reduces the character size.

On the other hand, the image data of the picture area is input to a picture scaling section 414, and is scaled by a magnification process such as a linear interpolation method or a cubic convolution interpolation method, or a reduction process such as a simple thinning process. The scaled image data is subjected to screening processing such as dither processing and error diffusion processing in a screening processing unit 416.

Next, an image synthesizing processing unit 418 synthesizes the image data of the scaled character area and the image data of the picture area subjected to the screening processing, and converts the character code data and other bitmap data into a general-purpose format. (For example, PDF format). The image output unit 420
The composite image including the scaled character area is converted into raster data using RIP or the like and output.

Next, the scaling process of a character image will be described in detail. FIG. 5 is a flowchart of the character image scaling process in the character scaling unit 412. First, the font size to be output is calculated based on the value obtained by multiplying the font size recognized by the character recognition by the scaling factor (S50).
1). A specific calculation method will be described later. Next, the font data of the font size calculated in step S501 is read from the font storage unit 410 (S502). The process ends for all characters whose character codes have been recognized (S50).
Until (YES at 3), the processing of steps S501 and S502 is repeated.

Next, the calculation of the font size in step S501 will be described. A font size correspondence table as shown in Table 1 is stored in the ROM 224 in advance, and is used for calculating the font size. This font size correspondence table indicates the width and height corresponding to the font size of a font that is used relatively frequently, such as MS Gothic and MS Mincho. In this example, only representative fonts are shown, but any other font can additionally store a width and height corresponding to the font size. Also, even if the fonts are the same, if the width and height differ depending on the type of character, all the widths and heights may be tabulated. By storing the width and height data for all characters, more appropriate scaling processing can be performed.

[0017]

[Table 1]

Calculation of font size (FIG. 5, S501)
As shown in the flowchart of FIG. 6, there are a font size calculation for the same magnification and a font size calculation for the magnification change. More specifically, it is determined whether or not the scaling ratio set in the scaling ratio setting unit 402 is 1.0 (actual magnification) (S601). Proceeding to S602), if it is not the same size, the font size calculation for scaling (S6)
Go to 03). These calculations are performed for each character area. Each specific calculation method will be described later. If the font size calculation for one character area is completed, it is determined whether the font size calculation has been completed for all the character areas in the document (S604).
Returning to step S601, the font size for the next character area is calculated. If the processing has been completed, the process returns to the flow in FIG.

Next, the calculation of the font size for the same size will be described with reference to FIGS. 7 and 8. FIG. Here, the description will be given on the assumption that the recognition of the font size in the current OCR processing technology is uncertain. For example, if the font size of a character image on a document is 10 points and the OCR processing unit 408 erroneously recognizes the font size as 12 points, the output character code data is output from the character area. There is a problem that it protrudes.

In the flow of the calculation of the font size for the same size in FIG. 7 (S602 in FIG. 6), first, the maximum number of characters in one line of the character area subjected to the character recognition is multiplied by the recognized font size to obtain the maximum size. The line width is calculated (S701).
Next, the calculated maximum line width is compared with the width of the circumscribed rectangle of the character area (S702). If the maximum line width is larger than the width of the circumscribed rectangle (YES in S702), the OCR processing unit 408 recognizes the maximum line width. The font size (default output font size) is corrected based on the following equation (S703). Corrected font size = default output font size x (circumscribed rectangle width / maximum line width)

The example shown in FIG. 8 will be described. The OCR processing unit 408 recognizes that the width of the circumscribed rectangle of the character area of the original image (the figure on the left) is 28.2 mm, and the maximum number of characters in one line is eight. Here, when the recognized font is MS Gothic and the font size is 12 points (4.2 mm, refer to the font size correspondence table), the maximum line width is 33.6 mm (center figure). Therefore, since the maximum line width is larger than the width of the circumscribed rectangle, the font size is changed using the above-described formula. Font size after correction = 12 x (28.2 / 33.6) =
10.07 The font size after correction will be 10 points if the decimals are rounded off (right figure).

Next, the calculation of the font size for scaling (S605 in FIG. 6) will be described with reference to FIG. First,
The circumscribed rectangle width of the character area recognized by the OCR processing unit 408 is multiplied by the scaling factor input from the operation panel such as the scanner 100, and the circumscribed rectangle width after the scaling is calculated (S901).
Next, the recognized font size is similarly multiplied by the scaling factor to calculate the font size after scaling (S902).
After that, the maximum line width is calculated based on the font size after the scaling (S903), and the maximum line width and the width of the circumscribed rectangle after the scaling are calculated in the same manner as the above-described font size calculation for the same size (FIG. 7). If the maximum line width is larger than the width of the circumscribed rectangle (YES in S904), the recognized font size is corrected based on the above expression (S905).

In the above description, an appropriate font size after scaling is obtained using the width of the circumscribed rectangle. further,
In addition, by comparing the maximum character width with the maximum column width using the height of the circumscribed rectangle, the output character code data can be reliably contained in the character area.

Next, an embodiment will be described in which the case where the recognized font does not exist in the font storage unit 410 is considered. FIG. 10 shows a flow of character image scaling in this case. First, a font size to be output is calculated based on a value obtained by multiplying a font size recognized by character recognition by a scaling factor (S1001). The specific calculation method is the same as that described above (FIG. 5, S501), and a description thereof will be omitted. Next, it is determined whether the recognized font is present in the font storage unit 410 (S1002). If not, the font storage unit 510 () of another external device 500 connected to the network 300 is determined. It is determined whether or not it exists (see FIG. 1) (S1008). External device 50
If it exists in the 0 font storage unit 510, then:
It is determined whether a font having a font size corresponding to the scaling ratio exists in the font storage unit 510 of the external device (S1).
009) If present, the font is read from the font storage unit 510 (S1010). If not,
A font having a size closest to the font size corresponding to the scaling factor is read (S1011), and enlargement processing such as linear interpolation and cubic convolution interpolation, and reduction processing such as simple thinning processing are performed (S1012).

In step S1008, the external device 5
If it is determined that the recognized font does not exist in the font storage unit 510 of the 00, a character image is extracted from the original image data (S1013), and step S101 is performed.
2 is performed (S1014), and image processing for character images such as edge enhancement is performed (S1015).

If it is determined in step S1002 that the recognized font exists in the font storage unit 410, then it is determined whether a font having a font size corresponding to the scaling factor exists in the font storage unit 410. (S1003), and if there is, the font storage unit 410
The corresponding font is read from (S1004). If not, the font of the size closest to the font size corresponding to the magnification is read out (S1006), and step S1 is executed.
The same scaling process as in 012 is performed (S1007). When the scaling of one character is completed, it is determined whether the scaling process has been completed for all the characters (S1005). If the scaling process has not been completed for all the characters, step S10
Returning to step 02, the next character is scaled. If it has ended, the process returns to the main routine.

In the above-described embodiment, when the recognized font is not present in the font storage unit 410, the font is read from the font storage unit 510 of the external device 500. Or a web page server or the like.

In the above-described embodiment, the enlargement / reduction processing of the character image using the character recognition function has been described. However, this enlargement / reduction processing further reduces the image of a plurality of pages to one sheet. Output copy (Nin
1 processing). Further, the present invention can be applied to a case where a sheet output by the layout copy is divided and enlarged into N sheets.

[0029]

According to the present invention, a character on a document is recognized by using a character recognition function, converted into a character code, and at the time of zooming, the coded character is converted into an output image by using font size data stored in advance. To prevent the character quality from deteriorating due to zooming.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a system according to a first embodiment of the present invention;

FIG. 2 is a block diagram of the configuration of the system in FIG. 1;

FIG. 3 is a block diagram of a configuration of an image processing unit.

FIG. 4 is a flowchart of image data processing.

FIG. 5 is a diagram for explaining region extraction;

FIG. 6 is a flowchart of font size calculation.

FIG. 7 is a flowchart of calculating a font size for the same size.

FIG. 8 is a diagram for explaining a change in font size.

FIG. 9 is a flowchart of calculating a font size for scaling.

FIG. 10 is a flowchart of a character scaling process in another embodiment.

[Explanation of symbols]

100 scanner, 200 printer, 210
Image forming unit, 220 printer controller,
230 image processing unit, 300 network,
402 scaling ratio setting unit, 408 OCR processing unit,
410 font storage unit, 412 character scaling unit, 500 external device, 510 font storage unit.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI theme coat ゛ (Reference) G09G 5/26 B41J 3/12 L F-term (Reference) 2C062 AA24 AA69 5B057 CD05 5B064 AA10 AB18 5C076 AA21 AA22 BA06 5C082 AA01 AA27 AA32 AA36 BA02 BB32 BB34 BB49 CA33 CA34 CA36 CA85 DA32 MM09 MM10

Claims (8)

[Claims] An image input unit for inputting image data, a character recognition unit for recognizing and extracting characters in the image data input to the image input unit, and recognizing a size of the character recognized by the character recognition unit Character size recognition unit, scaling unit that enlarges or reduces the size of image data according to the scaling ratio, scaling unit that sets the scaling ratio of the scaling unit, and stores font data of multiple different sizes A font data setting unit for setting font data of a size corresponding to the character size recognized by the character size recognizing unit and the scaling factor set by the scaling factor setting unit by referring to the storage unit; An output unit that outputs the font data set by the data setting unit. 2. The image processing apparatus according to claim 1, further comprising an image reading unit that reads a document and outputs image data, wherein the image reading unit outputs the image data to an image input unit. 3. The image processing apparatus according to claim 1, further comprising an image forming unit that forms an image on a sheet based on the font data output from the output unit. apparatus. 4. The communication apparatus according to claim 1, further comprising a communication unit for communicating with an external device, wherein the font data setting unit is capable of inputting and setting font data stored in the external device from the communication unit. The image processing device according to claim 1. 5. A font size correction unit for correcting the size of font data based on the character size recognized by the character size recognition unit and the scaling ratio set by the scaling ratio setting unit. The image processing apparatus according to claim 1, wherein: 6. The variable magnification unit according to claim 1, wherein the font data corresponding to the recognized character is not stored in the storage unit, and the character in the image data is scaled according to the magnification. The image processing device according to claim 1. 7. A step of inputting image data; a step of recognizing and extracting characters in the input image data; a step of recognizing a size of the extracted characters; and a step of setting a magnification of the image. , Enlarges the image data size according to the set magnification.
A step of reducing, and a step of setting font data of a size corresponding to the recognized character size and the set scaling factor with reference to a storage unit for storing a plurality of font data of different sizes; Outputting font data. 8. A step of inputting image data; a step of recognizing and extracting characters in the input image data; a step of recognizing a size of the extracted characters; and a step of setting a magnification of the image. , Enlarges the image data size according to the set magnification.
A step of reducing, and a step of setting font data of a size corresponding to the recognized character size and the set scaling factor with reference to a storage unit for storing a plurality of font data of different sizes; And a computer-readable recording medium storing an image processing program comprising the steps of outputting font data.