JPH0795400A - Picture processing unit - Google Patents

Abstract

PURPOSE:To obtain a picture in which a mis-discriminated area is not remarkable even when a character and a photograph are discriminated in error in an intermediate area between the character and the photograph in the case of applying image area separation to a picture in mixture of the character and the photograph so as to attain processing suitable for each area. CONSTITUTION:a character/photograph/intermediate area discrimination circuit 3 discriminates whether picture information of a local area indicates a property specific to a character part, or indicates a characteristic as a photograph part or indicates a property as an intermediate area, identifies and discriminates the type of the picture, a threshold level selection circuit 7 is selected according to the identification discrimination result, a threshold level given from a character area threshold level calculation circuit 4, or a threshold level given from a photograph area threshold level calculation circuit (memory) 6, or a threshold level given from an intermediate area threshold level calculation circuit 5 is selectively extracted as a threshold level used to apply N-value processing to the picture information and a comparator circuit 9 implements the N-value processing based on the extracted threshold level.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document image in which a character image and a photographic image are mixed, and an image processing for performing a multi-valued process which simultaneously satisfies the resolution of the character portion and the gradation of the photograph portion. Regarding the device.

[0002]

2. Description of the Related Art As a method of simultaneously satisfying the resolution of a character portion and the gradation of a photograph portion, a single image in which a character image and a photographic image are mixed is used as an image density in a local area of an image to be processed. A method has been proposed in which the maximum density difference (ΔDmax) is calculated and the value is compared with the determination threshold value (Th) to separate the character area from the photograph area.

For example, in Japanese Patent Application No. 58-3374, a screen is divided into blocks each having a plurality of pixels, and a density level between a pixel having the highest density level and a pixel having the lowest density level in each block. If the difference is smaller than a fixed value, it is determined to be a grayscale image area, and binarization processing with emphasis on halftone reproduction is performed. If it is larger than a fixed value, it is determined to be a binary image area and emphasis is placed on resolution. A method of performing binarization with the above is disclosed.

That is, in such a system, the image portion having high contrast of the character or the diagram separated in this way is subjected to the N-value conversion processing (N ≧) by using the dynamic threshold processing.
2) Then, for an image portion having gradation such as a photograph, N is obtained by using a pseudo gradation method such as an error diffusion method or a systematic dither method.
Since the value is set (N ≧ 2), the resolution of a character image and the gradation of a photographic image can be simultaneously satisfied.

For example, a photographic image generally has a density profile as shown in FIG. 12, and since the maximum density difference within a local area (3 × 3) pixel is small, it is determined that the image is a photographic image and gradation is emphasized. Processing is performed. On the other hand, the character image is shown in FIG.
As shown in the concentration profile in Fig.
3) Since the maximum density difference within a pixel is large, it is determined that the character is a character and a process for emphasizing the contrast is performed.

By utilizing such characteristics, it is possible to determine that the maximum density difference (ΔDmax) in the local area is a character area when the difference is larger than the determination threshold Th, and the photographic area when the difference is small.

However, when the character area and the photographic area are separated by using such a method, there is an edge portion such as a portion where the background area is changed to the object even in a photographic image, and thus such an area is formed. It is conceivable that the area may be mistakenly determined to be a character, or conversely, there is an image with a low contrast even in a character image, and such an area may be determined to be a photograph. In this way, since there is an intermediate area that has both character and photo characteristics depending on the image, if such an area is judged by the conventional method, it is misjudged as either a character or a photograph, which is very annoying. It becomes an image.

For example, when the density profile shown by the dotted line of the area where the background portion of the photographic image changes to the object as shown in FIG. 14A, it becomes as shown in FIG.
The maximum density difference increases. As a result, this area, that is, only the contour of the object is erroneously determined as a character area, so that the contrast is emphasized and the image becomes very unpleasant.

In the case of a low-contrast image such as a pencil drawing as shown in FIG. 15A, the density profile shown by the dotted line is as shown in FIG. 15B, and the maximum density difference is small. As a result, the image is determined to be a photograph, resulting in a blurred image with low contrast.

As described above, when the image area separation of an image in which characters and photographs are mixed is present, an area having both the characteristics of characters and photographs, that is, an intermediate area exists in the image. It was impossible to separate into areas. If such an intermediate area, for example, an area originally thought to be a photographic area, where the maximum density difference is relatively large, or a graphic area having a complicated shape is mistakenly determined to be a character or a photograph, the character area and the photograph area Since there is a large gap in the processing method of (1), there is a problem that the erroneous determination area becomes noise and is very annoying.

[0011]

As described above, in the intermediate area when separating an image area of an image in which characters and photographs are mixed, for example, even in an area that is supposed to be a photograph area, an area having a relatively large maximum density difference, If a graphic area with a complicated shape is mistakenly determined to be a character or a photo, there is a large gap between the processing methods of the text area and the photo area, and the false determination area becomes noise, which is very annoying. was there.

Therefore, according to the present invention, when an image in which characters and photographs are mixed is separated into image areas and processing suitable for each area is performed,
An object of the present invention is to provide an image processing apparatus capable of obtaining an image in which an erroneous determination area is less noticeable even when a character and a photograph are erroneously determined in the intermediate area between the character and the photograph.

[0013]

An image processing apparatus according to the present invention calculates a maximum density difference between a target pixel and a peripheral pixel from image information within a predetermined range including a target pixel in an image to be processed. Calculating means, determining means for determining the value of the maximum density difference calculated by the maximum density difference calculating means using a predetermined threshold value to determine whether the pixel of interest is a character area, a photograph area, or an intermediate area; From the image information within a predetermined range including the, from the dynamic threshold value calculating means for calculating the dynamic threshold value of the character area, the dynamic threshold value calculated by this dynamic threshold value calculating means and a predetermined fixed threshold value, The intermediate area threshold value calculating means for calculating the threshold value of the intermediate area according to the value of the maximum density difference calculated by the maximum density difference calculating means, and the photographic area for setting the threshold value for multi-valued image information of the photographic area. Threshold setting means, The target pixel by serial determination means,
If it is determined to correspond to the character area, the dynamic threshold from the dynamic threshold calculation means is selected, and if it is determined to correspond to the intermediate area, the threshold from the intermediate area threshold calculation means. Image information of the pixel of interest by using the threshold value selecting means for selecting the threshold value from the threshold value setting means and the threshold value selected by the threshold value selecting means when it is determined that the image area corresponds to the photograph area. Is made up of multi-values.

The image processing apparatus of the present invention comprises maximum density difference calculating means for calculating the maximum density difference between the target pixel and peripheral pixels from image information within a predetermined range including the target pixel in the image to be processed, and the above-mentioned target A maximum and minimum value calculating means for calculating maximum and minimum values in a predetermined reference area from image information in a predetermined range including pixels, and image information in a predetermined range including the target pixel in the predetermined reference area Average value calculation means for calculating the average value, corrected average value conversion means for correcting the average value calculated by the average value calculation means, corrected average value from the corrected average value conversion means, and the maximum and minimum values From the dynamic threshold value calculating means for calculating the dynamic threshold value from the maximum value and the minimum value from the calculating means, and the dynamic threshold value calculated by the dynamic threshold value calculating means and a predetermined fixed threshold value, the maximum concentration Calculated by the difference calculation means And an intermediate region threshold calculating means for calculating a threshold value of the intermediate region according to the value of the maximum density difference is.

The image processing apparatus of the present invention comprises maximum density difference calculating means for calculating the maximum density difference between the target pixel and peripheral pixels from image information within a predetermined range including the target pixel in the image to be processed, and the maximum density difference calculating means. The value of the maximum density difference calculated by the density difference calculating means is used to determine whether the pixel of interest is a character area, a photographic area, or an intermediate area using a predetermined threshold value, and a predetermined range including the pixel of interest. From the image information,
Maximum and minimum value calculating means for calculating maximum and minimum values within a predetermined reference area; and average value calculating means for calculating an average value within a predetermined reference area from image information within a predetermined range including the pixel of interest. A corrected average value conversion means for correcting the average value calculated by the average value calculation means, a corrected average value from the corrected average value conversion means, and a maximum value and a minimum value from the maximum / minimum value calculation means. From the dynamic threshold calculation means for calculating the dynamic threshold of the character area, the dynamic threshold calculated by the dynamic threshold calculation means and the predetermined fixed threshold, the maximum calculated by the maximum density difference calculation means is calculated. The intermediate area threshold value calculating means for calculating the threshold value of the intermediate area according to the value of the density difference, the threshold value setting means for the photographic area for setting the threshold value for multi-valued image information of the photographic area, and the determining means The pixel of interest corresponds to the character area If it is determined that the dynamic threshold from the dynamic threshold calculation means is selected, if it is determined to correspond to the intermediate area, the threshold from the intermediate area threshold calculation means is selected, and the photograph When it is determined that the area corresponds to the area, the threshold value selecting means selects the threshold value from the threshold value setting means.

According to the image processing method of the present invention, from the image information within the predetermined range including the pixel of interest in the image to be processed,
The maximum density difference between the pixel of interest and the peripheral pixels is calculated, and the value of the calculated maximum density difference is used to determine whether the pixel of interest is a character area, a photographic area, or an intermediate area. The dynamic threshold of the character area is calculated from the image information within the predetermined range including the pixel of interest, and the calculated dynamic threshold and the predetermined fixed threshold are used to determine the value of the maximum density difference calculated above. Calculate the threshold value of the intermediate area, set the threshold value for multi-valued image information of the photograph area, and if the above-mentioned pixel of interest is determined to correspond to the character area by the above determination, the character area Dynamic threshold, select the threshold value for the intermediate area if it is determined to correspond to the intermediate area, and select the threshold value for the photograph area if determined to correspond to the photo area. Then, using the selected threshold value, Image information comprising a step of multi-valued.

According to the image processing method of the present invention, from the image information in the predetermined range including the pixel of interest in the image to be processed,
A maximum density difference between the target pixel and peripheral pixels is calculated, and a maximum value and a minimum value within a predetermined reference area are calculated from image information within a predetermined range including the target pixel, and a predetermined range including the target pixel is calculated. An average value within a predetermined reference area is calculated from the image information in the image, the calculated average value is corrected, and a dynamic threshold is calculated from the corrected average value and the calculated maximum value and minimum value. From the calculated dynamic threshold value and a predetermined fixed threshold value, and calculating the threshold value of the intermediate region according to the value of the calculated maximum density difference.

According to the image processing method of the present invention, from the image information within the predetermined range including the pixel of interest in the image to be processed,
The maximum density difference between the pixel of interest and the peripheral pixels is calculated, and the value of the calculated maximum density difference is used to determine whether the pixel of interest is a character area, a photographic area, or an intermediate area. The maximum value and the minimum value in the predetermined reference area are calculated from the image information in the predetermined range including the target pixel, and the average value in the predetermined reference area is calculated from the image information in the predetermined range including the target pixel. Then, the calculated average value is corrected, and the dynamic threshold of the character area is calculated from the corrected average value thus corrected and the calculated maximum value and minimum value. From the fixed threshold determined, calculate the threshold of the intermediate region according to the value of the calculated maximum density difference,
Set the threshold for multi-valued image information in the photo area,
If the pixel of interest is determined to correspond to the character region by the determination, the dynamic threshold value of the character region is selected, and if it is determined to correspond to the intermediate region, the threshold value of the intermediate region is set. If the selection is made and it is determined that it corresponds to the photo area, the step of selecting the threshold value of the photo area is performed.

[0019]

According to the present invention, the maximum density difference between the target pixel and the peripheral pixels is calculated by the maximum density difference calculating means from the image information within the predetermined range including the target pixel in the image to be processed, and the calculated maximum density difference is calculated. The determination means determines whether the pixel of interest is a character region, a photo region, or an intermediate region by using a predetermined threshold value, and the dynamic threshold of the character region is determined from image information in a predetermined range including the pixel of interest. From the calculated dynamic threshold and the predetermined fixed threshold, the threshold of the intermediate area is calculated according to the value of the maximum density difference calculated by the maximum density difference calculating means, and the image information of the photograph area is calculated. Is set to a multi-valued threshold value, and if the determination unit determines that the pixel of interest corresponds to a character area, it selects a dynamic threshold value of the character area and corresponds to the intermediate area. If it is determined that The threshold of the area is selected, and when it is determined that the area corresponds to the photograph area, the threshold of the photograph area is selected, and the image information of the pixel of interest is multi-valued using the selected threshold. It is a thing.

According to the present invention, the maximum density difference between the target pixel and the peripheral pixels is calculated by the maximum density difference calculating means from the image information in the predetermined range including the target pixel in the image to be processed,
From the image information in the predetermined range including the target pixel, the maximum value and the minimum value in the predetermined reference area are calculated by the maximum and minimum value calculating means, and from the image information in the predetermined range including the target pixel,
Calculate an average value in a predetermined reference region, correct the calculated average value, calculate a dynamic threshold from the corrected corrected average value and the maximum and minimum values from the maximum and minimum value calculating means, From the calculated dynamic threshold value and a predetermined fixed threshold value, the threshold value of the intermediate area is calculated according to the value of the maximum density difference calculated by the maximum density difference calculation means.

According to the present invention, the maximum density difference between the target pixel and the peripheral pixels is calculated by the maximum density difference calculating means from the image information within the predetermined range including the target pixel in the image to be processed.
The value of the calculated maximum density difference is determined by a determination means using a predetermined threshold value to determine whether the pixel of interest is a character region, a photographic region, or an intermediate region, and a predetermined value is determined from image information within a predetermined range including the pixel of interest. The maximum value and the minimum value in the reference area are calculated by the maximum / minimum value calculating means, the average value in the predetermined reference area is calculated from the image information in the predetermined range including the target pixel, and the calculated average value Is calculated, and the dynamic threshold value of the character area is calculated from the corrected average value corrected and the maximum value and the minimum value from the maximum / minimum value calculating means, and the calculated dynamic threshold value and a predetermined fixed threshold value. From the above, the threshold value of the intermediate area is calculated according to the value of the maximum density difference calculated by the maximum density difference calculating means, and the threshold value for multivalued image information of the photographic area is set, and by the judging means. Judge that the pixel of interest above corresponds to the character area If it is determined that the dynamic threshold of the character area is selected, if it is determined to correspond to the intermediate area, the threshold of the intermediate area is selected, if it is determined to correspond to the photo area, The threshold value of the photograph area is selected.

[0022]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 shows a schematic configuration of an image processing apparatus according to an embodiment of the present invention. This image processing device inputs image information read and input by a reading device such as an image scanner (not shown) as, for example, 8-bit digital data per pixel, and performs N-value conversion processing (N
≧ 2).

In FIG. 1, the line buffer 1 temporarily stores such image information and provides it to the following image processing (N-value conversion processing). The maximum density difference calculation circuit 2 inputs the image information output from the line buffer 1 in synchronization with a predetermined clock, and obtains the characteristic information in the local area including the pixel of interest from the image information. Next, the character / photograph / intermediate area determination circuit 3 determines this characteristic information and determines whether the image information of the local area shows the characteristic peculiar to the character portion, the characteristic as the photograph portion, or the image information of the intermediate area. The image type is discriminated and determined by determining whether or not the property is exhibited. The threshold value selection circuit 7 is switched according to the result of this discrimination, and the threshold value given from the threshold value calculation circuit 4 for the character area, the threshold value given from the threshold value calculation circuit (memory) 6 for the photo area, or the threshold value calculation circuit 5 for the intermediate area is given. The given threshold value is selectively extracted as a threshold value for performing the N-value conversion process on the image information. Then, it is read from the line buffer 1 and delayed by a predetermined timing via a delay circuit 8 and then compared with a comparison circuit (N
The image information guided to the binarization circuit 9 is N-valued by the threshold value extracted through the threshold value selection circuit 7 and output.

The character area threshold value generating circuit 4 calculates the maximum value and the minimum value in a reference area having a predetermined size, for example, a local area of (3 × 3) pixels, from the image information read from the line buffer 1. Maximum / minimum value calculation circuit 41
And an average value calculation circuit 42 that calculates the average value of the same area.
And a corrected average value conversion circuit 43 for correcting this average value (Da) using the following formula, and N- for dynamic N-value conversion from three values of a maximum value, a minimum value and a corrected average value. And a dynamic threshold value calculation circuit 44 for calculating one dynamic threshold value.

Da ′ = γ + (1-2 × γ / 255) Da Next, individual circuits will be described. FIG. 2 shows the configuration of the maximum density difference calculation circuit 2, which includes a maximum / minimum value detection circuit 21 and a subtractor 22. Maximum / minimum value detection circuit 2
1 is the maximum value of the density in the area of (5 × 5) pixels including the target pixel (pixels indicated by diagonal lines) with respect to the target pixel in the processing target image as shown in FIG. The minimum value and the minimum value are obtained respectively.

The maximum / minimum value detection circuit 21 includes a selector 2
1a, comparators 21b to 21h, and a counter 21i. The maximum / minimum value detection circuit 21 first receives the image information sequentially input from the line buffer 1 in units of 5 pixels in the column direction in synchronization with the clock CLK (8 bits / pixel) via a selector 21 a to a comparator 21 b,
21c, 21d, 21e and 21f are sequentially distributed.
The comparators 21b, 21c, 21d, 21e of the selector 21a for the image information input in units of columns,
The distribution to 21f operates by receiving the clock CLK 2
The operation is controlled by the selection signals SEI and SE2 of the bit counter 21i.

These comparators 21b, 21c, 21d,
21e and 21f, the image information is compared in the column direction in units of 5 pixels, and the maximum and minimum densities in the column are obtained.

The comparators 21g, 21h in the next stage receive the signals from the comparators 21b, 21c, 21d, 21e, 21f and compare the maximum and minimum values respectively obtained in the column direction in the row direction. , And the maximum value and the minimum value among them are obtained respectively. Through the above processing, the maximum density value Dmax and the minimum density value Dmin in the area of (5 × 5) pixels shown in FIG. 3A are obtained and output.

The subtractor 22 obtains the maximum density difference ΔDmax from the maximum density value Dmax and the minimum density value Dmin thus obtained using the following formula. ΔDmax = Dmax−Dmin The character / photograph / intermediate area determination circuit 3 compares the thus calculated maximum density difference ΔDmax with predetermined thresholds Thh and Thl, and outputs an identification signal 14 under the following determination conditions. .

[0030] Next, the N-value conversion means of each area will be described.

The character area threshold value generating circuit 4 comprises a maximum / minimum value calculating circuit 41, an average value calculating circuit 42, a corrected average value converting circuit 43, and a dynamic threshold value calculating circuit 44. Here, it is assumed that the number of output levels of the character area is four, that is, four-valued.

FIG. 4 shows a maximum / minimum value calculation circuit 41, which includes a selector 41a and comparators 41b, 41c, 41.
It is composed of d, 41e, 41f, and a counter 41g. The maximum / minimum value calculation circuit 41 obtains the maximum value (Dmax) and the minimum value (Dmin) of the density in the reference area of (3 × 3) pixels for the target pixel in the image to be processed. Maximum value (Dmax) and minimum value (D
min) are output to the dynamic threshold calculation circuit 44, respectively.

FIG. 5 shows an average value calculation circuit 42, which includes a selector 42a, adders 42b, 42c, 42d,
42e, a divider 42f, and a counter 42g. The average value calculation circuit 42 obtains the average density value (Da) within the reference region of (3 × 3) pixels similar to the maximum / minimum value calculation circuit 41. The average density value (Da) is output to the corrected average value conversion circuit 43. Then, the average density value (Da) is corrected by the corrected average value conversion circuit 43.

FIG. 6 shows a corrected average value conversion circuit 43, which is composed of a multiplier 43a and an adder 43b. The corrected average value conversion circuit 43 converts the average density value (Da) input from the average value calculation circuit 42 into the corrected average value (Da ′) of the following formula. However, e = 1-2
Xγ3 / 255 and f = γ3 are CPUs not shown in advance.
Is set to.

Da ′ = γ3 + (1-2 × γ3 / 255) × Da The dynamic threshold calculation circuit 44 includes the maximum / minimum value calculation circuit 4 described above.
Maximum value (Dmax) and minimum value (Dmin) of density calculated in 1
), And the corrected average value (Da ′) calculated by the corrected average value conversion circuit 43, the dynamic threshold value is calculated.

FIG. 7 shows the dynamic threshold calculation circuit 44. First, the adders 44a and 44b calculate the sum of the maximum density value (Dmax) and the corrected average value (Da ') and the sum of the minimum density value (Dmin) and the corrected average value (Da'), respectively. .
The dividers 44c and 44d each calculate the average value of the values thus obtained.

Th [1] = (DmAX + Da) / 2 Th [2] = Da Th [3] = (Dmin + Da) / 2 In this way, three threshold values for quaternization of the character area are given. .

Although the dynamic quaternarization has been described in the present embodiment, it is not limited to quaternary. When the value is N (N ≧ 2), the threshold value can be calculated, for example, by the following formula.

When (a) i <(N / 2) Th [i] = (Dmax-Da) × i / (N / 2) + Da (b) When i = (N + 1) / 2 Th [i] = Da (c) i> (N + 1) / 2 Th [i] = (Da−Dmin) × (i−N / 2) / (N / 2) + Dmin where i = 1, ..., (N− 1) FIG. 8 shows the threshold calculation circuit 5 for the intermediate area. The threshold value calculation circuit 5 in the intermediate region includes subtractors 5a to 5c, a divider 5d, a multiplier 5e, a subtractor 5f, and a delay circuit 5g. The threshold value calculation circuit 5 for the intermediate area is configured so that when the maximum density difference ΔDmax is between the predetermined threshold values Thl and Thh,
The threshold is controlled according to the value of ΔDmax, and its principle is shown in FIG. In this figure, the vertical axis represents the maximum density difference and the horizontal axis represents the threshold value. Character / photograph / intermediate area determination circuit 3
If ΔDmax is less than or equal to Thl, the threshold value Th ′ [1] to Th ′ [3] is determined by the following formula, assuming that the threshold value is Th4 [1] to Th ′ [3].

Th ′ [i] = (255/4) × i i
= 1, 2, 3, ... Further, when ΔDmax is larger than Thh, dynamic threshold processing is performed, and the thresholds are Th [1] to Th obtained by the dynamic threshold calculation circuit 44.
[3] Then, when ΔDmax is at the position indicated by the alternate long and short dash line in FIG. 8, that is, when it is between Thh and Thl, the threshold value Th ″ [1] for the intermediate region to be calculated is Th [1] and Th ′ [1] It becomes the value on the horizontal axis when the connecting line and this one-dot chain line intersect (marked by X in Fig. 9.) Th ″ [2] and Th ″ [3] can be similarly calculated.

This calculation method is expressed by the following equation. Th ″ [1] = Th [1]-(Th [1] -Th ′ [1]) / (Thh-Thl) × (Thh-ΔDmax) Th ″ [2] = Th [2]-(Th [2 ] -Th ′ [2]) / (Thh-Thl) × (Thh-ΔDmax) Th ″ [3] = Th [3]-(Th [3] -Th ′ [3]) / (Thh-Thl) × (Thh-ΔDmax) On the other hand, in the threshold value generation circuit 6 for the photograph area, for example, dither pattern information (dither matrix) as shown in FIG.

In this way, the threshold value selection circuit 7 is switched according to the discrimination judgment result of the character / photograph / intermediate region judgment circuit 3 described above, and the threshold value given by the character region threshold value calculation circuit 4 or the photoregion threshold value is selected. The threshold value indicated by the dither pattern of the calculation circuit 6 or the threshold value given by the threshold value calculation circuit 5 for the intermediate region is selectively extracted as the threshold value for performing the N-value conversion process on the image information. Then, the image information read from the line buffer 1, delayed by a predetermined timing via the delay circuit 8 and guided to the comparison circuit 9 is N-valued by the threshold value extracted via the threshold value selection circuit 7. Is output.

For example, a case where a photographic image as shown in FIG. 10A is processed will be described. As shown in the density profile of FIG. 10B, the area in which the background of the image changes to the target object has a relatively maximum density difference (ΔD).
max) is large. For this reason, if the conventional method shown in FIG. 10C is used, it is determined as a character area, and as shown in FIG. 10D, only the boundary between the background and the object is emphasized, resulting in an unpleasant image. Will end up. On the contrary,
When a region of the same image is discriminated by the method of this embodiment, the region is discriminated as an "intermediate region", so that the threshold value is slightly higher than that of the conventional method as shown in FIG. As a result, the output image is reproduced in a form close to the input image as shown in FIG. 10 (f), and only the edges are not emphasized unlike the conventional method.

Further, in a character image having a low contrast as shown in FIG. 11A, the maximum density difference is relatively small as shown in FIG. 11B, so that it is shown in FIG. 11C. As described above, according to the conventional method, the image is determined to be a photograph, and the output image is a blurred image with low density as shown in FIG. On the other hand, if the same image is used to discriminate an area by this method, such an area is also determined to be an intermediate area and the threshold value becomes slightly lower, as shown in (e) of FIG.
As shown in FIG. 11 (f), the output image has a sharper contrast and becomes a sharper image than before.

As described above, according to the above embodiment,
The area that seems to be the intermediate area between the text and the photo is set so as to be an intermediate threshold between the threshold for the character processing that emphasizes contrast and the threshold for the photo processing that emphasizes gradation. Even when the judgment is made, it is possible to obtain an image in which the erroneous judgment area is not noticeable.

The present invention is not limited to the above embodiment. For example, the size of the local area for calculating the feature amount is not limited to the area of (5 × 5) pixels shown in the embodiment, and the size of the local area for calculating the dynamic threshold is Then, (3 × 3) pixels were used, but
It can be changed according to the resolution of the image to be processed. Further, the adaptive generation means of the threshold value can be changed, and the dither pattern used for N-value conversion of the photograph part is not particularly limited.
Further, the size of the dither matrix is not limited, and the dither pattern can be threshold-distributed as well as threshold-distributed.

Furthermore, in the above embodiment, the density information is obtained as it is from the image information read and input, but the characteristic amount is obtained by using a value obtained by converting this amount into the image density (logarithm of the reciprocal of the reflectance). It is also possible. Also here
Although the maximum density difference is used as the image feature information when the character region and the photo region are separated, it is of course possible to use other feature information. Others The present invention can be variously modified and implemented without departing from the spirit of the invention.

[0048]

As described above in detail, according to the present invention,
When an image with mixed characters and photographs is separated into image areas and processed to suit each area, an image in which the erroneous judgment area is not noticeable is obtained even if the characters and pictures are erroneously judged in the intermediate area between the characters and pictures. It is possible to provide an image processing device that can do this.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is a diagram showing a configuration example of a maximum density difference calculation circuit.

FIG. 3 is a diagram showing an example of a reference region of (5 × 5) pixels and a dither pattern.

FIG. 4 is a diagram showing a configuration example of a maximum / minimum value calculation circuit in a (3 × 3) pixel.

FIG. 5 is a diagram showing a configuration example of an average value calculation circuit.

FIG. 6 is a diagram showing a configuration example of a corrected average value conversion circuit.

FIG. 7 is a diagram showing a configuration example of a dynamic threshold calculation circuit.

FIG. 8 is a diagram showing a configuration example of a threshold value calculation circuit in an intermediate area.

FIG. 9 is a diagram for explaining a threshold calculation principle of an intermediate region.

FIG. 10 is a diagram for explaining a method of processing a photographic image.

FIG. 11 is a diagram for explaining a character image processing method.

FIG. 12 is a diagram showing an example of a density profile of a photographic image.

FIG. 13 is a diagram showing an example of a density profile of a character image.

FIG. 14 is a diagram showing an example of a photographic image including edges and a density profile.

FIG. 15 is a diagram showing an example of a character image having a low contrast and a density profile.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Line buffer 2 ... Maximum density difference calculation circuit 3 ... Character / photo / intermediate area determination circuit 4 ... Character area threshold calculation circuit 5 ... Intermediate area threshold calculation circuit 6 ... Photo area threshold calculation circuit 7 ... Threshold selection circuit 8 ... Delay circuit 9 ... Comparison circuit 41 ... Maximum / minimum value calculation circuit 42 ... Average value calculation circuit 43 ... Corrected average value conversion circuit 44 ... Dynamic threshold value calculation circuit

Claims (6)

[Claims] 1. A maximum density difference calculating means for calculating a maximum density difference between the target pixel and a peripheral pixel from image information within a predetermined range including a target pixel in an image to be processed, and the maximum density difference calculating means. The determined maximum density difference value is determined using a predetermined threshold value to determine whether the pixel of interest is a character region, a photo region, or an intermediate region, and image information within a predetermined range including the pixel of interest is used to determine the character region. Of the maximum density difference calculated by the maximum density difference calculation means from the dynamic threshold calculation means for calculating the dynamic threshold value and the dynamic threshold value calculated by the dynamic threshold value calculation means and the predetermined fixed threshold value. Intermediate area threshold value calculating means for calculating the threshold value of the intermediate area according to the value of, the threshold value setting means for the photo area for setting the threshold value for multi-valued image information of the photo area, and the pixel of interest by the determination means But the character If it is determined to correspond to the area, select the dynamic threshold from the dynamic threshold calculation means, if it is determined to correspond to the intermediate area, the threshold from the intermediate area threshold calculation means If the image information of the pixel of interest is selected using the threshold value selecting means for selecting the threshold value from the threshold value setting means and the threshold value selected by the threshold value selecting means when it is determined to correspond to the photographic area. An image processing apparatus comprising: a multi-value conversion unit for converting the signal into multi-value. 2. A maximum density difference calculating means for calculating a maximum density difference between the target pixel and peripheral pixels from image information within a predetermined range including the target pixel in the processing target image, and within a predetermined range including the target pixel. The maximum and minimum value calculating means for calculating the maximum value and the minimum value in the predetermined reference area from the image information of 1., and the average value in the predetermined reference area from the image information in the predetermined range including the pixel of interest. Average value calculating means, corrected average value converting means for correcting the average value calculated by the average value calculating means, corrected average value from the corrected average value converting means, and maximum value from the maximum / minimum value calculating means And a minimum value, a dynamic threshold value calculating means for calculating a dynamic threshold value, and a dynamic threshold value calculated by the dynamic threshold value calculating means and a predetermined fixed threshold value are calculated by the maximum density difference calculating means. The maximum density difference Flip the image processing apparatus characterized by comprising an intermediate region threshold calculating means for calculating a threshold value of the intermediate region. 3. A maximum density difference calculating means for calculating the maximum density difference between the target pixel and peripheral pixels from image information within a predetermined range including the target pixel in the image to be processed, and the maximum density difference calculating means. Based on the determined maximum density difference value using a predetermined threshold value, a determination unit that determines whether the pixel of interest is a character region, a photographic region, or an intermediate region, and a predetermined range from image information within a predetermined range including the pixel of interest. A maximum / minimum value calculating means for calculating a maximum value and a minimum value in the reference area; and an average value calculating means for calculating an average value in the predetermined reference area from image information in a predetermined range including the pixel of interest. A corrected average value conversion means for correcting the average value calculated by the average value calculation means, a corrected average value from this corrected average value conversion means, and a maximum value and a minimum value from the maximum / minimum value calculation means. The dynamic threshold of Depending on the value of the maximum density difference calculated by the maximum density difference calculation means, from the dynamic threshold calculation means to be output, and the dynamic threshold calculated by this dynamic threshold calculation means and a predetermined fixed threshold value. An intermediate area threshold value calculation means for calculating a threshold value of the intermediate area, a photograph area threshold value setting means for setting a threshold value for converting the image information of the photograph area into a multi-valued value, and the pixel of interest by the determination means to be a character area. If it is determined that they correspond, select the dynamic threshold from the dynamic threshold calculation means, and if it is determined that they correspond to the intermediate area, select the threshold from the intermediate area threshold calculation means. An image processing apparatus comprising: a threshold selecting unit that selects a threshold from the threshold setting unit when it is determined that the region corresponds to a photographic region. 4. A maximum density difference between the target pixel and peripheral pixels is calculated from image information in a predetermined range including the target pixel in the processing target image, and the calculated maximum density difference is set to a predetermined threshold value. It is used to determine whether the pixel of interest is a character region, a photo region, or an intermediate region, and a dynamic threshold of the character region is calculated from image information within a predetermined range including the pixel of interest, and the calculated dynamic threshold is calculated. And a preset fixed threshold value, the threshold value of the intermediate area is calculated according to the value of the calculated maximum density difference, and the threshold value for multivalued image information of the photographic area is set. If the pixel of interest is determined to correspond to the character area, the dynamic threshold of the character area is selected, and if it is determined to correspond to the intermediate area, the threshold of the intermediate area is selected. , Determined to be compatible with the photo area Comprising the step of selecting the threshold value of the photograph area, and multi-value image information of the target pixel using the selected threshold if. 5. A maximum density difference between the target pixel and peripheral pixels is calculated from image information within a predetermined range including a target pixel in the processing target image, and a predetermined density is determined from image information within a predetermined range including the target pixel. The maximum value and the minimum value in the reference area are calculated, the average value in the predetermined reference area is calculated from the image information in the predetermined range including the target pixel, and the calculated average value is corrected. A dynamic threshold value is calculated from the corrected average value and the calculated maximum value and minimum value, and the calculated maximum density difference is calculated from the calculated dynamic threshold value and a predetermined fixed threshold value. A method comprising the step of calculating a threshold value of the intermediate region according to the value. 6. A maximum density difference between the target pixel and peripheral pixels is calculated from image information within a predetermined range including the target pixel in the image to be processed, and the calculated maximum density difference is set to a predetermined threshold value. It is used to determine whether the pixel of interest is a character region, a photo region, or an intermediate region, and the maximum value and the minimum value in a predetermined reference region are calculated from image information in a predetermined range including the pixel of interest, An average value in a predetermined reference area is calculated from image information in a predetermined range including pixels, the calculated average value is corrected, and the corrected average value thus corrected and the calculated maximum value and minimum value are calculated. Then, the dynamic threshold of the character area is calculated from, and the threshold of the intermediate area is calculated from the calculated dynamic threshold and the fixed threshold determined in advance according to the value of the calculated maximum density difference. Threshold for multi-valued image information of area If the pixel of interest is determined to correspond to the character area by the above determination, the dynamic threshold of the character area is selected, and if it is determined to correspond to the intermediate area, the intermediate value is set. A method comprising the step of selecting a threshold for a region and selecting the threshold for the photo region if determined to correspond to a photo region.