JPH0325580A - Image processing device - Google Patents

Abstract

PURPOSE:To accurately judge a character part and a photographing part by judging the kind of an image by referring to the feature information of a picture element not only in a local area but also in the neighborhood of the area. CONSTITUTION:The feature information of a remarked picture element in which weight is applied on peripheral picture element information stored in a line buffer 27 sequentially with a coefficient decided corresponding to distance between a peripheral picture element and the remarked picture element is calculated as the feature information of the peripheral picture element at a peripheral picture element feature information calculation circuit 26. Meanwhile, the kind of the image is judged by discriminating the maximum density difference obtained by subtracting the maximum density and the minimum density calculated at a maximum value/minimum value calculation circuit 21 with a subtractor 22 with a prescribed threshold value Thb setting standardized maximum density difference divided by means density obtained at a mean value calculation circuit 23 as the feature information of the remarked picture element. A threshold value to be binary coded is decided based on the above result, then, image information is binary coded. In such a way, erroneous judgement for the image can be prevented.

Description

DETAILED DESCRIPTION OF THE INVENTION [Object of the Invention] (Industrial Application Field) The present invention relates to an image processing apparatus that processes a document image in which a text portion and a photograph portion coexist.

(Prior Art) Generally, in an image processing device such as a document image processing device that can handle not only code information but also image information, text and line drawings are processed based on the image information read by a reading means such as a scanner. Image information with contrast is binarized using a fixed threshold value, and image information with gradation characteristics such as photographs is binarized using a pseudo gradation method such as a dither method. This is because if read image information is uniformly subjected to simple binarization processing using a fixed threshold value, resolution will be preserved in areas such as text and line drawings, so image quality will not deteriorate, but in areas such as photographs, image quality will not deteriorate. The gradation is not preserved, resulting in an image with degraded image quality. On the other hand, if read image information is uniformly gradated using systematic dithering, etc., the gradation will be preserved in areas such as photographs, so image quality will not deteriorate; In this case, the resolution deteriorates and the image quality deteriorates.

In this way, if the read image information is binarized using a single binarization method, the image quality of both the text/line drawing area and the photo area can be satisfied at the same time. It is impossible to obtain an image.

Therefore, in document image processing, it is essential to separate image information into regions according to the characteristics of the image and perform adaptive processing on each region. This also applies to various types of image processing; for example, if processing is not performed that matches the characteristics of the image, the image quality may deteriorate when enlarging or reducing a binarized image, or when encoding an image. If processing is not performed using a compression method that matches the characteristics, data compression will be inefficient.

Therefore, as disclosed in Japanese Patent Application Laid-Open No. 58-3374, for example, as a method for simultaneously satisfying the resolution of text areas and the gradation of photographic areas, image density is increased in local areas within the image plane. By calculating the maximum density difference ΔD + gax and comparing this maximum density difference ΔD wax with the determination threshold Th, the region is separated into text/line drawing regions and photograph regions, and binarized according to the characteristics of each image region. Methods for switching methods are known.

Here, "density" means the image signal level read by the reading means, and is different from the commonly used "density". below,
Unless otherwise specified, "concentration" is used in this sense.

However, the above-mentioned method has the disadvantage that in a photographic image, an area where the density changes rapidly is erroneously determined to be text, resulting in deterioration of gradation. For example, the image density dynamic range is set to 8 bits (0~255:
(0 to FF [hex] in hexadecimal), in the case of a character image, the frequency distribution of the maximum density difference ΔD wax is the 10th
As shown in the figure, the extreme values are near 0[hexco and FF[hexl]. Pixels that take a value near this FF [hex] are pixels that include the edge part of the character within a predetermined range, and pixels that take a value near 0 [hex] are all pixels within the predetermined range that are background pixels or pixels that take a value near 0 [hex]. A pixel inside a character that does not include edges. In addition, in the case of a photographic image, since local density changes are relatively small, the maximum density difference ΔD■aX within a predetermined range is determined by O Chex as shown in FIG.
] Concentrate in the vicinity. The two originals of text and photos with such frequency distribution are set to a predetermined threshold, e.g., rTh-7.
0 [hex] J is used to identify the type of image under the following conditions. In the case of a character image, pixels with the maximum density difference ΔD wax in the area indicated by ■ in FIG. 10 are determined to be characters; Maximum density difference ΔD Ilax in the area indicated by ■
Pixels with this value are incorrectly determined to be photographs. On the other hand, in the photographic image, the maximum density difference △ in the area indicated by ■ in Figure 11
A pixel having DrAax is determined to be a photograph, but a pixel having the maximum density difference ΔDwax in the area indicated by ■ is erroneously determined to be a text. This erroneous determination of a photographic image means that a pixel within a predetermined range with a sharp change in density, such as the outline of a face, is determined to be a character, which results in deterioration of image quality due to a decrease in gradation. Portions in a photograph where the density changes rapidly are visually conspicuous areas, and erroneous determination of these areas can cause significant deterioration in image quality.

In this way, when distinguishing between text/line drawings and photographs using the maximum density difference ΔD Ilax as feature information, in photographic images, pixels that include areas with large density changes within a predetermined range may be incorrectly determined to be characters. Therefore, it is not possible to accurately separate image areas, and therefore it is not possible to perform binarization processing adaptively and accurately according to the characteristics of the image. At the same time, there was a drawback that a satisfactory image could not be obtained.

(Problems to be Solved and Attempted by the Invention) As described above, this invention distinguishes between text/line drawings and photographs using the maximum density difference as characteristic information. Pixels that include large areas are incorrectly determined to be characters, making it impossible to accurately separate image areas, making it impossible to perform binarization processing adaptively and accurately according to image characteristics, and character parts cannot be accurately separated. This was done to eliminate the drawback that it is not possible to obtain an image that satisfies the resolution of the image and the gradation of the photographic area at the same time. Image regions can be separated, and therefore, by adaptively and accurately performing binarization processing according to the characteristics of the image, it is possible to obtain an image that satisfies both the resolution of text and the gradation of photographs. The purpose is to provide an image processing device.

[Structure of the Invention] (Means for Solving the Problems) The image processing device of the present invention includes a feature extraction means for extracting feature information of a pixel of interest from image information within a predetermined range including the pixel of interest in an image to be processed. , storage means for sequentially storing feature information of the pixel of interest extracted by the feature extracting means as surrounding pixel information; and a positional relationship between the pixel of interest and surrounding pixels with respect to the surrounding pixel information stored in the storage means. surrounding pixel feature information calculation means for calculating feature information of surrounding pixels by weighting according to the surrounding pixel; and feature information extracted by the feature extraction means based on the feature information of the surrounding pixels calculated by the surrounding pixel feature information calculation means. determining means for determining the type of image of the pixel of interest by correcting the corrected feature information and discriminating the corrected feature information using a predetermined threshold; The pixel of interest comprises a threshold determining means for determining a threshold for binarizing the image information, and a binarizing means for binarizing the image information of the pixel of interest using the threshold determined by the threshold determining means. .

(Function) According to the present invention, in a document containing a mixture of text and photographs, photographic areas are rarely dispersed in minute units;
Taking advantage of the property that pixels exist in a concentrated state in a predetermined area on a document, characteristic information of pixels surrounding a pixel of interest at that time when those surrounding pixels are the pixel of interest is sequentially stored. The surrounding pixel information consisting of the above is weighted by a coefficient determined according to the distance between the surrounding pixel and the pixel of interest, and the information is set as the feature information of the current surrounding pixel, and the information of the pixel of interest extracted by the feature information extraction means is The type of image of the pixel of interest is determined by discriminating the corrected feature information obtained by correcting the feature information with the feature information of the surrounding pixels using a predetermined threshold, and the image information of the image of interest is binarized based on this determination result. A threshold value is determined, and the image information of the pixel of interest is binarized using the determined threshold value. In this way, by performing identification that takes into account the characteristic information of surrounding pixels for photo pixels that are concentrated and distributed in a predetermined area, erroneous determination of photo areas can be suppressed and text areas and photo areas can be accurately identified. This makes it possible to perform binarization processing according to the characteristics of each image.

(Example) Hereinafter, an example of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing the structure of an image processing apparatus according to the present invention. This image processing device inputs image information S1 read by a reading device such as an image scanner (not shown) as digital data of 8 bits per pixel, for example, and performs binarization processing to generate a binarized image signal S2. This outputs the following. The line buffer 1 temporarily stores such image information S1 and provides it for image processing (binarization processing) to be performed below.

The identification means 2 in the figure has the following functions. That is, the identification means 2 manually inputs the image information 83 to S6 that the line buffer 1 outputs in synchronization with a predetermined clock, and uses the image information 83 to S6 to determine maximum density Dsaxq and minimum density D+e as feature information in a local area including the pixel of interest.
Ins and average concentration Da are determined respectively, and from these,
The maximum density difference ΔDn normalized by the average density Da as characteristic information of the pixel of interest is determined. Next, the minimum concentration D IIi
If n is larger than a predetermined threshold value, it is determined that there is a high possibility that it is a photographic pixel, and the feature amount (surrounding pixel information) of the surrounding pixels is determined as the normalized maximum density difference ΔDn according to the distance from the pixel of interest. Add feature information of surrounding pixels weighted by coefficients. Conversely, if the minimum density Diin is smaller than a predetermined threshold value, it is determined that there is a high possibility that the pixel is a character pixel, and characteristic information of surrounding pixels is not added. Based on the results of such processing, it is determined whether the image information of the local area exhibits characteristics unique to a text portion or characteristics of a photograph portion, thereby identifying the type of image and outputting a selection control signal S7. be.

The selection control signal S7 from the identification means 2 is supplied to the selector 3 and used as a threshold switching signal. That is, either the first threshold Th1 from the first threshold memory 4 or the second threshold Th2 such as a dither matrix from the second threshold memory 5 is used for binarizing the image information S1. It is selectively extracted as the threshold Th. Then, the image information S8 read from the line buffer 1, delayed by a predetermined timing in the delay memory 6, and supplied to the comparator circuit 7 is binarized by the threshold Th extracted by the selector 3. It is output as an image signal S2.

Note that the first threshold Thl is dynamically calculated in the dynamic threshold calculation circuit 8 according to the input image information S1 (details will be described later).

Here, the local area including the pixel of interest is "4 x 4 pixels".
Assuming that an area is set, characteristic information of the pixel of interest is determined, and image type identification processing is executed by the identification means 2, a 3-line buffer is used as the line buffer 1. The identification means 2 then identifies this 3-line buffer 1.
Image information 8 that is input in parallel for each 4 pixels in the column direction from
3 to S6 are subjected to signal processing as shown below.

That is, the identification means 2 determines the maximum density value D saw and the minimum density value D in a local area of "4 x 4 pixels" from the image information 83 to S6 read from the line buffer 1.
A maximum/minimum value detection circuit 21 which calculates the respective gains and outputs them as a maximum density signal S21 and a minimum density signal S22, and inputs the maximum density signal S21 and minimum density signal S22 from this maximum/minimum value detection circuit 21, A subtracter 22 is provided to obtain a maximum density difference ΔDwax representing the difference between the maximum density value Daax and the minimum density value D10 from these forces 1 and output it as a maximum density difference signal 323.

The maximum density difference ΔD wax obtained by the maximum value/minimum value detection circuit 21 and the subtracter 22 is used as the first feature information of the image in the local area.

Further, the average value calculation circuit 23 of the identification means 2 calculates the average density value Da in the local area from the image information 83 to S6 read from the line buffer 1, and calculates the average density value Da in the local area.
This is what is output as.

The average density Da calculated by the average value calculation circuit 23 is used as second feature information of the image in the local area.

Further, the divider 25 of the identification means 2 receives the maximum concentration difference signal 823 output from the fI & calculator 22 as the first characteristic information.
is divided by the average density signal S24 output as the second characteristic information from the average value calculation circuit 23 to obtain the normalized maximum density difference ΔDn, which is output as the normalized maximum density difference signal S25.

This normalized maximum density difference ΔDn is used as characteristic information of the pixel of interest for identifying the type of image information.

Further, the determining means 24 in the identifying means 2 inputs the minimum density signal S22 supplied from the maximum value/minimum value detection circuit 21, and when the minimum density Dmln within a predetermined range including the pixel of interest is larger than a predetermined threshold value, the It is determined that there is a high possibility that the pixel is a photograph, and correction is performed by adding the characteristic information of the surrounding pixels weighted by the weighting circuit 28 to the normalized maximum density difference signal S25, which is the characteristic information of the pixel of interest. Corrected feature information is calculated and discriminated using a predetermined threshold Thb to determine the type of image information in the local area. Then, according to this determination result, a selection control signal S7 is generated to determine a threshold Th for binarizing the image information S1,
Controls threshold selection by selector 3.

The determination means 24 includes an addition circuit that adds characteristic information of surrounding pixels to the normalized maximum density difference ΔDn, which is characteristic information of the pixel of interest in the image, and a minimum density D m1n and a predetermined threshold value The.
and a selector that selects whether to supply characteristic information of peripheral pixels from the weighting circuit 28 or a predetermined constant to the addition circuit according to the comparison result of the first comparison circuit. and a second comparison circuit that compares the addition result of the addition circuit with a predetermined threshold Thb. The determining means 24 determines the type of image according to the comparison result between the normalized maximum density difference ΔDn (corrected characteristic information), which is obtained by adding characteristic information of peripheral pixels based on the comparison result of the second comparison circuit, and the threshold Thb. The selection control signal S7 shown in FIG. That is, when the value corrected by adding characteristic information of surrounding pixels to the normalized maximum density difference ΔDn is larger than a predetermined threshold Thb, the type of image is determined to be a text portion, and when it is smaller, the type of image is determined to be a photo portion. It is determined that

The surrounding pixel feature information calculation circuit 26 is composed of a line batzer 27 and a weighting circuit 28. The line buffer 27 temporarily stores the normalized maximum density difference ΔDn as peripheral pixel information, and is used to calculate characteristic information of peripheral pixels. In this embodiment, since the reference range of peripheral pixels is the area shown in FIG. 8, a two-line buffer is provided. The weighting circuit 28 sequentially inputs the peripheral pixel information stored in the line buffer 27 in synchronization with a predetermined clock, and indicates characteristic information of the peripheral pixels weighted by a coefficient determined according to the distance from the pixel of interest. A surrounding pixel feature signal S26 is generated.

Now, the first feature information (
The maximum density difference ΔDiax) and the second characteristic information (average density Da) output by the average value calculation circuit 23 are obtained as follows.

FIG. 2 is a block diagram showing the structure of the maximum value/minimum value detection circuit 21. As shown in FIG. The maximum value/minimum value detection circuit 21 detects the pixel of interest in the image to be processed, as shown in FIG. Maximum value DlaX and minimum value Dwln of concentration
and, respectively.

That is, the maximum/minimum value detection circuit 21 receives an 8-bit image per pixel that is sequentially input in units of 4 pixels in the column direction from the line buffer 1 in synchronization with the clock CLK, as shown in FIG. The information 83 to S6 is sent to the comparators 21b, 21c, 21d, 2 by the selector 21a.
1e sequentially. Comparators 2lb and 21 by the selector 21a of the image information 83 to S6 input in column units
The distribution to c, 21d, and 21e is based on the selection signals SEO and SE from the counter 21h that operates in response to the clock CLK.
I, the output terminals AO-3, BO- of the selector 21a
3, CO-3. Select DO-3 sequentially and display image information 83~
This is done by outputting S6. And comparator 2
lb, 21c, 21d. 21e compares the image information in units of four pixels in the column direction, and determines the maximum density and minimum density in each column. Next stage comparator 21
f, 21g are the comparator 2 l b. 2 1 c
, 2 1 d, 2 1 e to EDG
The maximum value and minimum value inputted at the timing I, respectively determined in the column direction, are compared in the row direction, and the maximum value and minimum value among them are respectively determined. Through the above processing, the maximum density value D■aX and minimum density value D■In within the "4x4 pixel" area shown in FIG. Output.

The subtracter 22 calculates the maximum density value DI obtained in this way.
The maximum density difference ΔD■aX, which is the first characteristic information, is determined from aX and the minimum density value Dso1n using the following equation.

ΔDsax − D+sax − Daln
- (2) Maximum density difference A which is this first characteristic information
D laX is given to a divider 25 .

On the other hand, the average value calculation circuit 23 for calculating the average density value Da, which is the second characteristic information, is configured as shown in FIG. 6, for example. This average value calculation circuit 23, like the maximum value/minimum value detection circuit 21 described above, is connected to the clock C from the line buffer 1.
The selector 23 selects image information 83 to S6 of 8 bits per pixel, which is sequentially input in column direction 1 in units of 4 pixels in synchronization with LK.
adder 23b. 23c. It is distributed sequentially to 23d and 23e. Image information S3 to S6 manually input for each column
Adders 23b, 23c, 23d by selector 23a of
, 23e is based on the selection signal SE2. SE3 selects output terminal AO-3. of selector 23a. BO-3. Co-3
, Do-3 are sequentially selected and image information 83 to S6 are output. And adders 23b, 23c
．． 23d and 23e add image information in the column direction in units of four pixels, and output the sum of image densities in each column. The next stage adder 23f includes these adders 23b,
By adding the sum of the density values of four pixels in the column direction obtained by 23c, 23d, and 23e over four rows,
The sum of the density values in the local area of "4 x 4 pixels" mentioned above is calculated. By dividing the sum of the density values by the number of pixels [16] constituting the local area using the divider 23g, the average density Da of the local area is obtained as second feature information.

The divider 25 shown in FIG. 1 divides the maximum density difference ΔD saw thus obtained by the average density Da to obtain the normalized maximum density difference Dn using the following equation.

ΔDn=ΔDmax/Da=・(3)
Further, FIG. 7 shows the structure of the weighting circuit 28. The shift registers 31 and 32 have 8-bit x 5 serial in/parallel out functions, and the shift register 31 stores peripheral pixel information on the line two lines before the pixel of interest, and the shift register 32 stores peripheral pixel information on the line before the pixel of interest. It stores pixel information. Also, shift register 3
0 has an 8-bit x 2 serial in◆parallel out function, and stores peripheral pixel information of the previous pixel and the pixel before the pixel of interest. Also, the multiplier 33.
... weights the peripheral pixel information output by the shift registers 30, 31, and 32 according to the distance from the pixel of interest. In this embodiment, the values shown in FIG. 9, for example, are used as the weighting coefficients for peripheral pixels. Adder 3 4
a r 3 4 b *34c, 34d calculates the sum of surrounding pixel information weighted by the multipliers 33... to generate feature information SFO of surrounding pixels. Note that in comparison S35, the feature information SF of this peripheral pixel
0 and a predetermined threshold value Tha, and supplies a signal S26 indicating the determination result to the determining means 24.

The surrounding pixel feature information SFO is determined by the following equation.

SFO−Σ (kn)XΔDn (i)) −
(4)i Here, k (i) is a weighting coefficient, and in this example, the values shown in FIG. 9 were used as coefficients. Also, ΔDn
(i) is the normalized maximum density difference of the peripheral pixel L, which is "1" when the peripheral pixel i is determined to be a character, and "-1" when the peripheral pixel i is determined to be a photograph. Then, the comparator 35 performs discrimination using a predetermined threshold value Tha, and if the SFO is larger than Tha, the surrounding pixels are judged to be characters, and equation (5) is output, and if it is less than Tha, the surrounding pixels are judged to be photos. (6)
Print the expression.

If SFO>Tha, SFI-SFO...(5) SFO≦T
If ha, SFI- (-1) That is, if D sin is smaller than the predetermined threshold The, the pixel of interest is likely to be a background portion, and the normalized maximum density difference ΔDn of the pixel of interest is set to the predetermined threshold Th without weighting.
The type of image is determined by discrimination using b. The determination formula is shown below.

However, if Diin is larger than the predetermined threshold The, the normalized maximum density difference ΔDn of the pixel of interest is added to the surrounding pixel feature information SF.
The result of adding I is discriminated using a predetermined threshold Thb to determine the type of image. The determination formula is shown below.

The determining means 24 (see FIG. 1) determines the pixel of interest as a character and outputs "1" if the normalized maximum density difference ΔD n s ΔDn+SF1 is larger than Thb, and in the following cases, determines the pixel of interest as a photograph. It makes a judgment and outputs "0".

Note that the first threshold value Thl selected by the selector 3 according to such a determination result is generated by the dynamic threshold value calculation circuit 8 according to the image information. Specifically, the maximum density value D sax obtained by the maximum value minimum value detection circuit 21
According to the minimum density value Dsin, the threshold value Bh for binarizing the image information S1 is set as, for example, Bh − (Dsax + Dm1n ) /2 −
(9) is dynamically determined and stored in the first threshold memory 4.

On the other hand, the second threshold Th2 for binarizing the photographic area is given as dither pattern information (dither matrix) as shown in FIG. 4, for example, and is stored in the second threshold memory 5. There is.

Such threshold value Bh (first threshold value Th1) or the threshold value indicated by the dither pattern (second threshold value Th2) is selectively extracted by the selector 3 based on the determination result of the determination means 24, and It is used as the binarization threshold Th.

As mentioned above, in a manuscript containing a mixture of text and photographs, the photographic areas are rarely dispersed in minute units, but are concentrated in a predetermined area on the manuscript. Regarding the surrounding pixel information, which is formed by sequentially storing feature information of the pixel of interest at that time in the tine buffer 27 when the surrounding pixels are the pixel of interest, The surrounding pixel feature information calculation circuit 26 calculates the weighted information using a coefficient determined according to the distance as the feature information of the surrounding pixels, and the maximum density D calculated by the maximum/minimum value calculation circuit 21
The normalized maximum density difference Dn obtained by dividing the maximum density difference ΔDlaX obtained by subtracting laX and the minimum density Dmln by the subtractor 22 by the average density Da obtained by the average value calculation circuit 23 is calculated as the characteristic information of the pixel of interest. The type of image of the pixel of interest is determined by discriminating the corrected feature amount corrected by the feature information of the surrounding pixels using a predetermined threshold Thb, and the threshold value is used to binarize the image information of the image of interest based on this determination result. Since Th is determined and the image information of the image of interest is binarized using this determined threshold, the maximum density difference ΔD
Identification using only wax can eliminate the drawback that pixels in a photographic image that include areas with sharp density changes (for example, the outline of a face) within a predetermined range are misjudged.

In other words, the type of image is determined by referring not only to the feature information in a local region, but also to the feature information of surrounding pixels, so even if a pixel is incorrectly determined based only on the feature information of the pixel of interest, It is now possible to reliably identify the type of image. As a result, it is possible to accurately determine text and photo parts, and in a document image in which multiple i-class information exists, text parts can be binarized with good resolution, and photo parts can be binarized with high resolution. It is possible to binarize while preserving gradation.

Note that when identification is performed using the maximum density difference ΔD wax within a predetermined range as a feature quantity, the background area of the character image is determined to be a photograph. There are many background pixels around the text area that are determined to be photos, so if the character area is identified by adding the feature information of the surrounding pixels to the feature information of the pixel of interest, even the edges of the text will be judged as photos. There is a risk that this may occur. Therefore, for pixels judged to have a high possibility of being a text image, identification is not performed taking into account the characteristic information of the surrounding pixels, and only for pixels judged to have a high possibility of being a photographic image, the above-mentioned surrounding pixels are identified. Identification is performed taking characteristic information into consideration. This makes it possible to prevent the edge portion of a character image from being erroneously determined to be a photograph. At this time, it is determined as follows whether the pixel of interest is more likely to be a character pixel or a photographic pixel. In other words, in the case of a character image, many of the surrounding areas of the edge area are background pixels, so the minimum density D sin within the predetermined range is small.

Utilizing this, if the minimum density D win within the predetermined range is smaller than the predetermined threshold value The, it is determined that there is a background part of the document within the predetermined range, and it is determined that there is a high possibility that it is a character pixel. Conversely, if the minimum density within the predetermined range is greater than the predetermined threshold value The, it is determined that there is no background part of the document within the predetermined range, and the pixel is determined to have a high possibility of being a photograph. In this way, by performing identification that takes into account characteristic information of surrounding pixels only for photographic pixels that are concentrated and distributed in blocks, it is possible to suppress misjudgment of photographic areas and to accurately identify text and photographic areas. ing.

Note that the present invention is not limited to the above embodiments.

For example, the area of the predetermined range is not limited to "4x4 pixels" and may be configured to be variably set depending on the image to be processed. Similarly, the reference area of peripheral pixels is not limited to the area shown in FIG. 8. Further, the means for adaptively generating the threshold value can be modified in various ways, and the dither pattern used for binarizing the photographic area is not particularly limited. Further, the size of the dither matrix is not limited either, and the dither pattern can be arranged not only in a dot-distributed manner but also in a dot-concentrated manner.

Furthermore, in this example, the maximum density difference normalized by the average density within a predetermined range was used as the characteristic information, but this is because images with small contrast with the background, such as pencil-drawn manuscripts and newspaper manuscripts, can also be identified as characters. However, the characteristic information is not limited to this. Furthermore, in the present invention, the value of the feature information and the determination threshold are calculated based on the image signal read by the reading device, that is, the amount corresponding to the reflectance of the image information. The value converted to the logarithm of
Furthermore, identification may be performed based on a converted signal that takes human visual characteristics into consideration.

[Effects of the Invention] As explained above, according to the present invention, it is possible to eliminate misjudgments in areas with large density changes in a photographic image, and perform accurate separation of image areas, thereby performing binarization processing according to the characteristics of the image. By applying this adaptively and accurately, it is possible to provide an image processing apparatus that can obtain an image that satisfies both the resolution of the text portion and the gradation of the photographic portion.

[Brief explanation of drawings]

The figures show an embodiment of the present invention, in which Fig. 1 is a block diagram showing the configuration of the image processing device of the present invention, Fig. 2'' is a detailed block diagram showing the structure of the maximum value/minimum value detection circuit, Figure 3 is a diagram showing an example of a local area for explaining the operation;
The figure shows an example of a dither pattern, Figure 5 is a timing chart for explaining the operation of the maximum value/minimum value detection circuit, Figure 6 is a detailed block diagram showing the structure of the average value calculation circuit, and Figure 7 is a diagram showing an example of a dither pattern. is a block diagram showing the configuration of a weighting circuit, FIG. 8 is a diagram for explaining the reference range of peripheral pixels, FIG. 9 is a diagram for explaining weighting coefficients that weight peripheral pixels, and FIG. 10 is a typical diagram. FIG. 11 is a diagram for explaining the frequency distribution of the maximum density difference of a typical photographic image. 1... Line buffer, 2... Identification means, 3...
Selector (threshold value determining means), 4... First threshold memory, 5... Second Mfli memory, 6... Delay memory, 7... Comparison circuit (binarization means), 8... - Dynamic threshold calculation circuit, 21... Maximum value/minimum value detection circuit (feature extraction means), 22... Subtractor (feature extraction means), 23...
- Average value calculation circuit (feature extraction means), 24... Judgment means, 25... Divider (feature extraction means), 26... Surrounding pixel feature information calculation circuit (surrounding pixel feature quantity calculation means),
27... Line buffer (storage means), 28... Weighting circuit.

Claims (1)

[Scope of Claims] Feature extraction means for extracting feature information of a pixel of interest from image information within a predetermined range including the pixel of interest in an image to be processed; and feature information of the pixel of interest extracted by the feature extraction means. A storage means for sequentially storing peripheral pixel information, and calculating characteristic information of peripheral pixels by weighting the peripheral pixel information stored in the storage means according to the positional relationship between the pixel of interest and the peripheral pixels. Surrounding pixel feature information calculation means; Correcting the feature information extracted by the feature extraction means using the feature information of the surrounding pixels calculated by the surrounding pixel feature information calculation means to calculate corrected feature information; a determining means for determining the type of image of the pixel of interest by making a discrimination using a predetermined threshold; and a threshold determining means for determining a threshold for binarizing the image information of the pixel of interest according to the determination result of the determining means. , and binarizing means for binarizing the image information of the pixel of interest using the threshold determined by the threshold determining means.