JP2624427B2 - Image discriminating device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image discriminating apparatus for discriminating whether binary image data is a photographic image or a character image.

[0002]

2. Description of the Related Art In a facsimile apparatus, 200 × 2
When pixel density conversion of received data of 00 dpi into a recording pixel size of 400 × 400 dpi, a method of performing smoothing correction for smoothing the outline of a character is known (Japanese Patent Application Laid-Open Nos. Hei 3-82267 and Hei 3-82267). 822
No. 68).

[0003] Even if this character smoothing correction is effective when applied to a character image, when applied to a photographic image, gradation is lost and image quality is degraded. The cause is that when the image is enlarged twice in the main scanning direction and the sub-scanning direction, the character may be enlarged by a signal different from the received data in order to smooth the outline of the character. However, since the density of binary image data of a photographic image is expressed by area modulation by a dither method or an error diffusion method, the density of a single area changes in smoothing correction of characters.

Therefore, there has been conventionally known a method of judging whether received data is a character image or a photographic image, and automatically controlling whether or not to perform smoothing correction in accordance with the result. For example, Japanese Patent Application Laid-Open No. 3-254276 discloses that in a reference area of 6 (sub-scanning direction) × 9 (main scanning direction) pixels, a majority decision of a judgment result based on a spatial frequency, a periodicity, and a pixel isolation of a received image is performed. A method is described in which an image area is separated from a character area and a photograph area, and smoothing correction is performed only on the character area.

The discrimination between a character image and a photographic image is a technique required not only in the facsimile field described above but also in various fields dealing with image data.

[0006]

Generally, the more pixels that are referred to for discriminating between a character image and a photographic image, the more accurate the discrimination becomes. In this regard, FIG. 9 and FIG.
0 will be described.

FIG. 9 shows a pseudo halftone expression by the dither method. Here, it is assumed that a uniform density area of 8 × 8 pixels is dithered using a 4 × 4 threshold matrix having a threshold arrangement as shown in the upper left of FIG. Each pixel is expressed in black if its density is equal to or greater than the value of the corresponding position in the threshold matrix, so that a region with a density of 0 (white), as shown in FIG.
The area of density 1 is as shown in (b), and the area of density 2 is (c).
like,. . . , The area of density 15 is as shown in (q),
The density is expressed by the area ratio between black and white. Although not shown, all pixels in the black area are black pixels.

FIG. 10A shows an example of a character image.
FIG. 9B shows an example of a dither-processed photographic image, which corresponds to the pattern of the area having the density 8 shown in FIG.

It is assumed that character / photo discrimination is performed on the character image and the photographic image with reference to a 4 × 4 matrix area including the pixel of interest. For example, if attention is paid to a pixel with an asterisk, the pattern of the 4 × 4 reference area is as follows.
In the case of a character image, the pattern is as shown in (c), and in the case of a photographic image, as in (d), both patterns are the same. That is, in the 4 × 4 reference area, character / photo discrimination is impossible.

In this example, the reference area is 4 (sub-scanning direction).
If it is enlarged to a matrix of × 8 (main scanning direction), the pattern of the reference area becomes different between the character image and the photographic image as shown in (e) and (f), so that the character / photo discrimination is possible. Becomes

If the reference area is enlarged as described above, the accuracy of character / photo discrimination can be improved. For this reason, even in the example shown in the above-mentioned JP-A-3-254276, 6
A reference area of × 9 (54 pixels) is used.
However, when the number of reference pixels increases, there is a problem that a circuit for character / photo identification becomes extremely complicated and expensive.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems, and has as its object to provide an image discriminating apparatus for discriminating a character image and a photographic image with high accuracy without increasing a reference area. .

[0013]

In order to solve the above-mentioned problems, a first aspect of the present invention provides a method for each pixel of binary image data.
Means for determining whether there are more or less changes in the pixel value in the reference area than a certain reference, and counting the number of consecutively appearing pixels determined to have more changes in this means, Means for determining that the image is a photographic image when the numerical value is equal to or more than a predetermined value, and determining that the image is a character image when the numerical value is not equal to the predetermined value.

According to a second aspect of the present invention, for each pixel of the binary image data, a judging means for judging whether or not a change point of the pixel value in the reference area is larger or smaller than a certain reference, A first counting means for counting the number of continuously appearing pixels whose number is determined to be large, and a second counting means for counting the number of continuously appearing pixels whose number of change is determined to be small by the determining means. Counting means, and when the count value of the first counting means is equal to or greater than a predetermined value and the count value of the second counting means is less than a predetermined value, the image is determined to be a photographic image, and the counting of the first counting means is performed. Means for determining that the image is a character image when the numerical value is less than the predetermined value and the second count value is equal to or more than the predetermined value, and under other conditions, means for performing the same determination as the immediately preceding pixel. is there.

According to a third aspect of the present invention, for each pixel of the binary image data, a judging means for judging whether the pixel value change point in the reference area is larger or smaller than a certain reference, and a continuous predetermined number of pixels Means for determining whether the image is a photographic image or a character image based on the number of pixels determined to have a large or small number of pixel value changes by the determination means. is there.

[0016]

According to the first to third aspects of the present invention, discrimination between a photographic image and a character image is performed by using the results of judging the number of pixel value change points for a plurality of continuous pixels in an accumulated form. Since the size of the reference area can be regarded as being enlarged compared to the reference area of each pixel, it is impossible to determine the size of the reference area to a minimum and determine the size of the reference area. Such an image can also be determined.

As will be described in more detail with reference to the embodiments described below, in a binary character image and a photographic image, when the pixel value change in the reference area is examined in the main scanning direction and the sub-scanning direction, On the other hand, it is recognized that pixels having both large numbers of pixel value change points in both the sub-scanning directions tend to appear continuously, while character images have a small number of such pixels and a small number of continuous pixels. .

According to the first aspect of the invention, a region where a predetermined number of pixels determined to have a large number of pixel value change points continues for a predetermined number or more is determined as a photographic image, and a region other than that is determined as a character image. .

In a photographic image area, a pixel having a small number of pixel value changes may appear locally in a continuous area of a pixel having a large number of pixel value changes. According to the first aspect, such a pixel may be determined to be a character image.

According to the second aspect of the present invention, the image is determined based on both the continuous number of pixels having a large number of pixel value change points and the continuous number of pixels having a small number of pixel value change places. In order to perform image discrimination based on the number of pixels having a large or small number of pixel value change portions included in a predetermined continuous plurality of pixels, a region of a pixel having a small number of pixel value change portions locally appearing in a photographic image region, or vice versa,
It is also possible to correctly determine a region of a pixel having a large number of pixel value change portions that appears locally in the character image region. Further, according to the third aspect, it is easy to avoid the influence of noise, and it is possible to stably perform image discrimination in a large unit (for example, one line unit).

[0021]

FIG. 1 is a block diagram of a recording apparatus according to a first embodiment of the present invention. In the present embodiment, 200 × 200 dpi image data such as facsimile reception
This is an example in which pixel density is converted to a recording pixel size of 00 × 400 dpi and recording is performed.

In FIG. 1, reference numeral 1 denotes a storage unit having a memory capacity for one page, which is used for storing image data transferred to a terminal 8 from an external circuit (not shown). Numeral 2 denotes a correction table section composed of a ROM or the like, which performs pixel density conversion and character smoothing correction or photograph smoothing correction, and an operation for determining whether there are many pixel value changes in the reference area (hereinafter referred to as a correlation operation). And outputs the result as a non-correlated signal a. Reference numeral 3 denotes an area determination unit that determines whether the image is a character image or a photographic image by using the correlation calculation results of the correction table unit 2 in an accumulated form, and returns the determination result to the correction table unit 2 as a determination signal b. In this embodiment, a counter circuit operates as described later. Reference numeral 4 denotes a storage unit for storing image data (correction data) subjected to pixel density conversion and smoothing correction by the correction table unit 2, and has a memory capacity for one page. Reference numeral 5 denotes a recording unit that records image data stored in the storage unit 4 on recording paper at 400 × 400 dpi. Reference numeral 6 denotes a control unit that controls the above-described units.

The operation of the recording apparatus configured as described above will be described below. First, the control unit 6 outputs the clear signal CLR to clear the storage units 1 and 4 and the area determination unit (counter circuit) 3.

Next, the control section 6 outputs a clock SCLK. Image data SiN for one page is sequentially transferred to the terminal 8 by an external circuit (not shown) in synchronization with the clock SCLK. This image data is sequentially written to the storage unit 1 in synchronization with the clock SCLK.

When the image data for one page is stored in the storage unit 1, the control unit 6 stops sending the clock SCLK, stops the transfer and storage of the image data, and sets another clock RC
LK is output. The storage unit 1 stores data DAT (0, 0, 16) of 16 pixels (reference pixels) of a 4 × 4 matrix (reference area) including a target pixel to be processed in synchronization with the clock RCLK.
0) to DAT (3, 3) are output. Correction table section 2
Receives the reference pixel data as input, performs pixel expansion of the pixel of interest twice in the main scanning direction and the sub-scanning direction, and performs smoothing correction for a character image or a photographic image.
The correction data CDT0 to CDT3 of × 2 pixels are output, and a correlation operation is performed on the reference pixels.

FIG. 2 is an explanatory diagram of the reference pixel and the correction pixel for the target pixel. In FIG. 2, DAT
(1, 1) is the data of the target pixel.

The value of the twice-enlarged pixel of the target pixel is determined based on reference pixel data of a 4 × 4 matrix. For the type of smoothing correction, a smoothing correction for a photo is selected when the output signal b of the area determination unit 3 is "1" (photo image), and a smoothing correction for a character is obtained when b = "0" (character image). Correction is selected. The correction data is clock R
The data is sequentially written to the storage unit 4 in synchronization with the CLK. FIG.
Indicates the operation timing at this time.

Here, the contents of the correlation calculation in the correction table section 2 will be described. FIG. 4 is a flowchart thereof.

First, the counter COUNT used in the processing
A, COUNTB, I, J are cleared to zero (S
1). The counters I and J indicate the relative coordinates of the pixels in the reference area in the sub-scanning direction and the main scanning direction, and the coordinates of one pixel are indicated by (I, J).

Next, DAT (0, 0), DAT (0, 1), and DAT (0, 1) for four pixels on the first line (J = 0)
(0,1) and DAT (0,2), DAT (0,2) and DAT
AT (0, 3) is sequentially compared, and the counter COUNTA is incremented each time there is a mismatch (S2 to S).
5). That is, for the first line, locations where pixel values adjacent in the main scanning direction are different (pixel value change locations) are counted.

Next, the counters I and J are cleared to zero (S
After 6), the number of change points of the pixel value in the sub-scanning direction is counted from the first line (S6 to S12). Specifically, DAT (0,0), DAT (1,0),... Between the first and second lines. . . , DAT (0,3) and DAT
(1,3) are compared in order, and then DAT (1,0) and DAT (2,2) between the second and third lines.
0),. . . , DAT (1,3)) and DAT (2,3)
, And finally, DAT (2,0), DAT (3,0),... Between the third and fourth lines. . . , D
The comparison between AT (2,3) and DAT (3,3) is performed in order, and the counter COUTA is incremented each time the comparison does not match.

Next, the counters I and J are cleared to zero (S1).
After 3), for the first column (I = 0), the values of the pixels adjacent in the sub-scanning direction are compared, and the unmatched portions are counted by the counter COUTB (S14 to S17). Following this, the DATs from the first row in the main scanning direction
(0,0) and DAT (1,0),. . . , DAT (2,
0) and DAT (3,0), DAT (0,0) and DAT
(0,1),. . . , DAT (3,0) and DAT (3,3)
1), DAT (0,1) and DAT (0,2),. . . ,
DAT (3,1) and DAT (3,2), DAT (0,
2) and DAT (0,3),. . . , DAT (3,2) and DAT (3,3) are compared in order, and the counter COUNTB is incremented each time they do not match (S19 to S24).

Then, the counters COUNTA, COUN
Both values of TB are a predetermined reference value S (S = 4 in this embodiment)
If it is the above (when the determination results in S25 and S26 are both YES), it is determined that the current pixel of interest is "no correlation" (the number of pixel value change points is small), and as the uncorrelated signal a "
A 1 "signal is output (S27). Otherwise, a
= "0".

The area judging section 3 counts up if the uncorrelated signal a is "1" (no correlation) in synchronization with the clock RCLKI, but clears it if a = "0" (correlated). . That is, the continuous number of “no correlation” pixels is counted. The count value is equal to a predetermined reference value S
(S = 4 in this embodiment) At the time of the above, the discrimination signal b = "1"
Outputs a signal (determined as a photographic image), otherwise b
== "0" is output (determined as a character image).

The above image discriminating operation will be described with reference to FIGS. In the example of the character image shown in FIG. 5A (this is the same as the image shown in FIG. 10A), consider the image discrimination of the pixel of the star mark. Three pixels before this pixel of interest, the reference area is located as shown in (b), so that the value of COUTNA is 5 and the value of COUNTB is 2 in the correlation operation, and the result of the correlation operation is “correlation”. a = ”
0 "is output, and the area determination unit (counter) 3 is cleared. From the next pixel to the pixel of interest, the reference areas are located at positions shown in (c), (d), and (e), respectively. And the value of both COUNTA and COUNTB is 4
As a result, the result of the correlation operation is “no correlation”, and a = “1” is output. Therefore, the count value of the area determination unit 3 at the time of the pixel of interest is 3, which is determined to be a character image, and b = "0" is output.

Similarly, in the example of the photographic image shown in FIG. 6A (this is the same as the image shown in FIG. 10B), consider the image discrimination of the pixels marked by stars. (B)-(e)
As shown in, all the correlation calculation results for four pixels from three pixels before to the pixel of interest are “no correlation”,
Since a = “1” is continuously output, the count value of the area determination unit 3 increases to 4 at the time of the pixel of interest and is determined as a “photo image”, so b = “1” is output. You.

The character image shown in FIG. 5A and the photographic image shown in FIG. 6B cannot be identified by solely referring to a 4 × 4 matrix as described with reference to FIG. Although it was necessary to enlarge the reference area to 4 × 8, according to the present invention, the identification can be made with a 4 × 4 reference area. This is because, in the present invention, since the correlation calculation result of a plurality of pixels before that is used for the determination of the target pixel, the substantial reference area is enlarged.

When the output of one page of image data from the storage unit 1 is completed, the control unit 6 stops the clock RCLK and outputs the recording start signal PSTR. Recorder 5
When the recording start signal PSTR is input, the clock PCLK is output and the correction data is sequentially read from the storage unit 4 and recorded.

According to the second embodiment of the present invention, the area judging section 3 shown in FIG. 1 is configured as shown in FIG. In FIG.
21 and 22 are counters, and 23 is a latch circuit. a,
b, RCLK, and CLR are signals corresponding to the signals of the same names shown in FIG.

One counter 21 receives a clock RCLK
In synchronization with the above, the count-up is performed when the non-correlation signal a is "1" (no correlation), and cleared when a = "0" (correlation exists). That is, the counter 21 counts the continuous number of “no correlation” pixels. When the count value becomes equal to or greater than a predetermined reference value S (S = 4 in this embodiment), the output signal c is set to “1”.

The other counter 22 outputs a clock RCLK
In synchronization with the above, the count-up is performed when the non-correlation signal a is "0" (correlation is present), and is cleared when a = "1".
That is, the continuous number of “correlated” pixels is counted.
Then, the count value is equal to the reference value S (S = 4 in this embodiment).
Then, the output signal d is set to "1".

The latch circuit 23 outputs c = “1” and d = “1”.
When it is 0, the discrimination signal b is set to "1" (photo image), and c
When d = “1” and d = “1”, the determination signal b is set to “0” (character image). Both signals c and d are "0" or "
When it is 1 ", the state of the discrimination signal b does not change.

According to the configuration of the area determination section 3 of the first embodiment, if at least one pixel having "correlation" appears in a region where pixels having "no correlation" continue, the determination signal b is obtained at that position. Becomes “0”. On the other hand, according to the configuration of the area determination unit 3 of the present embodiment, the number of “no correlation” pixels is 4
When four or more “correlated” pixels continue after four or more consecutive pixels, or when four or more “uncorrelated” pixels continue after four or more “correlated” pixels continue,
Since the state of the discrimination signal b changes, otherwise, the previous state is maintained, so that more stable photo / character discrimination is possible.

According to the third embodiment of the present invention, the area judging section 3 shown in FIG. 1 is configured as shown in FIG. In FIG.
31 is a register formed by connecting (L-1) latch circuits in series, 32 is an adder, and 33 is a comparator. In this embodiment, L is equal to the total number of pixels in one line. a, b, RC
LK and CLR are signals corresponding to the signals of the same name in FIG.

The uncorrelated signal a is input to the register 31,
The data is sequentially shifted to a subsequent latch circuit in synchronization with the clock RCLK. The input uncorrelated signal a and the output signal (delayed signal a) of the latch circuit at each stage of the register 31 are input to the adder 32, and the number of “1” bits in the input L bit signal is added. It is output from the unit 32. This addition value (the number of pixels having no correlation) is input to the comparator 33 and compared with a predetermined reference value Q. When the addition value is equal to or larger than the reference value Q, the discrimination signal b becomes “1”. However, otherwise, b = "0".

As described above, in the present embodiment, not the number of “correlated” pixels but the number of “correlated” pixels included in L consecutive pixels is determined by whether or not the number of “correlated” pixels is larger than the reference number. Perform character judgment. This method can easily avoid the influence of noise, and can stably perform image determination in a large unit (for example, one line unit).

However, in this embodiment, the number of pixels (a = “0” pixels) determined to have little change in the pixel value is counted, and similar image discrimination is performed based on the counted value. It is also possible.

In a dither image, a pixel having a low or high black ratio in the reference area may be determined to be a character image area (however, such a pattern hardly appears in a character image). In order to perform more accurate image discrimination, the correction table unit 2 adds a judgment of a black ratio of a reference area or a judgment of a specific pattern of a photographic image or a character image in addition to the correlation operation. And effective. Further, the image identification device according to the present invention can be applied to various uses other than the image recording device.

[0049]

As is apparent from the above description, the present invention has the following effects. (1) In the first to third inventions, since the substantial size of the reference area can be regarded as being enlarged as compared with the reference area of each pixel, the size of the reference area is minimized. Thus, it is possible to determine an image that cannot be determined based on the size of the reference area. (2) In a photographic image area, a pixel having a small number of pixel value changes may appear locally in a series of pixels having a large number of pixel value changes. The second invention or the third invention is directed to a pixel region having a small number of pixel value change portions locally appearing in a photographic image region or a pixel region having a large number of pixel value change portions locally appearing in a character image region. Area can also be correctly determined. (3) According to the third aspect of the present invention, stable image discrimination can be performed while avoiding the influence of noise, and image discrimination in large units can be stably performed.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a first embodiment of the present invention.

FIG. 2 is an explanatory diagram of reference pixels and correction data.

FIG. 3 is an operation timing chart.

FIG. 4 is a flowchart of a correlation operation.

5A is a diagram illustrating an example of a character image. FIGS. 5B to 5E are diagrams illustrating a process of determining a character image.

6A is a diagram showing an example of a photographic image, and FIGS.

FIG. 7 is a block diagram of an area determining unit according to a second embodiment of the present invention;

FIG. 8 is a block diagram of an area determining unit according to a second embodiment of the present invention.

FIG. 9 is a diagram showing an example of a pseudo halftone expression by the dither method (a) to (q).

10A is a diagram illustrating an example of a character image. FIG. 10B is a diagram illustrating an example of a photographic image. FIG. 10C is a diagram illustrating a pattern of a 4 × 4 reference area of a character image. (E) A diagram showing a pattern of a 4 × 8 reference area of a character image. (F) A diagram showing a pattern of a 4 × 8 reference area of a photographic image.

[Explanation of symbols]

 1, 4 storage unit 2 correction table unit 3 area determination unit 5 recording unit 6 control unit 8 image data input terminal 9 clock output terminal a uncorrelated signal b discrimination signal 21, 22 counter 23 latch circuit 31 register 32 adder 33 Comparator

Claims (3)

(57) [Claims] 1. For each pixel of binary image data, a matrix area including a pixel of interest at a predetermined position and a pixel area of the pixel of interest
A plurality of reference areas are set by a matrix area for all pixels up to n pixels before (n is a positive integer), and it is determined whether the number of changed pixel values in each reference area is larger or smaller than a reference value. A determining means for determining, and counting the number of consecutive appearances of the reference area in which the number of changed portions is determined to be larger than the reference value by the determining means, and when the counted value is equal to or more than a predetermined value, the pixel of interest And an image discriminating means for discriminating the pixel of interest as a photographic image and otherwise discriminating the pixel of interest as a character image. 2. For each pixel of binary image data, a matrix area including a pixel of interest at a predetermined position and a
A plurality of reference areas are set by a matrix area for all pixels up to n pixels before (n is a positive integer), and it is determined whether the number of changed pixel values in each reference area is larger or smaller than a reference value. Determining means for determining; first counting means for counting the number of consecutive appearances of the reference area for which the number of change points is determined to be larger than the reference value; Counting means for counting the number of consecutively appearing pixels whose number is determined to be smaller than the reference value, and wherein the count value of the first counting means is greater than or equal to a predetermined value and the second counting means When the count value is less than a predetermined value, the pixel of interest is determined to be a photographic image, and the count value of the first counting means is less than a predetermined value and the count value of the second counting means is equal to or more than a predetermined value. Sometimes the pixel of interest is determined to be a character image, Image discrimination apparatus in question of having an image discrimination means for the same determination as the previous pixel of interest pixel. 3. For each pixel of binary image data, a matrix area including a pixel of interest at a predetermined position and
A plurality of reference areas are set by using a matrix area for all pixels up to n pixels before (n is a positive integer), a plurality of reference areas are set for a target pixel, and the number of pixel value changes in each reference area is reduced. A determination means for determining whether the number is larger or smaller than the reference value, and a photographic image in accordance with the number of successively appearing reference areas in which the number of changed portions is determined to be larger than the reference value by the determination means. And an image discriminating means for discriminating whether the image is a character image.