JPH11313218A - Image processing unit, binary processing method, and machine-readable recording medium recording program to allow computer to execute binary processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To avoid occurrence of set-off by processing even a black/white original to be a color image through the utilization of occurrence of a difference from a color component between a part causing the set-off and a medium tone component part on a surface of an original so as to acquire a desired binary image. SOLUTION: The processing unit is provided with an image input section 101 that receives a black/white image as an RGB color image, a lightness detection section.RbRw detection section 102 that obtains lightness of the color image and an RGB ratio of a minimum lightness part and a maximum lightness part, a tri-state processing section 103 that obtains a 'black level', a 'white level' or a 'medium level' depending on the obtained lightness, and a medium pixel binary processing section 104 that applies binary discrimination to decide the image to be a black image when the RGB ratio of a pixel of the medium tone is closer to a black level or to decide the image to be a white image when the RGB ratio of a pixel of the medium tone is closer to a white level.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is used for pre-processing (binarization of an image) of a scanner, a digital copier, an OCR, etc., and in particular, processes even a black-and-white original as a color image. Recorded an image processing apparatus and a binarization method for obtaining a desired binary image by utilizing a difference between a halftone component and a color component on the surface of a document, and a program for causing a computer to execute the binarization method. The present invention relates to a machine-readable recording medium.

[0002]

2. Description of the Related Art Conventionally, when a black-and-white document is input as an image by a scanner or the like, a brightness signal is first read and then binarized. This binarization technique is disclosed in, for example, JP-A-6-195511 and JP-A-9-305754. In "Binarization threshold value determination device" of Japanese Patent Application Laid-Open No. 6-195511, a binarization threshold value is determined using a density histogram of a multivalued image as an input to a neural network. Also, Japanese Patent Application Laid-Open No. 9-30575
In the "image processing method" of Japanese Patent Application Laid-Open No. 4 (1999) -2002, a binarization process is performed for each block.

Also, a method of determining black characters and a halftone area in consideration of back-filling in a color image is disclosed in
Japanese Patent Application Laid-Open No. 226,842 discloses a "base control method and method for color image forming apparatus". Note that this method is not for binarization but for obtaining a halftone such as a color background.

[0004]

However, in the conventional techniques disclosed in Japanese Patent Application Laid-Open Nos. Hei 6-195511 and Hei 9-305754 as described above, the binarization is not performed by using the brightness value. Processing depends only on
If the back-facing portion appears on the image signal as an intermediate brightness, it has been difficult to correctly remove this and binarize it.

[0005] That is, when a conventional binarization process is performed on a portion where the front side of a document is white and the back side is black, "black" is determined depending on the setting of the threshold level, and as a result, the back side is determined. There has been a problem that the image becomes a reentrant image.

SUMMARY OF THE INVENTION The present invention has been made in view of the above, and even when a monochrome document is processed as a color image, the difference between the halftone component and the color component on the back side of the document is obtained. It is an object of the present invention to obtain a desired binary image by utilizing the phenomenon, and to prevent the occurrence of back-side-down.

[0007]

In order to achieve the above object, an image processing apparatus according to the first aspect comprises an image input means for inputting a monochrome image as an RGB color image, and an image input means for inputting the color image. Lightness / RGB ratio detecting means for obtaining the lightness and the RGB ratio of the minimum and maximum parts of the lightness; ternary means for obtaining three values of "black", "white" and "intermediate" based on the lightness; And an intermediate pixel binarizing means for making a binary decision of "black" when the RGB ratio of the pixel of "" is close to the black level and "white" when it is near the white level.

That is, a desired binary image is obtained by inputting a black-and-white document as a color image, and obtaining a back-facing portion based on a difference between a halftone component and a color component (RGB ratio) on the surface of the document. Thus, it is possible to avoid the occurrence of a back-flush image.

According to a second aspect of the present invention, a first step of inputting a black-and-white image as a color RGB image, finding a portion having the highest brightness, and recording the RGB ratio as Rw. And find the lowest brightness part,
A second step of recording the RGB ratio as Rb, a third step of dividing the brightness into three values of "black", "white", and "intermediate"; and examining the RGB ratio of the "intermediate" pixel. If it is close to Rb, it will be "black", if it is close to Rw, it will be "white",
And a fourth step of obtaining a black and white binary image.

That is, a black-and-white image is input as a color RGB image, the RGB ratio of the highest lightness portion is recorded as Rw, the RGB ratio of the lowest lightness portion is recorded as Rb, and "black" and "white" in lightness are further recorded. , "Intermediate", and the RGB ratio of the "intermediate" pixel is examined. When the pixel is close to Rb, "black" and when it is close to Rw, "white", a binary image of black and white is obtained. It is possible to avoid the occurrence of a back-flushed image.

Further, in the binarizing method according to the third aspect, a black-and-white image is input as a color RGB image, and the black-and-white, white, and intermediate values are binarized by brightness. A second step of specifying a pixel representing a white portion and recording its RGB ratio as Rw; and a third step of specifying a pixel representing a black portion and recording its RGB ratio as Rb. And a fourth step of performing binarization on the intermediate value image based on the RGB ratio to obtain a black and white binary image.

That is, a black-and-white image is input as a color RGB image, and “black”,
Ternary conversion of “white” to obtain the RGB value of a pixel representing black and the RGB value of a pixel representing white, and comparing the RGB value with the RGB value of a pixel having an “intermediate” value As a result, it is possible to avoid the occurrence of a back-flushed image by determining the back-flushed portion determined to be “intermediate” as “white”.

Further, in the binarizing method according to the fourth aspect, when a black-and-white image is input as a color RGB image, the back-facing portion is determined to be white, and a desired binarizing result is obtained. , RGB ratios are obtained from all or some of the pixels in the black portion or the white portion.

That is, a black-and-white image is input as a color RGB image, the back-facing portion is determined to be white, and the RGB ratio is obtained from all or a plurality of pixels of the black portion / white portion to obtain a desired ratio. By obtaining a binarized image, it is possible to avoid the occurrence of a back-flushed image.

According to a fifth aspect of the present invention, there is provided a binarization method, wherein a program for causing a computer to execute the binarization method according to any one of the second to fourth aspects is recorded.

That is, any one of claims 2 to 4
By recording a program for causing a computer to execute the binarization method described in (1), the computer
It is possible to perform a value conversion process.

[0017]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an image processing apparatus and a binarizing method according to the present invention and a machine-readable recording medium storing a program for causing a computer to execute the binarizing method will be described in detail with reference to the accompanying drawings. explain.

(System Configuration) FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to the embodiment. In FIG. 1, reference numeral 101 denotes an image input unit as an image input unit for optically reading and inputting a black-and-white original as a color image (R, G, B signals) using a CCD mounted scanner or the like;
Reference numeral 02 denotes a brightness detection unit / RbRw detection unit as brightness / RGB ratio detection means for obtaining the brightness of a color image and calculating an RGB ratio between a minimum portion and a maximum portion of the brightness.

Reference numeral 103 denotes a pixel based on brightness as "black";
A ternarization unit 104 as ternarization means for ternarization into “white” and “intermediate”, and an intermediate pixel 104 as an intermediate pixel binarization means for determining the intermediate pixel to be a black and white binary based on the RGB ratio 2
A value conversion unit 105 is a control unit that controls the apparatus in accordance with a predetermined control program, 106 is a data storage unit for storing input color images, connected component data, area data, and the like. Reference numeral 107 denotes a data communication unit that performs data transmission / reception with an external device.

(System Operation) Next, the operation of the image processing apparatus configured as described above will be described. First, a document is set on a scanner (image input unit 101), and the document is exposed and scanned to obtain a color image of R, G, and B signals. In addition, an image may be externally input via the data communication unit 109.

Here, an image reading operation and an example of capturing an RGB image will be described with reference to FIGS. FIG. 4 is an explanatory diagram showing an example in which a black-and-white document is read by a light source / CCD. In the figure, reference numeral 401 denotes a black and white original, 402 denotes a light source / CCD, and 403 denotes a pressure plate. FIG. 5 is an explanatory diagram showing an example in which a black-and-white document is read as a multi-value signal by a scanner in the document reading of FIG.

When the reading light is not reflected at all on the surface of the original 401 but is partially transmitted, the transmitted light is reflected by the pressure plate 403 on the original, and is obtained as an image signal similarly to the reflected light on the original surface. Can be

Here, each reflected light and each transmitted light (light transmitted and returned again) are represented as follows. Lr: Reflected light on the front surface of the document Lrw: Reflected light in the white portion Lrg: Reflected light in the halftone Lrb: Reflected light in the black portion Lt: Light that has passed through and returned again Ltw: Transmitted light in the white portion on the back surface of the document : Transmitted light with black back side of original

At this time, the image signal becomes a graph as shown in FIG. In this case, depending on the setting level of the threshold value Th, the determination of “black” is made for a portion where the front side of the document is white and the back side is black.

Here, for example, as shown in FIG.
Assuming that each of RGB takes a value in the range of 55 to black 0, white portions on both sides: (200, 202, 192) black portions in the table: (85, 75, 57) halftone portions in the table: ( (156, 160, 140) Part where the manuscript table is white and the back is black: (158, 161, 15)
8) It is assumed that

In this example, the reflected light Lrb and Lrg with respect to the ink on the surface both have a lower B value than R and G. However, although the value of B is low in the white portions of both sides of the original document, the difference is small, and B in the portion of the back side is not much different from R and G.

This is because the reflected light Lrw basically reflects the color of the original paper (strictly speaking, it slightly deviates from white). This is because Lt and Lr are different due to the influence and the change in color components when the light passes through the document.

Here, in order to make the halftone (Lrg) part black and the back side (Lrw + Ltb) part white, the operation shown in the flowchart of FIG. 2 may be performed.

In FIG. 2, first, an RGB image is input (S201), a portion with the highest brightness is found, and the RGB
The B ratio is recorded as Rw (S202). Further, a portion having the lowest brightness is found, and its RGB ratio is recorded as Rb (S203). Next, the brightness is simply divided into three values of "black", "white", and "middle" (S20).
4). For this, a threshold value determined in advance may be used, or another method such as using a histogram of overall or local brightness may be used. Subsequently, the RGB ratio of the “middle” pixel is checked. As a result, “black” is set when the pixel is close to Rb, and “white” is set when the pixel is close to Rw. This is executed for each “intermediate” pixel (S205), and the monochrome 2
A value image is obtained (S206).

Therefore, by executing the above-described processing, it is possible to obtain a desired binarization result even for a portion that is difficult to determine only by brightness.

When determining Rw and Rb, the RGB ratio of the pixel specified based on another index may be used as Rw and Rb instead of the image and the pixel with the highest brightness. This operation will be described with reference to the flowchart shown in FIG.

In FIG. 3, first, an RGB image is input (S301), and ternarization based on lightness (“black”, “white”,
("Intermediate" three values) is performed (S302). Further, a pixel representing the white portion is specified, and its RGB ratio is recorded as Rw (S303). Subsequently, a pixel representing the black portion is specified, and its RGB ratio is recorded as Rb (S3).
04). Next, the intermediate value image is binarized by the RGB ratio (S305), and a black and white binary image is obtained (S306).

As described above, for the RGB image, ternarization of “black”, “white”, and “intermediate” is performed according to the brightness value, and the RGB value of the pixel representing black and the RGB value of the pixel representing white are obtained. Is calculated, and the RGB value is compared with the RGB value of the pixel having the “intermediate” value.
By the determination, it is possible to obtain a desired binarized image even if there is a reverse embossing.

As another method described above, for example,
Instead of the RGB ratio of a specific pixel, the RGB ratio may be obtained from all or some of a plurality of pixels in a black portion or a white portion. In this case, the average of each pixel is taken or the median is taken.

The present invention can be realized by software other than the above embodiment. For example, the binarization method described with reference to FIGS. 2 and 3 is programmed, stored in a machine-readable recording medium, and executed on a computer.

[0036]

As described above, according to the image processing apparatus of the present invention (claim 1), a black-and-white document is input-processed as a color image, and the back-facing portion is replaced with a halftone component on the surface of the document. Since a difference is obtained in the color components (RGB ratios), a desired binary image can be obtained, and it is possible to avoid the occurrence of a back-facing image.

According to the binarization method of the present invention (claim 2), a monochrome image is input as a color RGB image, and the RGB ratio of the highest brightness portion is recorded as Rw.
The RGB ratio of the lowest lightness portion is recorded as Rb, and further divided into three values of “black”, “white”, and “intermediate” according to the lightness, and the RGB ratio of the “middle” pixel is examined. , Rw, it is regarded as “white”, and a black-and-white binary image is obtained.

According to the binarizing method of the present invention (claim 3), a black-and-white image is input as a color RGB image, and the black-and-white image is given to the image according to brightness. The value is determined, the RGB value of the pixel representing black and the RGB value of the pixel representing white are determined, and the RGB value is compared with the RGB value of the pixel having the “intermediate” value to determine “intermediate”. It is possible to avoid the occurrence of a back-flushed image, since the determined back-flushed portion is determined to be “white”.

According to the binarization method of the present invention (claim 4), a black-and-white image is input as a color RGB image, the back-facing portion is determined to be white, and the whole pixels of the black portion / white portion are determined. Alternatively, by obtaining the RGB ratio from some of the plurality of pixels, a desired binarized image can be obtained, and it is possible to avoid the occurrence of a back-facing image.

According to a machine-readable recording medium of the present invention (claim 5), a program for causing a computer to execute the binarization method according to any one of claims 2 to 4 is recorded. This enables the computer to perform the binarization processing.

[Brief description of the drawings]

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

FIG. 2 is a flowchart illustrating a first processing operation example until a black-and-white binary image is obtained from an RGB image according to the embodiment;

FIG. 3 is a flowchart showing a second processing operation example until a black-and-white binary image is obtained from an RGB image according to the embodiment;

FIG. 4 is an explanatory diagram showing an example in which a black-and-white document is read by a light source / CCD.

FIG. 5 is an explanatory diagram showing an example in which a black-and-white original is read as a multi-value signal by a scanner in the original reading of FIG. 4;

[Explanation of symbols]

 Reference Signs List 101 image input unit 102 brightness detection unit / RbRw detection unit 103 ternarization unit 104 intermediate pixel binarization unit

Claims (5)

[Claims] 1. An image input means for inputting a black and white image as an RGB color image, and a lightness / R for obtaining the lightness of the color image and an RGB ratio of a minimum part and a maximum part of the lightness.
GB ratio detecting means and "black", "white",
A ternary means for obtaining the ternary value of "intermediate", and an intermediate for making a binary determination of "black" when the RGB ratio of the "intermediate" pixel is close to the black level and "white" when the RGB ratio is close to the white level An image processing device comprising: a pixel binarizing unit. 2. A first step of inputting a black-and-white image as a color RGB image, finding a portion having the highest brightness, recording the RGB ratio as Rw, and finding a portion having the lowest brightness, and determining the RGB ratio. The second step of recording as Rb, the third step of dividing the brightness into three values of “black”, “white”, and “intermediate”, and the RGB ratio of the “intermediate” pixel are examined.
A fourth step of obtaining a black-and-white binary image by setting “black” when close to Rb and “white” when close to Rw. 3. A black-and-white image is input as a color RGB image, a first step of performing ternarization of “black”, “white”, and “intermediate” according to lightness, and a pixel representing a white portion is specified. A second step of recording the RGB ratio as Rw, a third step of specifying a pixel representing a black portion and recording the RGB ratio as Rb, and
A fourth step of performing binarization by a ratio to obtain a black and white binary image. 4. A black-and-white image is input as a color RGB image, a back-facing portion is determined to be white, and when obtaining a desired binarization result, a plurality of all or a part of pixels of a black portion or a white portion is obtained. The binarization method according to claim 2, wherein the RGB ratio is obtained from the pixel of (b). 5. A machine-readable recording medium on which is recorded a program for causing a computer to execute the binarization method according to any one of claims 2 to 4.