JPH11110552A - Method for extracting color of image and image processor using the same - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for extracting colors of an image from the one with uneven luminance due to illumination and an image processor using the method with comparatively simple structure and high-speed operation processing. SOLUTION: This image processor is constituted to calculate one or plural difference values among the difference values between an R value and a G value, the difference value between a B value and the G value, the difference value between the R value and the B value in addition to the R value, the G value and the B value of respective pixels in an image pickup area 11a, to set threshold values for the R value, the G value, the B value and the one or plural difference values among the difference values between the R value and the G value, the difference value between the B value and the G value, the difference value between the R value and the B value in one or plural selected pixels and to extract the pixel in which the R value, the G value, the B value and one or plural difference values among the difference value between the R value and the G value, the difference value between the B value and the G value, the difference value between the R value and the B value of an optional pixel in the image-pickup area 11a does not the threshold as the pixel with the same color as that of the selected pixel.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image color extraction method for extracting a color component from an image as a feature value, and an image processing apparatus using the method.

[0002]

2. Description of the Related Art In an extraction process for extracting a target object from a color image, it is important to identify individual regions included in the image. In general, a method of identifying an image as a partial image having a uniform feature amount such as density, color, and texture is used.

A method of identifying a region using a color component as a feature has already been used in various industrial fields.
In the field of food, medicine, etc., a device for inspecting the position of a colored label attached to a product, a device for identifying a product on a mixed production line or a color bar printed on a package for packing the product, etc. Has been applied to

In such an apparatus, an object such as a product is imaged using an image pickup device such as a color camera, and the imaged image is divided into analog signals composed of R, G, and B values for each pixel. After that, the analog R value, G value, and B value taken into the image processing device and taken into the image processing device are:
The data is converted into digital R, G, and B values and stored in the storage device. The image processing apparatus displays the original image on a display device such as a CRT based on the stored information, and also displays a pointer movably provided on a screen on which the original image is displayed in a superimposed manner.

By operating this pointer using input means such as a controller, a color to be extracted is selected from a color pallet displayed on the screen, or a color to be extracted is set to an R value, a G value, And a pixel having a color to be extracted from the original image is directly input with each numerical value of the pixel value and the B value, and the R value, the G value, and the B value of the pixel are set in advance. The threshold for each of the R, G, and B values is determined based on the permissible range of the threshold for each of the R, G, and B values, and the R value of each pixel in the original image is determined. ,
If the values of the G value and the B value do not exceed the respective threshold values, it is determined that the color is the same as the color to be extracted, and all the pixel regions determined to be the same color are extracted and the CRT or the like is extracted. A method of displaying on a display device is used. In this method,
R value, G value, and B value, and a preset R value
By comparing values, G values, and B values with thresholds corresponding to the respective values, regions of the same color can be identified, so that the configuration of the device that performs the operation can be simplified, and the processing speed is high.

However, in the above-described method, for example, when a colored label attached to a side surface of a rounded object such as a chemical tube is taken in by an image pickup device, light from illumination is applied to the object surface. Since the light is normally radiated from one direction, the entire colored label is not evenly irradiated with light, and bright and dark portions are generated, and the entire colored label cannot be identified as a uniform color area. However, there is a problem that the entire colored label cannot be extracted. Further, when the threshold values of the R value, the G value, and the B value are set large as described above in order to extract the entire colored label, a new problem arises in that unnecessary regions are extracted.

[0007] Further, there is a problem that the brightness of the target surface becomes uneven due to the illumination that causes the illumination unevenness, and the area to be extracted becomes patchy. When the thresholds of the value, the G value, and the B value are set large, other unnecessary regions are extracted as described above.

In order to solve these problems, for example, Japanese Patent Application Laid-Open No. Hei 4-10075 discloses that the R value, G value, and B value of each pixel of a digitized captured image are HSI-converted as described above. H (hue), S (saturation), I (lightness)
And the color to be extracted is selected from the color pallet displayed on the screen, or the color to be extracted is input as each of the R value, the G value, and the B value. ,
Or, as the pixel having the color to be extracted from the original image is directly selected, the H value, S value, and I
The threshold for each of the H, S, and I values is determined based on the values and the preset tolerances of the threshold for each of the H, S, and I values. H of each pixel
Value, S value, and I value do not exceed each threshold,
A method of extracting a color of an image which is determined to be the same color as a color to be extracted, and all the pixel regions determined to be the same color are extracted and displayed on a display device is disclosed. For example, it is possible to evaluate with a color component of the target surface which does not change due to uneven illumination.

[0009]

In this method, however, the R, G, and B values are converted to H, S, and I values by H
Since it is necessary to perform SI conversion, not only the configuration of the apparatus is complicated as compared with the above-described method in which the R value, G value, and B value are used as they are, but also the processing speed is increased due to the complicated arithmetic processing. The problem of lowering occurs.

The present invention has been made in view of the above circumstances, and has been made in consideration of the R value, G value, and B value of each pixel in an imaging region.
In addition to the values, the difference value between the R value and the G value, the difference value between the B value and the G value, and the difference value between the R value and the B value are calculated in advance, and the difference value and the R value corresponding to the pixel to be extracted are calculated. Value, G value, and B
The thresholds of the difference value, the R value, the G value, and the B value are individually set based on the values, and the pixels within the threshold values are extracted as having the same color as the region to be extracted. Provided is a method for extracting a color of an image with a relatively simple configuration and a high speed of arithmetic processing, and an image processing apparatus using the method, even in an imaging area having an uneven brightness portion due to uneven illumination or an imaging area having uneven brightness. The purpose is to:

[0011]

According to a first aspect of the present invention, there is provided a method for extracting a color of an image, comprising the steps of: extracting an R value, a G value, and a B value at one or a plurality of pixels selected from a captured image;
Thresholds for values related to the G value and the B value are set, and pixels whose values related to the R value, the G value, and the B value of any pixel in the image do not exceed the threshold value are defined as the selected pixels. In the color extraction method of an image to be extracted as having the same color, a difference value between an R value and a G value, a difference value between a B value and a G value, and a difference value between an R value and a B value are determined based on the captured image. Calculating one or more difference values, and setting a threshold value based on the R value, G value, B value of the selected pixel, and the difference value.

An image processing apparatus according to a second aspect of the present invention provides an image processing apparatus comprising: an R value and a G value for one or a plurality of pixels selected from a captured image;
Setting a threshold value for the R value, the G value, and the value related to the B value based on the value and the B value, and determining the value related to the R value, the G value, and the B value of any pixel in the image. In an image processing apparatus for extracting a pixel that does not exceed a threshold value as having the same color as the selected pixel, a difference value between an R value and a G value, a difference value between a B value and a G value, Calculating means for calculating one or more difference values among the difference values of the R value and the B value; and the R value and the G value of the selected pixel.
Threshold value determining means for determining a threshold value based on the value, the B value, and the difference value; and an R value, a G value,
Extracting means for extracting a pixel whose B value and the difference value do not exceed the threshold value as a pixel having the same color as the selected pixel.

According to a third aspect of the present invention, there is provided an image processing apparatus, comprising: an image pickup means for picking up a target image; operating a pointer superimposed on the image to display one or a plurality of target pixels from the image; Based on the selection means for selecting and the R value, G value, and B value of the selected pixel, R value, G value,
And a threshold value for a value related to the B value, and a pixel in which the value related to the R value, G value, and B value of any pixel in the image does not exceed the threshold value is set to the same color as the selected pixel. In an image processing apparatus provided with an extracting means for extracting as a result and a display means for displaying an extraction result, a difference value between R value and G value, a B value and a G value based on the image taken by the imaging means. Calculating means for calculating one or a plurality of difference values among the difference values of the R, G and B values of the selected pixel, based on the R, G and B values of the selected pixel and the difference value Threshold value determining means for determining a threshold value.

According to the image color extraction method and the image processing apparatus using the method according to the present invention, the R value, the G value, and the B value serving as the color extraction parameters are added to the R value and the G value. A difference value, for example, an RG value, a B value, and a difference value between the G values, for example, a BG value, a difference value between the R value, and the B value, for example, RB
By adding a plurality of difference values as parameters from one of the difference values such as values, even in an imaging region having a bright and dark portion due to illumination or an imaging region having a non-uniform luminance portion due to uneven illumination, high accuracy can be achieved. Color extraction can be performed. Further, since the above-described difference value, which is a value related to the R value, the G value, and the B value, is calculated without performing relatively complicated processing such as HSI conversion, the calculation is performed with a relatively simple configuration. A reduction in processing can be suppressed.

FIGS. 13 and 14 are schematic diagrams showing an image pickup area. For example, the imaging region 11a illustrated in FIG. 13 illustrates a state where an object is imaged by an imaging device from a side surface direction of a columnar member whose axis is horizontally arranged.
In FIG. 13, the imaging region 11 is
It is assumed that three color regions are provided so as to divide a into three equal parts. Therefore, the three color regions are vertically long rectangular regions that are white, bluish, and reddish from the left end of the imaging region 11a, and the rectangular regions of each color are uniformly colored in the region. Shall be. FIG.
FIG. 14 shows a state in which light is radiated to the object from an angle slightly inclined with respect to the optical axis of the image pickup device. In FIG. It is assumed that light and dark portions are generated in the respective color regions so as to be equally divided into three in the direction perpendicular to. As described above, the colors of the respective color regions divided into 3 × 3 regions in directions orthogonal to each other are represented by R values, G values, and B values as shown in FIG.

FIG. 15 is a graph showing the R values of the respective color regions shown in FIG.
FIG. 16 is a table showing values, G values, and B values.
R value, G value, B value, RG value, B value of each color area shown in FIG.
It is a chart which shows -G value and RB value. For example, parameters for color extraction are three values of R value, G value, and B value, and the maximum value and the minimum value of the R value, G value, and B value of the entire color area including the selected pixel are R values. , G value, and B value, and select any pixel in a reddish color region (hereinafter, referred to as a red region, and a bluish region is also referred to as a blue region) at the right end of the imaging region 11a, and select all the pixels. Is extracted, the R value, the G value, and the B value in the central region of the red region are R = 30, G = 20, and B =
20, and the threshold for each value is R = 20-40, G =
10-30 and B = 10-30.

Then, the R value, the G value, and the B value of all the pixels in the image pickup area 11a are compared with the corresponding thresholds, respectively.
When all the pixels within the threshold range are extracted, in addition to all the red regions, an extra white region and a part of the blue region are extracted.

On the other hand, in the image color extraction method according to the present invention and the image processing apparatus using the method, the R
RG value, which is a difference value of each value from the value, the G value, and the B value,
The BG value and the RB value are calculated, and these three difference values are set in the same manner as described above in addition to the color extraction parameters, and are compared with the respective threshold values. Therefore, the R value, G
The threshold values of the value, the B value, the RG value, the BG value, and the RB value are R = 20 to 40, G = 10 to 30, B = 10 to 3
0, RG = 10 to 10, BG = 0 to 0, RB = 1
0 to 10 and the R of all the pixels in the imaging area 11a.
When the value, the G value, the B value, the RG value, the BG value, and the RB value are compared with the corresponding thresholds, only the entire red region can be extracted.

In the above-described configuration, a state is shown in which there is a bright and dark portion due to illumination in the imaging region. However, even in an imaging region having non-uniform brightness due to uneven illumination, a region to be extracted is based on the same principle. Only can be extracted.

Note that R values,
Although the configuration uses six parameters of G value, B value, RG value, BG value, and RB value, the present invention is not limited to this, and the R value, G value, and The number of parameters to be added to the R value, G value, and B value can be freely selected from one to three in accordance with the size of the difference between the B values. Therefore, by reducing the number of parameters, it is possible to suppress a decrease in arithmetic processing with a simpler configuration,
By increasing the number of parameters, more accurate color extraction can be performed.

As parameters for color extraction instead of the R, G, and B values, H (hue), S (saturation), and I (brightness) are determined based on the R, G, and B values. HSI conversion and use these values or add H
It is needless to say that a configuration using a difference value between the value, the S value, and the I value can be adopted.

Further, the maximum value and the minimum value of the R value, G value, B value, RG value, BG value, and RB value of the entire color area including the selected pixel are set as threshold values of each value. Configuration,
The present invention is not limited to this. For example, the R value, G value, B value, RG value, B
The maximum value and the minimum value of the -G value and the RB value may be set as the threshold values.

[0023]

BEST MODE FOR CARRYING OUT THE INVENTION

Embodiment 1 FIG. Hereinafter, the present invention will be described in detail with reference to the drawings showing the embodiments. FIG. 1 is a block diagram illustrating a configuration of the image processing apparatus according to the first embodiment.

In FIG. 1, reference numeral 1 denotes a workpiece such as a chemical tube on a production line as an object to be imaged, and a colored label 11 is attached to a side surface thereof. A color camera 2 for imaging the work 1 is provided above the work 1. The color camera 2 is connected to an image extraction device 3. The image extraction device 3 includes an input unit 4 for designating an area to be extracted and a display device 5 such as a CRT for displaying an original image and an extraction result. It is connected.

The image extracting device 3 includes an image input unit 31 using an A / D converter and the like, and a CPU 32 for performing arithmetic processing.
And a memory 3 for storing information given from the CPU 32.
4 and an image output unit 33 using a D / A converter and the like.
The analog captured image data of “a” is an R value, G
The value is decomposed into a value and a B value, and is provided to the image input unit 31. The image input unit 31 receives a given analog R
Values, G values, and B values are converted to digital R values, G values, and B values.
The values are converted into values (hereinafter simply referred to as R values, G values, and B values) and given to the CPU 32. CPU32
Stores the given R value, G value, and B value for each pixel in the memory 34 and supplies the R value, G value, and B value to the image output unit 33. The image output unit 33 converts the given R value, G value, and B value again into analog R values, G values,
And the B value, and outputs the original image of the imaging area 11a to the display device 5 to display it on the screen. Also,
The memory 34 stores a preset R value, a G value, a B value, and a threshold value for each of the RB values that are the difference between the R value and the B value.

On the displayed screen, a pointer (not shown) provided so as to be movable on the screen so as to be superimposed on the original image is displayed, and the operator operates the pointer using the input means 4. Thus, a pixel in the color area to be extracted can be specified. The image extracting device 3 extracts pixels of the same color as the selected pixel based on the R value, G value, and B value of the selected pixel in the imaging region 11.
Extracted from a and displayed on the display device 5.

FIGS. 2 and 3 show the R value and G value of the image pickup area 11a.
5 is a chart showing values and B values. The color label 11 attached to the work 1 is colored with five color bars in the circumferential direction of the work 1. Here, the color bar is imaged as shown in FIG. A vertically-long rectangular color region is provided so as to divide the region 11a in the horizontal direction into five equal parts, and from the left end of the imaging region 11a, becomes a white, reddish, bluish, purple-red, and reddish-purple color. Has become. Each color bar is uniformly colored over the entire color region, and FIG. 2 shows the R value, the G value, and the B value of each color bar in the imaging region 11a.

FIG. 3 shows a state in which light is applied to the colored label 11 from an angle slightly inclined with respect to the optical axis of the color camera 2. In FIG. It is assumed that light and dark portions are generated in each color region by the irradiation light so as to be equally divided into five portions in a direction perpendicular to the direction of division of each color region. As described above, the colors of the respective color regions divided into 5 × 5 regions in directions orthogonal to each other are represented by R values, G values, and B values as shown in FIG.

FIG. 4 is a flowchart showing the control contents of the CPU 32 in extracting a color area. The operator operates the pointer on the screen using the input means 4 to determine which color region of the original image of the imaging region 11a displayed on the display device 5 is to be extracted. It starts with selecting a pixel.

First, the CPU 32 fetches the R value, the G value, and the B value corresponding to each pixel in the imaging area 11a and stores them in the memory 34 (step 1). Next, the R value, G value, and B value of all the pixels in the color region including the selected pixel are read from the memory 34, and the RB value is calculated based on the read result (step 2), and is already set. The threshold value is compared with the threshold value (step 3).

If all of the R, G, B, and RB values of each pixel are within the threshold, it is determined that this pixel has the same color as the selected pixel. Is supplied to the image output unit 33 for display based on the R value, G value, and B value of this pixel (step 4). R value, G value, B value
If any of the values or the RB values are outside the threshold, the values of the R value, the G value, and the B value are set to zero, and so on.
The pixel having the same color as the selected pixel is provided to the image output unit 33 to be displayed in a distinguished manner (step 5).

FIG. 5 is a chart showing an example of an extraction result of the image processing apparatus according to the first embodiment. With the above configuration, for example, in the state of FIG. 3, a bluish-colored column having a relatively large B value (hereinafter, referred to as a blue column,
Similarly, in order to extract the entirety of the reddish column, the red column is referred to as the purple column, the purple column is referred to as the purple column, and the reddish column is referred to as the red-purple column. Is selected, the R value, G in this blue column
The threshold ranges of the value, the B value, and the RB value are as follows: R = 30 to 7
0, G = 30-70, B = 60-140, RB = -7
0 to −30, the R value of each pixel in the imaging area 11a,
When compared with G value, B value, and RB value, R value, G value
The pixels in which all of the values of the values, B values, and RB values are within the threshold range are only the pixels in the blue column surrounded by the dashed line as shown in FIG. 5, and only the color region including the selected pixels is extracted. We can see that we can do it.

FIG. 6 is a table showing an example of the extraction result of the conventional image processing apparatus. In addition, when the same evaluation as described above is performed using the three values of the R value, the G value, and the B value for comparison with the extraction result of the image processing apparatus according to the first embodiment, as shown in FIG. R value of partial area of white column and purple column,
Because the G value, B value, and RB value are within the threshold range,
These regions are extracted in addition to the blue columns. Further, if the threshold is narrowed in order not to extract these unnecessary color strings, it becomes impossible to extract all the regions of the blue string as described above.

As described above, in the image processing apparatus according to the first embodiment, in addition to the R value, the G value, and the B value of the pixel in the color region including the pixel to be extracted, the RB value, etc. Is set based on the difference value of R, G, B, and RB of each pixel in the imaging region 11a based on the threshold.
By evaluating the value, a pixel having the same color as the pixel to be extracted can be accurately extracted.

FIGS. 7 and 8 are tables showing an example of the extraction result of the image processing apparatus according to the first embodiment. However,
In the image processing apparatus according to the first embodiment, as shown in FIG. 7, even when an RB value is used as a difference value, if a different color string, for example, a purple In addition, as shown in FIG. 8, even when an attempt is made to extract an unnecessary color string as shown in FIG. 8 and to extract a blue string as shown in FIG. There is a possibility that some extra color strings may be extracted.

Embodiment 2 Therefore, the image processing apparatus according to the second embodiment does not employ a configuration using one difference value such as an RB value as in the first embodiment, but an RG value and an R value which are difference values between an R value and a G value. And a difference value between the B value and the RB value, which is a difference value between the B value and the B value. The same reference numerals are given to portions corresponding to those in the first embodiment, and description thereof will be omitted.

FIGS. 9 to 11 are tables showing examples of the extraction results of the image processing apparatus according to the second embodiment. As shown in FIGS. 9 and 10, the R value, G value, B value, and RB value
By adding the -G value as a difference value, a color string such as a blue string or a purple string can be accurately extracted.

However, as in the first embodiment, there is a possibility that an extra color string may be extracted depending on the combination of the difference values. For example, as shown in FIG. 11, when the RG value and the BG value are used, there is a possibility that a part of the red-purple line is extracted.

Embodiment 3 Therefore, in the image processing apparatus according to the third embodiment, the RG values and the RB values as in the second embodiment are used.
Instead of using two difference values such as values, R value and G
RG value, B value, which is the difference value of the value, and B, which is the difference value of the G value
A configuration using three difference values, such as a G value and an RB value, which is a difference value between the R value and the B value, is used, and portions corresponding to the second embodiment are denoted by the same reference numerals. Is omitted.

FIG. 12 is a chart showing an example of an extraction result of the image processing apparatus according to the third embodiment. As shown in FIG. 12, the R value, G value, B value, RB value, and RG value
By adding the G value as a difference value, all color strings can be accurately extracted.

In the above embodiment, the RB value,
Although one or more of the RG value and the BG value are used, the present invention may be any difference value between the R value, the G value, and the B value. Needless to say, a configuration using -R value, GB value and the like as the difference value can be adopted.

[0042]

As described in detail above, according to the image color extraction method and the image processing apparatus using the method according to the present invention,
One or a plurality of difference values of difference values such as RG value, BG value, RB value, etc. are added as parameters to three values of R value, G value, and B value which are parameters for color extraction. Accordingly, high-precision color extraction can be performed even in an imaging region having a bright and dark portion due to illumination or an imaging region having an uneven luminance portion due to uneven illumination. Further, the R value, the G value, and the B value can be obtained without performing relatively complicated processing such as HSI conversion.
Since the configuration is such that the difference between the values is calculated, the present invention has excellent effects, such as a reduction in the calculation processing can be suppressed with a relatively simple configuration.

[Brief description of the drawings]

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

FIG. 2 is a table showing an R value, a G value, and a B value of an imaging region.

FIG. 3 is a table showing an R value, a G value, and a B value of an imaging region.

FIG. 4 is a flowchart showing the control contents of a CPU associated with color region extraction.

FIG. 5 is a chart showing an example of an extraction result of the image processing apparatus according to the first embodiment;

FIG. 6 is a chart showing an example of an extraction result of a conventional image processing apparatus.

FIG. 7 is a table illustrating an example of an extraction result of the image processing apparatus according to the first embodiment;

FIG. 8 is a table illustrating an example of an extraction result of the image processing apparatus according to the first embodiment;

FIG. 9 is a table illustrating an example of an extraction result of the image processing apparatus according to the second embodiment;

FIG. 10 is a table illustrating an example of an extraction result of the image processing apparatus according to the second embodiment;

FIG. 11 is a chart illustrating an example of an extraction result of the image processing apparatus according to the second embodiment;

FIG. 12 is a chart showing an example of an extraction result of the image processing apparatus according to the third embodiment;

FIG. 13 is a schematic diagram illustrating an imaging region.

FIG. 14 is a schematic diagram illustrating an imaging region.

FIG. 15 illustrates an R value, a G value, and a B value of the color area illustrated in FIG. 14;
5 is a table showing values.

FIG. 16 shows R, G, and B values of the color area shown in FIG.
4 is a chart showing RG values, BG values, and RB values.

[Explanation of symbols]

 Reference Signs List 1 work 2 color camera 3 image extraction device 4 input means 5 display device 11 colored label 11a imaging area 31 image input unit 32 CPU 33 image output unit 34 memory

Claims (3)

[Claims] An R value based on an R value, a G value, and a B value at one or a plurality of pixels selected from a captured image.
Set thresholds for values associated with values, G values, and B values, and set R, G, and B values for any pixel in the image.
In a color extraction method of an image for extracting a pixel whose value related to a value does not exceed the threshold value as the same color as the selected pixel, a difference value between an R value and a G value based on the captured image,
One or more difference values of the difference value between the B value and the G value, the difference value between the R value and the B value are calculated, and the R value of the selected pixel is calculated.
A method for extracting a color of an image, wherein a threshold value is set based on a value, a G value, a B value, and the difference value. 2. An image processing apparatus according to claim 1, further comprising: selecting one of a plurality of pixels selected from a captured image based on an R value, a G value, and a B value.
Set thresholds for values associated with values, G values, and B values, and set R, G, and B values for any pixel in the image.
In an image processing apparatus for extracting a pixel whose value related to a value does not exceed the threshold value as having the same color as the selected pixel, a difference value between an R value and a G value based on the captured image;
Calculating means for calculating one or more of a difference value between the B value and the G value, a difference value between the R value and the B value, and an R value, a G value, a B value, and Threshold value determining means for determining a threshold value based on the difference value; and pixels in which the R value, G value, B value, and the difference value do not exceed the threshold value in the captured image have the same color as the selected pixel. An image processing apparatus comprising: an extraction unit that extracts a pixel. 3. An image pickup means for picking up an image to be processed,
Operating a pointer displayed superimposed on the image, selecting one or more target pixels from the image, and selecting an R value, a G value, and a B value of the selected pixel. Thresholds for values related to the R value, the G value, and the B value are set, and the R value, G value of an arbitrary pixel in the image are set.
An image processing apparatus comprising: an extraction unit that extracts a pixel whose value related to a value and a B value does not exceed the threshold value as having the same color as the selected pixel; and a display unit that displays an extraction result. Based on the image captured by the image capturing means, R
Calculating means for calculating one or a plurality of difference values among the difference value between the G value and the G value, the difference value between the B value and the G value, the difference value between the R value and the B value, and the R value of the selected pixel. An image processing apparatus comprising: a threshold value determining unit that determines a threshold value based on a G value, a B value, and the difference value.