JP2002131133A - Method for specifying color of image, method for extracting color of image, and image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for specifying colors of images which can designate a color range close to the human sensory scale. SOLUTION: A color TV camera 11 outputs a color image having tristimulus values of an RGB color display system as values for pixels. A CPU 10 converts the tristimulus values obtained from the pixels of the color image into the tristimulus values which are close to the human sensory scale by performing a nonlinear conversion with a lookup table 15 or a computing memory 15. A color specifying value, which is combination of hue, chroma, and brightness, is determined from the converted tristimulus values. After the color specifying values for standard colors are determined, CPU 10 compares the color specifying value for each pixel of the color image to be examined and the color specifying value for each standard color, judges, if both the range defined for color specifying value and the range defined for color difference are satisfied, the pixel of the color image to be examined and each standard color are the same color, and shows the pixel judged to be the same color on a display device 17.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for specifying a color value of an image for obtaining a color specification value in which a color can be easily specified when extracting a specific color from a color image taken of an object on a production line or the like. The present invention relates to a color extraction method and an image processing device.

[0002]

2. Description of the Related Art Generally, a color in a color image is specified by using a tristimulus value which is a mixed amount of original stimuli having the same color as the color of each pixel of the color image. The color image is R (70
0.0 nm), G (546.1 nm), B (435.8)
Since the three colors (nm) are used as the primary stimuli, an RGB color system that represents the colors by the tristimulus values of R, G, and B is used to specify the colors. In the following, the primary stimulus is [R] [G]
Symbols with brackets, such as [B], represent color stimuli, and symbols without brackets, such as R, G, B, represent tristimulus values. That is, since the tristimulus values that match the color [F] are represented by the following equations, the tristimulus values R, G, and B
Can specify the color. [F] = R [R] + G [G] + B [B] By the way, many color images are obtained by imaging an object with an imaging device such as a color TV camera. The tristimulus values R, G, and B may vary depending on the unevenness in the amount of light applied to the target. As described above, it is not appropriate if the same color is not determined because the three stimulus values R, G, and B are different from each other. Therefore, when specifying the color in the color image, the unevenness of the irradiation light amount to the object is considered. It is considered that a range is set for each of the tristimulus values R, G, and B, and if all of the tristimulus values R, G, and B do not exceed the set ranges, it is considered that the colors are the same. However, when a range is set for the tristimulus values, an unnecessary color area is also included, and a problem arises in that the color is determined to be the same even when the color is not the same.

In order to solve the above-mentioned problem, the technique disclosed in Japanese Patent Application Laid-Open No. 11-134503 does not include values related to tristimulus values R, G, and B of a pixel to be extracted. The range of R, G, B to be extracted is set within the range. Also, in addition to setting ranges for the tristimulus values R, G, and B, ranges for difference values such as RG values, BG values, and RB values are added, and the tristimulus values R , G, B
The publication also discloses a technique of converting into hue, saturation, and lightness and setting a range for these values, and setting a range for a difference value between these values.

As a technique for solving the above-mentioned problem, as described in Japanese Patent Publication No. Hei 7-92401, tristimulus values R, G, and B obtained from a color image are converted into hue, saturation, lightness, and color tone. The color in the range is determined to be the same color by converting into the angle and the color tone length and setting the range for at least three components including the hue and the color tone angle among these five components. It also describes that an L ^* a ^* b ^* color system can be adopted as a color system. The above publication describes that the color tone angle and color tone length correspond to the angle and length of a color tone vector on a color tone surface composed of lightness and chroma, respectively.

[0005]

As described above, the color of an object in a color image changes according to the amount of light applied to the object, and the color perceived by humans is a physiological function or a psychological function. , The hue, saturation, and brightness perceived by a human also change according to the amount of light applied to the object.

By the way, in the above-mentioned technologies,
Since the RGB color system using [R] [G] [B] is used as the primary stimulus, the hue, as well as the tristimulus values R, G, B and their difference values are used. Even if saturation, lightness and its difference value, or color tone angle and color tone length are used, there is a large deviation from the human perception of color change, and the range in which the same color is judged matches the human perception. Is difficult to set. That is, the range of colors to be determined to be the same color deviates from the human sense scale, and the determination ability varies depending on the color.

[0007] The latter publication (Japanese Patent Publication No. 7-92401) describes a technique for converting from the RGB color system to the XYZ color system, but the XYZ color system also has a basic spectral sensitivity to the human eye. Because it is not based on, general XY
Even if expressed in the Z color system, it deviates from the sensation scale for human color.

The present invention has been made in view of the above circumstances, and an object of the present invention is to specify a color range of an image for determining a color specification value so that a color range close to a human color scale can be specified. It is another object of the present invention to provide a color extracting method and an image processing apparatus for extracting a specific color from a color image using the color specifying method.

[0009]

According to the first aspect of the present invention, an RG
A color image in which a first tristimulus value in the B color system is used as a value of each pixel and a conversion of the first tristimulus value to a tristimulus value in the XYZ color system is corrected. By performing the conversion, a second tristimulus value in a color space approximating a sensory scale is obtained, and a hue, a saturation, and a lightness are further obtained from the second tristimulus value. The set is used as a color specification value of a pixel.

According to a second aspect of the present invention, in the first aspect, a plurality of cases are classified according to the magnitude of the sum of the first tristimulus values, and a different conversion condition is applied to each case. A non-linear conversion from the first tristimulus value to the second tristimulus value is performed.

According to a third aspect of the present invention, in the first or second aspect of the invention, in the nonlinear transformation, a result of performing a first-order transformation on the first tristimulus value and a square root of the first tristimulus value are obtained. And a result obtained by performing a first-order conversion to obtain a second tristimulus value.

According to a fourth aspect of the present invention, in the first or second aspect of the invention, in the non-linear transformation, a result of performing a first-order transformation on the first tristimulus value and a logarithm of the first tristimulus value are used. And a result obtained by performing a first-order conversion to obtain a second tristimulus value.

According to a fifth aspect of the present invention, in the first or second aspect of the invention, in the non-linear transformation, a result of performing a first-order transformation on the first tristimulus value and a square of the first tristimulus value. And a result obtained by performing a first-order conversion to obtain a second tristimulus value.

According to a sixth aspect of the present invention, the color specification is performed by applying the image color specifying method according to any one of the first to fifth aspects to a reference color from a color image of an object having the reference color. A value is obtained, and then the colorimetric value is obtained by applying the image color specifying method according to any one of claims 1 to 5 to each pixel of a color image of an object to be inspected, and inspected. The color value of each pixel of the object to be inspected is such that the color value of each pixel of the object is within a specified range with respect to the color value of the reference color, and When the color difference from the value is within the specified range,
It is characterized in that each pixel of the object to be inspected is determined to be the same color as the reference color.

According to a seventh aspect of the present invention, an image of an object is taken and RG
6. An image pickup device that outputs a color image having tristimulus values of the B color system as pixel values, a display device capable of displaying the image, and the color of the image according to any one of claims 1 to 5. A color specifying unit that determines a color specification value of a pixel in a color image by applying a specifying method, and specifies an area including a reference color from a color image of an object having the reference color captured by an imaging device and displayed on a display device An input device, a storage unit for storing a specified range of colorimetric values including a colorimetric value extracted by applying a color specifying unit to pixels in a range specified by the input device, and an imaging device for capturing an object to be inspected. The colorimetric value obtained by applying the color specifying means to each pixel of the color image obtained by imaging is within the range of the colorimetric value stored in the storage means, and the colorimetric value of the reference color The color difference between the color value of Each pixel of the inspected object when it is the inner is determined to be a reference color and the same color in which and a color extraction means for displaying the pixels on the screen of the display device.

[0016]

DESCRIPTION OF THE PREFERRED EMBODIMENTS (First Embodiment) In this embodiment described below, the image processing apparatus shown in FIG. 1 is used. This image processing device is a color TV as an imaging device.
The camera 11 captures an image of a space area including an object, and extracts a pixel of a specified color from a color image obtained by the color TV camera 11. The input device 12 including a keyboard, a mouse, and the like is used to specify a color.
A color image obtained by the color TV camera 11 is converted into a digital signal, and tristimulus values R,
G and B are separately stored in the image memories 13R, 13G, 13
B. Capture image memory 13R, 13G, 1
The tristimulus values R, G, B stored in 3B are converted into a color system using the color conversion formula shown in Expression 1. Here, in Equation 1, the tristimulus values are represented as X, Y, and Z, and the first term on the right side is R
This is a primary conversion of the tristimulus values R, G, and B in the GB color system.
The second term on the right side includes a nonlinear correction term, and XY
The correction is made to the tristimulus values of the Z color system. This correction term is a feature of the present invention, and is a correction term for adapting to a human color sensation scale. Since this correction term is a primary conversion of the square root of the tristimulus values R, G, and B in the RGB color system, the conversion formula of Equation 1 performs nonlinear conversion as a whole. Since the color system used in the present embodiment has a form obtained by adding a correction to the XYZ color system, it will be referred to as a corrected XYZ color system. In Equation 1, a to r are conversion coefficients.

[0017]

(Equation 1)

In this embodiment, the tristimulus values R, G, and B of the RGB color system are converted into tristimulus values X, Y, and Z of the corrected XYZ color system, and are further converted to tristimulus values X, Y, and Z. The hue (H), the saturation (S), and the lightness (V) are obtained by applying Expression 2. In order to obtain the hue (H), saturation (S), and lightness (V), first, the tristimulus values X, Y, and Z are converted into the CIELAB color space (L ^* a ^* b ^*).
Hue, saturation, and lightness are determined from the values of L ^* a ^* b ^* .

[0019]

(Equation 2)

The conversion coefficients a to r used in equation (1) are stored in a look-up table 14, and using the conversion coefficients a to r stored in the look-up table 14,
0 performs the operation of Equation 1 while using the operation memory 15 for work. Further, the CPU 10 receives the calculation result of Expression 1 and also performs the calculation of Expression 2 while using the calculation memory 15 for work. That is, the CPU 10, the lookup table 1
4. The color specifying means is constituted by the operation memory 15 and the like. Since the hue, saturation, and lightness of each pixel of the color image captured by the color TV camera 11 are obtained by the calculation of Expression 2, the calculation result for each pixel is stored in the overlay memory 16 as storage means. By the way, in the present embodiment, a display device 17 such as a CRT is used, and images displayed on the display device 17 are display image memories 18R and 18 for each of RGB colors.
G and 18B, and are displayed on the screen of the display device 17 through the display circuit 19. The display device 17 displays an original image captured by the color TV camera 11, an image obtained by extracting only a specific color region from the original image, and the like.

Next, a processing procedure for extracting a specific color from a color image of an object using the above-described image processing apparatus will be described. When extracting a specific color, first, the input device 1
It is necessary to specify the color to be extracted by 2. That is, as shown in FIG. 2, in order to designate a color, an object having a reference color to be extracted is imaged by the color TV camera 11, and the image is displayed on the display device 1.
7, a range including a color to be extracted is designated by a mouse or the like (S1). Next, conversion to the corrected XYZ color system is performed by applying Equation 1 to the tristimulus values R, G, and B of the RGB color system in the video signal (color image) in the designated area, Further, a set of hue, saturation, and lightness is obtained as a color specification value by applying Equation 2 (S2). Since a color specification value including a set of hue, saturation, and lightness is obtained by designating an area, generally, not a single set but a plurality of sets of values are obtained. Therefore, a set of representative values (H,
S, V) are obtained (S3), and further obtained sets (H, S,
An appropriate width is set for V) to determine a set (H1, S1, V1) as an upper limit of hue, saturation, and brightness and a set (H2, S2, V2) as a lower limit (S4). ). That is, when the hue is H1 or less and H2 or more, and when the saturation is S1 or less, S2
As described above, the range in which the brightness is equal to or lower than V1 and equal to or higher than V2 is registered in the overlay memory 15 as a reference color (S5).

After the reference color is registered as described above, a color in a range that can be regarded as the same color as the reference color is extracted from the object to be inspected by the processing procedure shown in FIG. That is, a set of hue, saturation, and lightness is expressed in the same manner as when the reference color is obtained by applying Equations 1 and 2 to each pixel of a color image obtained by imaging the object with the color TV camera 11. The value is obtained (S1). Next, the CPU 10 compares the obtained hue, saturation, and brightness with the hue, saturation, and brightness of the reference color,
When it is determined that all the values are within the range between the upper limit value and the lower limit value (S2), the color difference is calculated by the following equation (3). When the color difference is within the specified range (S3), the pixel extracted from the object is determined. It is determined that the color is the same as the reference color, and the pixel is extracted (S4). In Equation 3, ΔH ^* , ΔL ^* , and ΔC ^* represent a hue difference, a lightness difference, and a saturation difference, respectively.

[0023]

(Equation 3)

The extracted pixels are stored in the image memory 13 for capture.
R, 13G, 13B to display image memories 18R, 18
G, 18B. If it is determined in any of steps S2 and S3 that the hue, saturation, and brightness are out of the range or the color difference is within the specified range, the pixel is regarded as a pixel of a different color, and the pixel is ignored ( S5). The above-described processing is performed on all pixels of the color image including the object to be inspected (S6), and the processing ends. In this way, since only the extracted pixels are stored in the display image memories 18R, 18G, and 18B, the display device 17 can display only the reference color pixels of the object. Thus, the CPU 10 mainly functions as the color extracting means.

The color difference equation for calculating the color difference shown as Equation 3 is:
This is obtained by applying a correction coefficient suitable for the present embodiment to what is known as a CMC (l: c) color difference equation.

As described above, in this embodiment, the correction XY
By using the Z color system, it is possible to achieve a color scale close to the scale of human perception of colors, and to express hue, saturation, and lightness using a general RGB color system or XYZ color system. As compared with the case, it is possible to suppress the difference in the extraction ability depending on the color.

(Second Embodiment) In this embodiment, the first
An image processing apparatus having the same configuration as that of the first embodiment is used. However, in the color conversion from the RGB recognition system to the corrected XYZ color system, the case according to the color is divided to perform the first embodiment. It is possible to achieve a color specification that is closer to a human sensory scale than the form of the above. In the case of the present embodiment,
The size of R + G + B is used. That is, as shown in Equation 4, 0 ≦ R + G + B ≦ k1, k1 ≦ R + G + B ≦ k
2, k2 ≦ R + G + B ≦ k3 (k1, k2, and k3 are positive appropriate constant values), and in each case, the coefficient of the color conversion formula shown in Expression 1 is changed. By performing such a case division, a conversion closer to a human sensory scale is possible. In Equation 4, a
1 to r1, a2 to r2, and a3 to r3 are conversion coefficients.

[0028]

(Equation 4)

The processing after conversion into the tristimulus values X, Y, Z of the corrected XYZ color system is the same as in the first embodiment.
As shown in Equation 2, the obtained tristimulus values X, Y, and Z are represented by CI
After mapping in the ELAB color space (L ^* a ^* b ^* color space), the hue, saturation and lightness are obtained from the values of L ^* a ^* b ^* .

Hereinafter, a processing procedure for extracting a specific color from a color image of an object in this embodiment will be described. In order to extract a specific color, first, the hue, saturation, and brightness of the reference color are obtained based on a color image of an object having the reference color to be extracted. That is, as shown in FIG. 4, while displaying a color image on the display device 17, a range including a color to be extracted is designated by a mouse or the like (S1). Here, the value of R + G + B is determined for the pixels in the designated area, and the determined values are set to constant values 0 and k.
1, k2, and k3 (S2). This comparison shows that 0 ≦ R + G + B ≦ k1 and k1 ≦ R + G + B
≤ k2 and k2 ≤ R + G + B ≤ k3. In each case, the corrected XYZ table is obtained by applying Equation 4 to the tristimulus values R, G, and B of the RGB color system. Conversion into a color system is performed, and a set (H, S, V) of hue, saturation, and lightness is obtained by applying Expression 2 (S3).
~ S5). An appropriate width is set for the set (H, S, V) obtained in this way, and a set (H1, S1, V1) as an upper limit of hue, saturation, and lightness and a set (H2, S2) as a lower limit. ,
V2) is determined (S6). That is, the hue is H2 or lower and H2 or higher, the saturation is S1 or lower and S2 or higher, and the lightness is V1.
The range that is equal to or greater than V2 below is registered in the overlay memory 15 as a reference color (S7).

After the reference color is registered as described above, a color in a range that can be regarded as the same color as the reference color is extracted from the object to be inspected by the processing procedure shown in FIG. That is, the value of R + G + B is obtained from each pixel of a color image obtained by capturing an image of an object by the color TV camera 11, and the values are classified according to the value (S1). Hue, saturation, and lightness are obtained in the same manner as when they were obtained (S2
~ S4). Next, the obtained hue, saturation, and lightness are compared with the hue, saturation, and lightness of the reference color, and if it is determined that all are within the range between the upper limit value and the lower limit value (S5), The color difference is obtained, and when the color difference is within a specified range (S
6) It is determined that the color of the pixel extracted from the object is the same as the reference color, and the pixel is extracted (S7). Equation 5 is CI
The color differences in the ELAB color space, ΔL, Δa, and Δb are the differences in the lightness index L and the differences in the color coordinates a and b, respectively.

[0032]

(Equation 5)

The extracted pixels are stored in the capture image memory 13.
R, 13G, 13B to display image memories 18R, 18
G, 18B. If it is determined in any of steps S5 and S6 that the hue, saturation, and brightness are out of the range or the color difference is within the specified range, the pixel is regarded as a pixel of a different color, and the pixel is ignored ( S8). The above-described processing is performed on all pixels of the color image including the target object to be inspected (S9), and the processing ends. In this way, since only the extracted pixels are stored in the display image memories 18R, 18G, and 18B, the display device 17 can display only the reference color pixels of the object.

The color difference equation for calculating the color difference shown as Equation 5 is:
This is known as the Hunter's color difference formula.

As described above, in this embodiment, the color T
Based on the tristimulus values R, G, and B of the RGB color system obtained as the output of the V camera 11, classification is performed, and a different coefficient is applied according to each case, and the tristimulus values of the corrected XYZ color system are applied. Since X, Y, and Z are obtained, a color specification closer to a sensation scale for human colors than in the first embodiment can be obtained, and a general RGB color system or XYZ color system can be used. It is possible to suppress a difference in extraction ability depending on colors as compared with the case where hue, saturation, and brightness are expressed. Further, by performing the case division using the value of R + G + B as in the present embodiment, the hue, saturation, and brightness are accurately obtained even for a bright color or a dark color, which is difficult to extract the color by the conventional method. This makes it possible to enhance the color extraction accuracy.

In this embodiment, three types of cases are performed using the value of R + G + B. However, the number of cases is not particularly limited.

In the first embodiment and the second embodiment, the correction term of the equation (1) or (3) when converting from the RGB color system to the corrected XYZ color system (the second term on the right side).
Term) contains the square root of the tristimulus values R, G, B,
A logarithm or a square may be used instead of the square root of the tristimulus values R, G, and B. Further, either of Equation 3 and Equation 5 may be used for evaluating the color difference. That is, Equation 5 may be applied in Step S3 of FIG. 3 in the first embodiment, or Equation 3 may be applied in Step S6 of FIG. 5 in the second embodiment.

[0038]

According to the first aspect of the present invention, a color image in which the first tristimulus value in the RGB color system is used as the value of each pixel is input, and the first tristimulus value is input in the XYZ color system. A second tristimulus value in a color space approximating a sensory scale is obtained by performing a nonlinear transformation in a form that corrects the conversion to the tristimulus value, and the hue, saturation, and lightness are further determined from the second tristimulus value. It is characterized in that a set of the obtained hue, saturation and lightness is used as a color specification value of a pixel, and the first tristimulus value of the RGB color system in the input color image is subjected to non-linear conversion. Since a second tristimulus value in a color space similar to a human sense scale is obtained, and a set of hue, saturation, and lightness is obtained as a colorimetric value from the second tristimulus value, a second tristimulus value is obtained. The color gamut in the color space where stimulus values are mapped is determined by the scale of human perception of color. It is possible to approach the color range. Therefore, if the range of the same color is determined based on the color specification values obtained from the second tristimulus values, it is possible to set a range similar to the range that humans recognize as the same color.

According to a second aspect of the present invention, in the first aspect of the present invention, a plurality of cases are classified according to the magnitude of the sum of the first tristimulus values, and different conversion conditions are applied to each case. The method is characterized in that a non-linear conversion from the first tristimulus value to the second tristimulus value is performed, and a case is divided based on the first tristimulus value, and the conversion condition is changed for each case. Since the conversion into the two tristimulus values is performed, the distance between the colors can be adjusted for each region in the color space, and it becomes possible to make the distance closer to the human sense scale. In particular, by using the added value of the first tristimulus value as a condition for dividing into cases,
It is possible to reduce the influence of the brightness of the original color image when calculating the color specification value.

According to a third aspect of the present invention, in the first or second aspect of the invention, in the non-linear transformation, a result of performing a first-order transformation on the first tristimulus value and a square root of the first tristimulus value are obtained. A second tristimulus value is obtained by adding a result obtained by performing a first-order transformation to the second transformation, and a second tristimulus value is obtained. A second tristimulus value is obtained by adding a result obtained by performing a primary conversion to a tristimulus value of 1 and a result obtained by performing a primary conversion to a logarithm of the first tristimulus value. According to a fifth aspect of the present invention, in the first or second aspect of the invention, in the non-linear conversion, a result obtained by performing a first-order conversion on the first tristimulus value and a first
A second tristimulus value is obtained by adding the result of the primary conversion to the square of the tristimulus value of
Since the correction amount is set so as to have nonlinearity by using a value that can be easily obtained, such as the square root, logarithm, or square of the first tristimulus value, it is possible to perform nonlinear conversion by a simple operation. it can.

According to a sixth aspect of the present invention, the color specification is performed by applying the image color specifying method according to any one of the first to fifth aspects to a reference color from a color image of an object having the reference color. A value is obtained, and then the colorimetric value is obtained by applying the image color specifying method according to any one of claims 1 to 5 to each pixel of a color image of an object to be inspected, and inspected. The color value of each pixel of the object to be inspected is such that the color value of each pixel of the object is within a specified range with respect to the color value of the reference color, and When the color difference from the value is within the specified range,
It is characterized in that each pixel of the object to be inspected is determined to be the same color as the reference color, and defines a range including the colorimetric value obtained for the reference color, and determines whether or not the pixel is the same color. If the value is within the specified range and the color difference between the color specification value of the pixel that determines whether or not the color specification value obtained for the reference color is the same color is within the specified range, the color is determined to be the same color. ,
By the two-stage inspection, it is possible to accurately extract pixels having the same color.

According to a seventh aspect of the present invention, an image of an object is taken and RG
6. An image pickup device that outputs a color image having tristimulus values of the B color system as pixel values, a display device capable of displaying the image, and the color of the image according to any one of claims 1 to 5. A color specifying unit that determines a color specification value of a pixel in a color image by applying a specifying method, and specifies an area including a reference color from a color image of an object having the reference color captured by an imaging device and displayed on a display device An input device, a storage unit for storing a specified range of colorimetric values including a colorimetric value extracted by applying a color specifying unit to pixels in a range specified by the input device, and an imaging device for capturing an object to be inspected. The colorimetric value obtained by applying the color specifying means to each pixel of the color image obtained by imaging is within the range of the colorimetric value stored in the storage means, and the colorimetric value of the reference color The color difference between the color value of Each pixel of the inspected object when it is the inner is determined to be a reference color and the same color in which and a color extraction means for displaying the pixels on the screen of the display device. The first tristimulus values of the RGB color system in the color image of the target imaged by the imaging device are subjected to nonlinear conversion, and the second tristimulus values in the color space approximated to a human sense scale are obtained.
Is obtained, and a set of hue, saturation, and lightness is obtained as a colorimetric value from the second tristimulus value. Therefore, the color range in the color space to which the second tristimulus value is mapped is Can be made closer to the color gamut based on the sensory scale for the color. Therefore, if the range of the same color is determined based on the color specification values obtained from the second tristimulus values, it is possible to set a range similar to the range that humans recognize as the same color. Further, a range including the color specification value obtained for the reference color is defined, and the color specification value of the pixel for determining whether or not the color is the same is within the specified range, and When the color difference between the color value of the pixel for determining whether or not the color is the same and the color difference is within a specified range, the pixel is determined to be the same color, so that the pixels of the same color can be accurately extracted by the two-stage inspection.

[Brief description of the drawings]

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

FIG. 2 is an operation explanatory diagram showing a color identification processing procedure in the embodiment.

FIG. 3 is an operation explanatory diagram showing a processing procedure of color extraction in the embodiment.

FIG. 4 is an operation explanatory diagram showing a color identification processing procedure according to the second embodiment of the present invention;

FIG. 5 is an operation explanatory diagram showing a processing procedure of color extraction in the embodiment.

[Explanation of symbols]

 Reference Signs List 10 CPU 11 Color TV camera 12 Input device 13R, 13G, 13B Image memory for capture 14 Look-up table 15 Memory for operation 16 Overlay memory 17 Display device 18R, 18G, 18B Image memory for display 19 Display circuit R, G, B tristimulus value (first) X, Y, Z tristimulus value (second)

Claims (7)

[Claims] 1. A color image having the first tristimulus value in the RGB color system as a value of each pixel is input, and the first tristimulus value is converted into an XYZ color system tristimulus value. A second tristimulus value in a color space approximating a sensory scale is obtained by performing a non-linear transformation in a form to be corrected, and a hue, a saturation, and a lightness are further obtained from the second tristimulus value. A color specifying method for an image, wherein a set of a degree and a brightness is used as a color specification value of a pixel. 2. A plurality of cases are classified according to the magnitude of the sum of the first tristimulus values, and different conversion conditions are applied for each case to convert the first tristimulus values to the second tristimulus values. 2. The method according to claim 1, wherein a non-linear conversion into a value is performed. 3. The nonlinear transformation according to claim 1, wherein the first tristimulus value is subjected to a first-order transformation and the square root of the first tristimulus value is equal to one.
3. The method according to claim 1, wherein a second tristimulus value is obtained by adding the result of the next conversion. 4. The method according to claim 1, wherein in the non-linear conversion, a result obtained by performing a first-order conversion on the first tristimulus value and a result obtained by performing a first-order conversion on a logarithm of the first tristimulus value are added. 3. The method according to claim 1, wherein a tristimulus value is obtained. 5. The method according to claim 1, wherein in the non-linear conversion, a result obtained by performing a first-order conversion on the first tristimulus value and a result obtained by performing a first-order conversion on the square of the first tristimulus value are added. 3. The method according to claim 1, wherein a tristimulus value is obtained. 6. A method for determining a color value of an object having a reference color from a color image of an object having the reference color by applying the color specification method of an image according to any one of claims 1 to 5, The image color identification method according to claim 1 is applied to each pixel of a color image of an object to be inspected to determine the colorimetric value, and each pixel of the object to be inspected. The color difference between each of the colorimetric values for the reference color and the colorimetric value for each pixel of the object to be inspected is within a specified range with respect to the colorimetric value for the reference color. A color extracting method for an image, comprising determining that each pixel of an object to be inspected has the same color as a reference color when the pixel is within a prescribed range. 7. An image pickup apparatus for picking up an object and outputting a color image having tristimulus values of the RGB color system as pixel values,
A display device capable of displaying an image, a color specifying means for obtaining a color specification value of a pixel in a color image by applying the image color specifying method according to claim 1, An input device that specifies a region including a reference color from a color image of an object having the reference color captured by the device and displayed on a display device, and extraction is performed by applying a color specifying unit to pixels in a range specified by the input device. Storage means for storing a specified range of color values including the specified color values, and a color identification means obtained by applying a color identification means to each pixel of a color image obtained by imaging an object to be inspected by an imaging device. Inspection is performed when the colorimetric value is within the range of the colorimetric value stored in the storage means and the color difference between the colorimetric value of the reference color and the colorimetric value of the object to be inspected is within a prescribed range. Judge that each pixel of the object is the same color as the reference color The image processing apparatus characterized by comprising a color extraction means for displaying the pixels on the screen of the display device.