JPH07154619A - Color mixer equipment - Google Patents

Abstract

PURPOSE:To allow a desired color picture output device to easily output an object color by using a neural network as a conversion means converting a mixed color resulting from two colors into an analized color value matching the characteristic of each color picture output device. CONSTITUTION:When the operator registers the use of a color picture output device 9a, the color mixture mode is set to a control section 6. Then the control section 6 reads at first a parameter 15 for a neural network of conversion section 2, 4 from a memory section 5 to set the neural network for the conversion sections 2, 4. Upon the receipt of a analized color value from an interactive entry section 1, the value is converted into a color value corresponding to the analized color value through the neural network given to the conversion section 2. Then the converted color value is given to a color mixer section 3 in which the color value is converted into a mixed color value and it is given to the conversion section 4, in which the color value is converted into a color decomposition value for a color picture output device 9a and the result is given to the control section 6. The control section 6 displays the analized color value to a display section 8 and outputs it to an output section 9a.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION The present invention relates to a color separation value, that is,
Additive mixed three primary colors Blue (Blue: Abbreviation B), Green (Gree
n: Abbreviation G), Red (Red: Abbreviation R), or subtractive mixed primary colors cyan (Cyan: Abbreviation C), Magenta (Magenta: Abbreviation M), Yellow (Yellow: Abbreviation Y), Black (Black: Abbreviation K) ) Represents two colors CIEYxy, CIEL * a * b *, CIEL * u * v *, C
The color value is converted into a color value represented by IEXYZ, the color value of the mixed color is obtained by linear interpolation of the color values of the two colors, and the color value is obtained by various color image output devices. The present invention relates to a color mixing device that converts color separation values that match the characteristics of an output device.

[0002]

2. Description of the Related Art Color separation value is one of the methods for expressing colors. This is a value representing a color in accordance with the characteristics of various color image output devices in order to approximately reproduce the color in the color image output device, and is generally a subtractive color mixture of cyan, magenta, yellow, black or Red, green and blue which are additive colors. The color separation value obtained by mixing the colors expressed by these color separation values has conventionally been obtained by a simple arithmetic average of the two color separation values. However, since this value is not a color mixture value in terms of chromaticity, that is, a color mixture in a color value space, it did not represent an accurate color mixture of the two colors.
Further, due to different characteristics of various color image output devices, the same color could not be obtained even if the same color separation value was output to the color image output device.

[0003]

Therefore, an object of the present invention is to mix two colors (X1, Y1, Z1) and (X2, Y2, Z2), which is one of the features of the color value space. Color (X, Y, Z)
, Which is on a straight line connecting the respective color values, obtains the colorimetrically accurate color value of the input two color mixture, and the color value of the color mixture is calculated by various color image output devices. An object of the present invention is to provide a color mixing device capable of converting into a color separation value according to characteristics.

[0004]

In order to achieve the above object, the present invention is constructed as follows. That is, by giving a signal based on the color separation value, a color separation value of a desired two-color mixture is created, and when reproducing a color image corresponding to the color mixture signal from the color image output device, the signal based on the color separation value is generated. As a color mixing device for converting and inputting to the color image output device, it is composed of an input means for inputting color separation values and a neural network,
In the learning mode, the color separation value output from the color image output device is a color signal of a known standard color chart as a teacher signal,
The color separation value of the standard color chart is used as an input signal, and the conversion characteristic is learned for this input so as to approximate the value of the teacher signal. In the color mixing mode, the signal of the color separation value from the input means is colored. The learning mode includes a first conversion unit that converts the color values into two values, a color mixing unit that linearly interpolates the converted color values of the two colors in a color value space to calculate a color value of a color mixture, and a learning network. Sometimes, the color value of the standard color chart having a known color separation value output from the color image output device is used as an input signal, and the color separation value of the standard color chart is used as a teacher signal. And a second conversion unit that learns the conversion characteristic so as to approximate to, and converts the color value signal from the color mixing unit into a color separation value signal in the color mixing mode.

[0005]

In the above structure, in the color mixing mode, first, the color separation values of the desired two colors are input, and the color values CIEYxy, L * a * b *, etc. are converted according to predetermined characteristics, and the color values after the conversion are further converted. Is input to convert the color values of the two colors into a mixed color value by linear interpolation, and further, the mixed color value is input and converted into a color separation value or the like of the color image output unit.
Further, in the calibration mode, the color value from the color measuring unit connected to the color mixing device of the standard color sample whose color separation value from the color image output unit is known is used as the teacher signal, and the known color separation value of the standard color sample is used. As an input to the first conversion means to train the neural network,
The colorimetric value from the colorimetric means connected to the conversion device of the standard color sample from the color image output means is used as an input signal to the colorimetric value conversion means, and the known color separation value of the standard color sample is represented in the table. Since the color value conversion means can be given as a teacher signal to the second conversion means to perform learning of the neural network, the input two colors are mixed into color separation values suitable for the characteristics of each color image output device. It can be converted and output by the color image output device.

As described above, according to the present invention, the neural network is used as the conversion means for converting the mixed color of two colors represented by the color separation value or the color value into the color separation value suitable for the characteristic of each color image output device. When the input color separation value signal is given and color mixture conversion is performed into color separation values suitable for the characteristics of various color image output devices, a reference color sample is output from the color image output device to be used and this is output. By measuring
As a result, the color value of the color sample is obtained, and after learning the first neural network so as to have the characteristic of converting the color separation value into the color value, the reference color sample is output from the color image output device to be used. Is output, the color is measured by a color measuring device, the color value of the color sample is obtained, and the second neural network is learned so as to have a characteristic of converting the color value into a color separation value. After that, the desired color separation values of the two colors are converted into the color separation values of the mixed color of the two colors by the neural network.

The color separation value is color information that depends on the characteristics of each color image output device, and the color image output by the color image output device will have different colors. The color corresponding to the color image output device to be output is obtained by using the neural network that has been learned to measure the standard sample color output in Since the color separation values are obtained, even a color image output device having different characteristics can obtain the color separation values corresponding to the conditions, and the neural network is a neural circuit that performs arithmetic processing. Therefore, the color separation value, which is the conversion value of the neural network, can be obtained as numerical data.

Therefore, according to the present invention, it is possible to know what the value of the color separation value of the desired mixture of the two colors will be in the color image output device to be used, and the desired color can be obtained. The image can be easily output by the image output device.

[0009]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a main configuration of a color mixing apparatus of the present invention. As shown in FIG. 1, a color mixing apparatus of the present invention for converting the color separation value of a target two color mixture into a color separation value corresponding to a desired color image output apparatus, as shown in FIG. Unit 2, color mixing unit 3, conversion unit 4, memory unit 5, control unit 6, color measurement unit 7, display unit 8, output units 9a to 9a.
It is composed of c. The color measuring unit 7 includes output units 9a to 9c.
Load a standard color sample from
It is used to convert to EYxy color system signals. A color measuring device is used as the color measuring unit 7. Here, the colorimetric device is a device for displaying a color by a numerical value, illuminating an object with light,
The intensity of reflected light or transmitted light from that is measured by using the photoelectric principle, and the measured value is calculated by a predetermined calculation method, and three numerical values are displayed as a set of color values. .
Basically, it consists of a light source and a photometer.

In the case of the present system, the colorimetric section 7 calculates the measured values by a predetermined calculation method and outputs the colorimetric values which are a set of three numerical values as a color signal defined by CIE. The conversion unit 2 uses a neural network. Then, a feedforward coupled neural network is used as the neural network, and there are various learning methods for the network.
Back Propagation Algorithm (Runmelhert, DE and McClelland, JL (Eds), "Para
llel Distributied Processing ", Exploraation in the
Microstructure of Cognition. Voll, 2, MIT Press, Ca
mmbridge (1989)]) steepest descent method.

The conversion unit 2 receives the color separation values from the conversational input unit 1 and converts the color separation values into color values. In the calibration mode (learning mode),
The colorimetric color value of the standard color sample from the colorimetric unit 7 is received as a teacher signal, and the color separation value of the color sample is received as an input signal from the memory unit 5, and the color value signal corresponding to the input color separation value signal is received. It has a learning function so that it can be converted into. The color mixing unit 3 mixes the color value signals converted by the conversion unit 2, and linearly interpolates the color values of the two colors in the color space to convert the color values into mixed color values. It is possible to create a mixed color in which the mixing ratio of the two colors is different depending on the interpolation ratio. More specifically, two colors (X1, Y1, Z1) and (X2, Y2,
The color (X, Y, Z) of the sum of Z2) is on the straight line connecting the chromaticity coordinates, and the coordinates x, y are two points (x1, y1), (x2, y
2) Stimulating the distance

[0012]

[Equation 1] and

[0013]

It is created by the internal division with [Equation 2]. The conversion unit 4 receives the color value from the color mixing unit 3 as an input and converts the color value into a color separation value. In the calibration mode (learning mode), the color measurement unit 7 outputs the color value. The colorimetric color value of the standard color sample is received as an input signal, the color separation value of the color sample is received as a teacher signal from the memory unit 5, and learning is performed so that the input color value signal is converted into a corresponding color separation value. Have the function to The control unit 6 is responsible for the necessary control of each component of the conversion unit 2, the color mixing unit 3, and the conversion unit 4 and the center of execution of arithmetic processing. For example, various controls and calculations are performed by software using a microprocessor. The processing is realized. The control unit 6 also has a function of outputting the color separation value signal converted by the conversion unit 4 to the display unit 8 and the output units 9a to 9c connected to the output terminal.

In the calibration mode, the control unit 6 has a function of storing the colorimetric value signal of the standard color sample measured by the colorimetric device in the memory unit 5 and reading and using it in order during learning. I have it. The conversational input unit 1 is composed of, for example, a man-machine interface such as a keyboard and a mouse, and provides commands and instructions for menus.
Enables data input and editing operations. The operation information of the input unit 1 is input to the control unit 6. Display unit 7 and output unit 9
The characters a to 9c are controlled by the controller 6 to perform various displays and outputs.

The memory unit 5 stores color appearance three-attribute color values serving as teacher signals in the neural network, color values corresponding to the color values, and parameters of the neural network after learning. It is read at the time of color value conversion after learning and used for processing in the neural network. The memory unit 5 stores color value data of standard color samples by various color image output devices which are teacher signals in the neural network and each parameter of the neural network after learning, and the parameter is a color specification after learning. It is read at the time of value conversion and used for processing in the neural network. The parameters are stored for each color image output device and are used for each color image output device according to the operator's instruction.

<Example 1 of use> An example of use of the above apparatus will be described below. FIG. 2 is a block diagram of the essential parts showing an example of use of the color mixing apparatus of the present invention. In the figure, the same components as those of the main configuration block diagram 1 described above are designated by the same reference numerals, and detailed description thereof will be omitted. Each parameter of the neural network for which learning is completed in the conversion unit 2 and the conversion unit 4 stored in the memory unit 5 is read out to prepare for the color mixing mode. In the color mixing mode, the conversion unit 2 receives the desired color separation values of the two colors from the conversational input unit 1 and converts the color separation values into color values. The color mixing unit 3 mixes the color value signals converted by the conversion unit 2,
The color values of the colors are linearly interpolated in the color space to be converted into the color values of the mixed colors, and it is possible to create a mixed color in which the mixing ratio of the two colors is different depending on the interpolation ratio.

The conversion unit 4 receives the color value from the color mixing unit 3 and converts the color value into a color separation value. The color value is received in the color mixing mode, and the input color value is received. The signal is converted so as to have a corresponding color separation value, and the color separation value is output to the output unit through the control unit 6 to obtain the output product 21a of the mixed color of the two colors from the output unit 8. <Use Example 2> A use example of the above apparatus will be described below. FIG. 3 is a block diagram of the essential parts showing an example of use of the color mixing apparatus of the present invention. In the figure, the same components as those of the main configuration block diagram 1 described above are designated by the same reference numerals, and detailed description thereof will be omitted.

The parameters of the learning-completed neural network of the conversion unit 4 stored in the memory unit 5 are read out to prepare for the color mixing mode. The color mixing section 3 is a color measurement section 7
For mixing color value signals input from
The color values of the colors are linearly interpolated in the color space to be converted into the color values of the mixed colors, and it is possible to create a mixed color in which the mixing ratio of the two colors is different depending on the interpolation ratio. The conversion unit 4 receives the color value from the color mixing unit 3 and converts the color value into a color separation value. The color value is received in the color mixing mode, and the input color value signal corresponds to the color value. The color separation value is output to the output unit through the control unit 6, and the output product 21a obtained by mixing the two colors is obtained from the output unit 8.

Next, the operation of the present system having the above configuration will be described. The present apparatus having such a configuration is an apparatus for signal matching processing that is capable of performing conversion so that a desired color mixture of two colors becomes a separation value of a target color image output apparatus colorimetric apparatus. The color image output device to be used is to obtain a target color separation value regardless of the type of device, and a standard color sample is obtained from the color image output device to be used. Colorimetrically measure with a colorimeter to obtain a color value such as CIEYxy colorimetric system, learn the relationship with the color separation value of the standard color sample and use it for colorimetric value conversion. If the color separation values of the two colors are input, the characteristics of the color image output device are added so that the color values can be obtained, the obtained color values are mixed in the color space, and the mixed color values are obtained. , A standard color sample from the color image output device to be used Obtained and measured with a color measuring device, for example, to obtain a color value such as the CIEYxy color system, and learn the relationship with the color separation value of the standard color sample described above and use it for color value conversion. By inputting the target color mixture values of the two colors, the color separation values can be obtained by adding the characteristics of different color image output devices.

Therefore, it is necessary to carry out learning as the first step. This is performed in the learning mode, and its operation will be described with reference to the flowchart of FIG. First, a standard color swatch is prepared, and the standard color swatch is a plurality of ones filled with a single color. To perform learning, the input unit 1 may be operated to set the conversion units 2 and 4 in the calibration mode (learning mode) and a learning execution command may be given. The color separation values of the standard color sample are sequentially read from the memory unit 5 and used for learning. In response to the above-described instruction to execute learning, the control unit 6 of the color mixing apparatus extracts the color separation values in a predetermined order (the reading order of the standard sample color), and supplies them to the conversion unit 2 as an input signal and to the conversion unit 4 as a teacher signal. .

Further, the standard color sample is read by the color measuring section 7 to measure the color. The color values of the standard color sample read by the color measuring unit 7 are temporarily stored in a storage unit (not shown) and sequentially read out for use in learning. After the color measurement of the standard color sample is completed, the control unit 6 of the color mixing device extracts the color values of the standard color sample in a predetermined order (the reading order of the standard sample color) by the instruction of the learning execution described above, and the conversion unit 2 The teacher signal is used as the input signal of the conversion unit 4. Then, the control unit 6 controls the neural networks of the respective conversion units to start learning of the neural network so that the output approaches the teacher signal.

Here, the teacher signal refers to correct answer information for the input, and learning means changing the coupling strength in the neural network so that the output for the input matches the teacher signal. Learning continues until the output meets the required criteria for the teacher signal. When the learning is completed, various parameters of the neural network at the end of the learning are stored in the memory unit 5. As a result, the learning of a certain color image output device is completed. If another color image output device is also planned to be used, the color image output device is connected to the output terminal to learn it, and the same operation as described above is performed to learn the color image output device. Do.

In the case of the embodiment, since the three color image output devices 9a to 9c are planned to be used, learning is performed for each of these three devices. The parameters 15a to 15c, which are the learning results of the three color image output devices 9a to 9c, are separately stored in the memory unit 5 so that they can be selected for each color image output device, and the selection is controlled by the control unit 6. On the basis of this, the input unit 1 and the display unit 8 can specify and select, for example, in a menu format. When all the color image output devices 9a to 9c to be used have been learned, the operator then uses this color mixing device to obtain color separation values at different color image output devices. Next, this operation 1 will be described with reference to FIG.

That is, the operator connects the desired color image output device among the learned color image output devices 9a to 9c to the output terminal of the color mixing device. If the user wants to use the color image output device 9a, the operator operates the input unit 1 to register the use of the color image output device 9a. Then, the control unit 6 becomes a color mixing mode by this, and in this mode, first, the parameters 15 of the neural networks of the conversion units 2 and 4 are read from the memory unit 5 and set in the neural networks of the conversion units 2 and 4. To do. Then, the color separation value is input from the conversational input unit 1, and the conversion unit 2
Is applied to the color value corresponding to the color separation value by the neural network, and the converted color value is input to the color mixing unit 3 and converted into the color value of the mixed color, and then to the conversion unit 4. It is input, converted into the color separation value of the color image output device 9a, and given to the control unit 6.

The control unit 6 causes the display unit 7 to display the color separation value and causes the output unit 8a to output it. Therefore, the operator can confirm the desired two-color mixture. Further, the operation 2 will be described with reference to FIG. That is, the operator connects the desired color image output device among the learned color image output devices 9a to 9c to the output terminal of the color mixing device. If the user wants to use the color image output device 9a, the operator operates the input unit 1 to register the use of the color image output device 9a.

Then, the control unit 6 is brought into a color mixing mode by this, and in this mode, first, from the memory unit 5 to the parameter 1 of the neural network of the conversion unit 4.
5 is read out and set in the neural network of the conversion unit 4. Then, the color value is input from the color measurement unit 7, is given to the color mixing unit 3, and is converted into the color value of the color mixture, and then the conversion unit 4
Is input to the color image output device 9a, converted into color separation values of the color image output device 9a, and provided to the control unit 6. The control unit 6 causes the display unit 7 to display the color separation value and causes the output unit 8a to output it. Therefore, the operator can confirm the desired two-color mixture.

As described above, the present invention uses the neural network as the conversion means for converting the input color separation values of the desired two colors into the color separation values so as to be obtained from the color image output device. When a separation signal is given and converted into the color separation value of another color image output device, the reference color sample is output from the color image output device to be used, the color is measured by the color measuring device, and the color sample concerned is thereby obtained. After learning the neural network so as to obtain the color value of the color image and to convert it into a color separation value by the color image output device, the color separation values of the desired two colors are converted by the neural network of the conversion means. It is designed to be converted.

The color value is information unique to a color that does not depend on the characteristics of each color image output device, and has the property that when the color specification value is determined, the color is also determined. Using color values that have an invariant relationship,
It is used for conversion with color separation values (cyan, magenta, yellow, black or blue, green, red, etc.) that are different for each output device used in a color image output device (see Japanese Patent Application No. 4-319591). Note that the present invention is not limited to the above-described embodiments, and may be appropriately modified and implemented within a range that does not change the gist thereof. For example, in the above-described embodiments, the CIEYxy colorimetric system is used as the colorimetric values. But L * a * b *
Other color values such as color system, XYZ color system, L * u * v * color system may be used.

[0029]

As described in detail above, according to the present invention,
It is possible to provide a color mixing device that allows the user to easily know what color separation value two color mixtures having a desired color separation value will be in the color image output device desired to be used.

[Brief description of drawings]

FIG. 1 is a block diagram for explaining an operation of a device of the present invention during calibration.

FIG. 2 is a block diagram for explaining an operation 1 in the conversion mode of the device of the present invention.

FIG. 3 is a block diagram for explaining operation 2 in the conversion mode of the device of the present invention.

FIG. 4 is a flow chart for explaining the operation of the device of the present invention in the calibration mode.

FIG. 5 is a flow chart for explaining the operation 1 in the conversion mode of the device of the present invention.

FIG. 6 is a flow chart for explaining an operation 2 in the conversion mode of the device of the present invention.

[Explanation of symbols]

1 ---- Conversational input unit, 2 ---- Conversion unit, 3 ---- Color mixing unit, 4
---- Conversion unit, 5 ---- Memory unit, 6 ---- Control unit, 7 ---- Color measurement unit, 8 ---- Display unit, 9a to 9c --- Output unit, 10 --- Input signal, 11 --- Teacher signal, 12 --- Input signal, 13 ---
Teacher signal, 14 --- color separation value, 15a to 15c--parameter, 16a --- standard color sample, 17 --- input signal, 18--
-Output signal, 19 --- Input signal, 20 --- Output signal, 21
a --- Output

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI Technical display location G06T 1/00 H04N 1/40 8420-5L G06F 15/66 310 4226-5C H04N 1/40 Z

Claims (2)

[Claims] 1. A color separation value of two desired colors is created by giving a signal based on the color separation value, and the color separation value is reproduced when a color image corresponding to the color mixture signal is reproduced from a color image output device. As a color mixing device for converting the signal according to (4) and inputting it to the color image output device, it comprises an input means for inputting color separation values and a neural network, and a color output from the color image output device in a learning mode. With the color values of the standard color chart of which the separation values are known as the teacher signal and the color separation values of the standard color chart as the input signal, the conversion characteristics are learned for this input so as to approximate the value of the teacher signal. In the color mixing mode, a first conversion unit that converts the signal of the color separation value from the input unit into a color value, and the converted color values of the two colors in a color value space Color mixing means for linearly interpolating and calculating a color value of a color mixture, comprising a neural network, the color separation value output from the color image output device in the learning mode is a color value of a standard color chart as an input signal, Using the color separation value of the standard color chart as a teacher signal, the conversion characteristics are learned for this input so as to approximate the value of the teacher signal, and in the color mixing mode, the color value signal from the color mixing means is used as a color separation value signal. A second color conversion device for converting into a color mixing device. 2. A signal based on the color value is used for creating a color separation value of a desired color mixture of two colors by giving a signal based on the color value and reproducing a color image corresponding to the color mixture signal from a color image output device. As a color mixing device for converting and inputting into the color image output device, input means for inputting a color value signal, and linearly interpolating the input color values of the two colors in a color value space Color mixing means for calculating the color value of the standard color chart, which is composed of a neural network and has a known color separation value output from the color image output device in the learning mode. The color separation value is used as a teacher signal and the conversion characteristics are learned for this input so as to approximate the value of the teacher signal, and in the color mixing mode, the color value signal from the color mixing means is learned. The color mixing device according to claim 1, further comprising: first conversion means for converting the signal into a color separation value signal.