US20040073526A1 - Computer-implemented neural network color matching formulation system - Google Patents
Computer-implemented neural network color matching formulation system Download PDFInfo
- Publication number
- US20040073526A1 US20040073526A1 US09/778,819 US77881901A US2004073526A1 US 20040073526 A1 US20040073526 A1 US 20040073526A1 US 77881901 A US77881901 A US 77881901A US 2004073526 A1 US2004073526 A1 US 2004073526A1
- Authority
- US
- United States
- Prior art keywords
- color
- paint
- input
- output
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 78
- 239000000203 mixture Substances 0.000 title description 12
- 238000009472 formulation Methods 0.000 title description 9
- 239000003973 paint Substances 0.000 claims abstract description 161
- 238000000034 method Methods 0.000 claims abstract description 33
- 239000003086 colorant Substances 0.000 claims description 12
- 239000003607 modifier Substances 0.000 claims 2
- 238000012937 correction Methods 0.000 abstract description 9
- 239000000049 pigment Substances 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 19
- 210000002569 neuron Anatomy 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 238000013459 approach Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000002860 competitive effect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000010422 painting Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 235000021384 green leafy vegetables Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000002364 input neuron Anatomy 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B44—DECORATIVE ARTS
- B44D—PAINTING OR ARTISTIC DRAWING, NOT OTHERWISE PROVIDED FOR; PRESERVING PAINTINGS; SURFACE TREATMENT TO OBTAIN SPECIAL ARTISTIC SURFACE EFFECTS OR FINISHES
- B44D3/00—Accessories or implements for use in connection with painting or artistic drawing, not otherwise provided for; Methods or devices for colour determination, selection, or synthesis, e.g. use of colour tables
- B44D3/003—Methods or devices for colour determination, selection or synthesis, e.g. use of colour tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/462—Computing operations in or between colour spaces; Colour management systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/463—Colour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
- G01J3/504—Goniometric colour measurements, for example measurements of metallic or flake based paints
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
- G01N21/274—Calibration, base line adjustment, drift correction
- G01N21/276—Calibration, base line adjustment, drift correction with alternation of sample and standard in optical path
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
- G01N21/57—Measuring gloss
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
Definitions
- the present invention relates generally to color matching formulation, and more particularly to artificial neural networks used in color matching formulation.
- Vehicle paint laboratories perform paint color matching for numerous applications such as painting parts to match other painted parts and surfaces and painting portions of a vehicle that require body repair. Vehicle paint laboratories handle a great deal of complex information such as color measurement data and historical paint formulations. Numerous decisions are also made in color matching based on human analysis of color-related data. A large group of people, equipment and materials are needed to accomplish this task.
- one color matching approach includes identifying the effect pigments with the aid of a microscope and measuring the color values of the standard.
- Effect pigments include compositions which influence the chromatic and reflective characteristics of the paint. Most notably, effect pigments lend a sparkle characteristic to the paint and may produce color travel.
- color travel denotes a color which changes with viewing angle.
- Software is used to search databases of previous matches based on the data collected.
- an existing formula may provide a close match.
- the existing match can be utilized as a starting point for the color matching process.
- software may provide a recommendation of correcting this formula.
- the corrected formula is mixed, sprayed, and compared to the standard. Further formula corrections are performed until the match is deemed suitably close.
- the standard color is so unique that no existing match will serve as a suitable starting point. In these cases, the colors are “matched from scratch.”
- Software is used to produce a best theoretical match of reflectance curves or other color attributes based on pigments selected by a color technician.
- a deficiency in this lab process is the color matching correction process. Corrections are performed both with and without the aid of software. In general, too many corrections are performed, and they are often ineffective. Deciding how to correct a formula to better match a color standard is often the most difficult part of color matching. The manner in which the pigments interact with the light and one another to produce the color of the paint is complex. Often more than ten formula correction steps are needed to suitably match metallic or pearl colors. Years of training are required for a technician to learn the subtleties of these interactions and to become proficient at correcting formulas.
- the model therefore may not properly account for the complexities of the multiple interactions prevalent in most paint recipes.
- the present invention overcomes these and other disadvantages.
- One particular advantage of this invention is that it allows for continual improvement. As new formulation and color measurement sets are created, they can be added to training sets for the neural networks. As the matching processes continue, the performance of the matching system can increase.
- a method and apparatus for color matching employ paint recipe neural networks.
- the color of a standard is expressed as color values.
- the neural network includes an input layer having nodes for receiving input data related to paint recipes. Weighted connections connect to the nodes of the input layer and have coefficients for weighting the input data.
- An output layer having nodes are either directly or indirectly connected to the weighted connections. The output layer generates output data that is related to the color attributes. The data of the input layer and the data from the output layer are interrelated through the neural network's nonlinear relationship.
- FIG. 1 is a block diagram depicting the components of an alternate embodiment of the present invention's paint recipe neural network
- FIG. 2 is a neural network diagram depicting a structure of the paint recipe neural network
- FIG. 3 is a block diagram depicting the components of an alternate embodiment of the present invention that includes an inverse paint recipe neural network
- FIG. 4 is a block diagram depicting the components of a first preferred embodiment of the present invention that includes a bias adjustment
- FIGS. 5 a and 5 b are flow charts depicting training of the present invention paint color matching neural network
- FIG. 6 is a flow chart depicting the use of the paint color matching neural network for a color retrieval application
- FIG. 7 is a flow chart depicting training of the paint color matching neural network for a color retrieval application
- FIG. 8 is a data table depicting a comparison of the color matching capabilities of the neural network and extended Kubleka-Munk approach for metallic and pearl colors;
- FIG. 9 is a data table depicting the present invention's exemplary training results of blue colors.
- FIG. 1 shows a paint color matching neural network system generally depicted at 10 .
- a paint recipe neural network 12 performs color matching by determining a paint formula or recipe that substantially matches color values of a standard 14 .
- Color values 18 of a standard 14 are measured by a color measuring device 20 .
- Color values refer to color attributes used to quantify color. Examples include, but are not limited to, reflectance values, tristimulus values and color space values.
- L*a*b* color space developed by the Commission International de l'Eclairage. In this system, “L*” represents a luminous intensity. “a*” represents a red/green appearance. “b*” represents a yellow/blue appearance.
- L*, a* and b* values at various angles are obtained via measurement with a multi-angle color measuring device. From a reflection at a pre-selected angle, the color measuring device 20 determines color values of the standard 14 . Thus color values are determined for each pre-selected angle as shown by the reference numeral 22 .
- This color values may include a value designed to quantify color travel. This color value may be a specific combination of the other color values. The color value for quantifying color travel is calculated as the scaled difference between the lightness measured near the gloss angle and at a flop angle.
- the color measuring device 20 may determine the color values by illuminating the sample at a specific angle and measuring the reflectance at other angles.
- One preferred illumination angle is 45 degrees and the preferred observation angles are 25, 45, 75 and 110 degrees measured from the gloss angle.
- a non-limiting example of the color measuring device 20 is the XRite® Model MA58.
- a spherical geometry color measuring device typically used with solid color may be used or a digital camera.
- the paint recipe neural network 12 of the present invention uses the standard's color values 18 to determine a paint recipe that matches the color of standard 14 .
- a starting paint recipe 24 is provided as input to the paint recipe neural network 12 .
- the starting paint recipe 24 includes different paint compositions or bases, such as a black paint base, a white paint base, a blue paint base, and a red paint base.
- the starting paint recipe may be provided in a variety of ways, such as searching a database of historic color match formulations. Alternatively, a technician based on his experience or through the use of a formulation guideline may provide the starting paint recipe.
- a separate neural network provides the starting paint recipe 24 .
- the present invention includes using many paint bases that are suitable for the color matching application at hand. For example, if a color of the standard 14 is predominantly a blue color, then the starting paint recipe 24 includes one or more blue paint bases, white and black, and possibly various effect pigments.
- the paint recipe neural network 12 examines the starting paint recipe 24 relative to the color values 18 of the standard 14 via its neural network structure that is specially trained to evaluate the non-linear interrelationship 29 between the paint recipes 26 and the color values 28 . In one embodiment of the present invention, the paint recipe neural network 12 predicts the color values of a particular paint recipe at angles that correspond to the different angles of the color measuring device 20 .
- Color matching comparator module 31 compares predicted color values 30 at different angles from the paint recipe neural network 12 to the color values 18 of the standard 14 at corresponding angles to determine how different the predicted color values 30 are from the color values 18 of the standard 14 .
- Color matching comparator module 31 may utilize fuzzy logic to determine the significance of the difference between the predicted color values and color values of the standard 14 .
- Decision block 32 evaluates whether the difference is within a preselected threshold. If the difference is within the preselected threshold, then an acceptable paint recipe 34 is provided as output so that it can be used to formulate paint to match the color of the standard.
- paint recipe modification module 36 may apply constraints to the modification process. These may be implemented via fuzzy logic techniques. Constraints are used to enhance the performance of the color matching system or to enforce rules of paint recipe formulation. Enforcement of rules, for example, may include specifications on the minimum and maximum usage amounts for a particular base.
- the paint recipe neural network 12 is a “modular network” with separate networks.
- the “modular network” provides a group of neural networks, each trained for particular regions of the color space. For example, a separate neural network is used for reds, blues, greens and yellows. Alternatively, a separate neural network can be established for light reds, dark reds, light blues, dark blues, etc.
- Paint recipe neural network 12 is used for color formulation correction, matching from scratch, searching databases for the closest match, identification of formula or measurement mistakes in databases, and enhancing paint formula conversion routines. Skilled artisans will appreciate that there are other uses of the paint recipe neural network 12 .
- FIG. 2 depicts a neural network 50 diagram used in the paint color matching neural network system.
- Paint recipe neural network 50 includes three layers of neurons that include an input layer 52 , a hidden layer 54 and an output layer 56 .
- the input layer 52 preferably has a number of nodes 58 equal to the number of base paints of a region of the color space used by the modular network approach of the present invention.
- the hidden layer 54 preferably has a number of neurons equal to the number of input neurons.
- the output layer 56 represents the color values. For example, in the embodiment that uses L*, a*, b* color values, the output layer contains three neurons representing L*, a*, and b* values for each angle of color measurement for each angle at which color is measured.
- FIG. 3 depicts an alternate embodiment of the present invention wherein an inverse paint recipe neural network 80 is used to generate the starting paint recipe 24 .
- the inverse paint recipe neural network 80 determines a paint recipe based upon input color values.
- the inverse paint recipe neural network 80 uses an inverted neural network structure to determine the starting paint recipe 24 in that its input nodes correspond to the input color values (e.g., L*, a*, b*) and its output nodes correspond to paint bases.
- FIG. 4 depicts a preferred embodiment of the present invention wherein the paint recipe neural network 12 is used in a bias adjustment of the color values 18 of the standard 14 prior to recipe correction.
- the paint recipe neural network 12 generates the predicted color values 30 of the starting recipe based on color matching inputs 100 .
- the predicted color values 30 are used to add bias 110 to the standard's color values.
- the recipe adjustment step 114 is performed wherein the paint recipe neural network 12 generates predicted color values 30 based upon the paint recipe 120 of the sample.
- the adding of bias to the standard's color values is used by the present invention to account for some of the variability present in the color matching processes.
- the bias compensates for such problems as instrumentation drift, minor variation in base color quality and imperfect fit of the neural network to the data set.
- the adding of bias to the standard's color values thereby enhances the performance of the paint color matching neural network system.
- the predicted color values 30 are then compared to the standard's color values at 130 .
- a decision block 140 determines whether an acceptable paint recipe is provided. If an acceptable paint recipe is provided as determined at 150 , then the process ends; otherwise, recipe modification occurs at 160 and recipe adjustment 114 iterates.
- FIGS. 5 a and 5 b are flow charts depicting training for the paint recipe neural networks.
- the paint recipe neural networks are trained using the back-propagation training method, although it should be appreciated that other types of training mechanisms could be used. Thousands of epochs (iterations through the training set) were performed for each network.
- the neural network systems were incorporated into a software program that performs a color correction routine using the relationship between paint recipes and color values learned by the networks. Both the training routines and the color correction program were written in the Java computer language.
- the training of the neural network is accomplished by feeding into inverse paint recipe neural network 80 the color values 210 associated with network historic color recipes.
- Network historic color recipes are developed via the color matching process.
- the connection weights in the inverse paint recipe neural network 80 are modified until the difference between the predicted and actual recipe is sufficiently small.
- the adjustment of the weights of the inverse paint recipe neural network 80 is based on the difference.
- the training of paint recipe neural network 12 is accomplished by providing the network historic color recipes.
- the output of the paint recipe neural network 12 is the color values.
- the connection weights in paint recipe neural network 12 are modified until the difference between the predicted and measured (actual) color values is sufficiently small.
- FIG. 6 depicts a color retrieval neural network 320 .
- Color retrieval neural network 320 selects a standard 322 that has the closest color to the color values of the sample 324 .
- An advantage to using color retrieval neural network 320 is that through the training process, the color retrieval neural network 320 analyzes the color values for the significant features which distinguish the best retrieval. For example, if the reflectance values are provided as input, color retrieval neural network 320 learns to distinguish the important characteristics of the associated reflectance curves. This analysis ability is learned by color retrieval neural network 320 and does not have to be specifically programmed into the system.
- One preferred network architecture is a self-organizing map network.
- a self-organizing map network uses “internal training” based on competitive learning.
- a self-organizing map network has one input layer and only one processing layer. Each neuron in the processing layer is connected to the other neurons in this layer. The network has no output layer. For each input vector, a neuron in the processing layer is selected as the best match. The mapping then is from input space to the set of neurons in the processing layer.
- the network has 31 inputs (points on the reflectance curve), and contains 1000 neurons in the processing layer, and is trained on the data set. Afterwards, sample data is submitted to the network and the neuron 326 corresponding to the best match member of the search database is selected. The network learns to identify which features of the reflectance curve are important for classifying the colors.
- a “modular network” composed of smaller self-organizing map networks can be utilized. This approach simplifies the training process and produces better results.
- One non-limiting example includes the color space of the search database being split into four parts. A neural network is established for each color space. A fifth network serves as the “conductor” sending the input data to the appropriate network based on L*, a*, b* or reflectance data.
- FIG. 7 depicts the training of the color retrieval neural network 420 .
- Color values 422 of samples are inputted into the color retrieval neural network 420 and a vector of neuron responses 424 is generated.
- the vector of neuron responses 424 is compared with the desired response. The comparison yields a difference which is used at block 426 to modify the weights until each neuron responds only to one set of color values. If the network architecture is a self-organizing map network, then the self-organizing map network uses “internal training” based on competitive learning.
- FIG. 8 depicts the “delta E” results of the color matching neural networks.
- the term “delta E” is indicative of the difference between the target color value and another color value.
- the tem “delta E” represents the Euclidean distance between two sets of L*, a*, b* values.
- the CIE color value differences represented as dE25 (color value differences at 25 degrees), dE45 (color value differences at 45 degrees) and dE75 (color value differences at 75 degrees) between the target and the recipes (predicted by the present invention and sprayed out) decrease for the neural network as compared to the Kubleka-Munk approach.
- FIG. 9 shows the results of the training a paint recipe neural network with blue colors.
- the “delta E” represents the color difference between the standard's L*, a*, b* color values and network predicted L*, a*, b* color values. These color difference values were sorted into ranges of 1 unit.
- the “number of colors” associated with each color difference value is provided. For example, there were 755 colors where the difference between predicted and measured color values was between 2.0 and 3.0 dE units, indicating the prediction capability of the paint color matching neural network for a particular training set from the blue color region.
- the color matching neural networks of the present invention handles many different types of color values. Color values that are in cylindrical, spherical coordinates or any color value system derived from reflectance data may be used by the present invention for color matching. Alternatively, the reflectance data may be used. Also, the color matching neural networks of the present invention are applicable to color matching for a variety of paints, such as solid colors and metallic/pearl colors.
- the present invention handles color values derived from many different illuminants at many different angles (especially at the aforementioned “lower” angles).
- color values at different angles can be measured using incandescent illumination and other types of illuminants (such as, fluorescent lighting).
- the color matching neural networks of the present invention can produce for a color matching application a paint recipe based upon color values from different illuminants at different angles. The use of different illuminants reduces the problem of metamerism in color matching.
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectrometry And Color Measurement (AREA)
- Color Image Communication Systems (AREA)
Abstract
A method and apparatus for color matching are provided, in which paint recipe neural networks are utilized. The color of a standard is expressed as color values. The neural network includes an input layer having nodes for receiving input data related to paint bases. Weighted connections connect to the nodes of the input layer and have coefficients for weighting the input data. An output layer having nodes are either directly or indirectly connected to the weighted connections and generates output data related to color values. The data to the input layer and the data from the output layer are interrelated through the neural network's nonlinear relationship. The paint color matching neural network can be used for, but not limited to, color formula correction, matching from scratch, effect pigment identification, selection of targets for color tools, searching existing formulas for the closest match, identification of formula mistakes, development of color tolerances and enhancing conversion routines.
Description
- 1. Field of the Invention
- The present invention relates generally to color matching formulation, and more particularly to artificial neural networks used in color matching formulation.
- 2. Description of Related Art
- Vehicle paint laboratories perform paint color matching for numerous applications such as painting parts to match other painted parts and surfaces and painting portions of a vehicle that require body repair. Vehicle paint laboratories handle a great deal of complex information such as color measurement data and historical paint formulations. Numerous decisions are also made in color matching based on human analysis of color-related data. A large group of people, equipment and materials are needed to accomplish this task.
- Presently, one color matching approach includes identifying the effect pigments with the aid of a microscope and measuring the color values of the standard. Effect pigments include compositions which influence the chromatic and reflective characteristics of the paint. Most notably, effect pigments lend a sparkle characteristic to the paint and may produce color travel. The term “color travel” denotes a color which changes with viewing angle.
- Software is used to search databases of previous matches based on the data collected. In some cases, an existing formula may provide a close match. In other instances, the existing match can be utilized as a starting point for the color matching process. In such cases, software may provide a recommendation of correcting this formula. The corrected formula is mixed, sprayed, and compared to the standard. Further formula corrections are performed until the match is deemed suitably close. In some cases, the standard color is so unique that no existing match will serve as a suitable starting point. In these cases, the colors are “matched from scratch.” Software is used to produce a best theoretical match of reflectance curves or other color attributes based on pigments selected by a color technician.
- A deficiency in this lab process is the color matching correction process. Corrections are performed both with and without the aid of software. In general, too many corrections are performed, and they are often ineffective. Deciding how to correct a formula to better match a color standard is often the most difficult part of color matching. The manner in which the pigments interact with the light and one another to produce the color of the paint is complex. Often more than ten formula correction steps are needed to suitably match metallic or pearl colors. Years of training are required for a technician to learn the subtleties of these interactions and to become proficient at correcting formulas.
- Traditional computer software that assists the technician in his tasks has several disadvantages. Traditional computer software has not proven to be very effective on colors containing “effect pigments.” This software is typically based on a physical model of the interaction between illuminating light and the coating. These physical models involve complex physics and typically do not account for all aspects of the phenomena. A traditional approach is to use a model based on the work of Kubleka-Munk or modifications thereof. The model is difficult to employ with data obtained from multi-angle color measuring devices. One particular difficulty is handling specular reflection that occurs near the gloss angle. Another deficiency of the Kubleka-Munk based models is that only binary or ternary pigment mixtures are used to obtain the constants of the model. The model therefore may not properly account for the complexities of the multiple interactions prevalent in most paint recipes. The present invention overcomes these and other disadvantages. One particular advantage of this invention is that it allows for continual improvement. As new formulation and color measurement sets are created, they can be added to training sets for the neural networks. As the matching processes continue, the performance of the matching system can increase.
- In accordance with the teachings of the present invention, a method and apparatus for color matching are provided that employ paint recipe neural networks. The color of a standard is expressed as color values. The neural network includes an input layer having nodes for receiving input data related to paint recipes. Weighted connections connect to the nodes of the input layer and have coefficients for weighting the input data. An output layer having nodes are either directly or indirectly connected to the weighted connections. The output layer generates output data that is related to the color attributes. The data of the input layer and the data from the output layer are interrelated through the neural network's nonlinear relationship.
- Additional advantages and aspects of the present invention will become apparent from the subsequent description and the appended claims, taken in conjunction with the accompanying drawings in which:
- FIG. 1 is a block diagram depicting the components of an alternate embodiment of the present invention's paint recipe neural network;
- FIG. 2 is a neural network diagram depicting a structure of the paint recipe neural network;
- FIG. 3 is a block diagram depicting the components of an alternate embodiment of the present invention that includes an inverse paint recipe neural network;
- FIG. 4 is a block diagram depicting the components of a first preferred embodiment of the present invention that includes a bias adjustment;
- FIGS. 5a and 5 b are flow charts depicting training of the present invention paint color matching neural network;
- FIG. 6 is a flow chart depicting the use of the paint color matching neural network for a color retrieval application;
- FIG. 7 is a flow chart depicting training of the paint color matching neural network for a color retrieval application;
- FIG. 8 is a data table depicting a comparison of the color matching capabilities of the neural network and extended Kubleka-Munk approach for metallic and pearl colors; and
- FIG. 9 is a data table depicting the present invention's exemplary training results of blue colors.
- FIG. 1 shows a paint color matching neural network system generally depicted at10. A paint recipe
neural network 12 performs color matching by determining a paint formula or recipe that substantially matches color values of a standard 14. Color values 18 of a standard 14 are measured by acolor measuring device 20. Color values refer to color attributes used to quantify color. Examples include, but are not limited to, reflectance values, tristimulus values and color space values. One example of the latter is L*a*b* color space developed by the Commission International de l'Eclairage. In this system, “L*” represents a luminous intensity. “a*” represents a red/green appearance. “b*” represents a yellow/blue appearance. L*, a* and b* values at various angles are obtained via measurement with a multi-angle color measuring device. From a reflection at a pre-selected angle, thecolor measuring device 20 determines color values of the standard 14. Thus color values are determined for each pre-selected angle as shown by thereference numeral 22. This color values may include a value designed to quantify color travel. This color value may be a specific combination of the other color values. The color value for quantifying color travel is calculated as the scaled difference between the lightness measured near the gloss angle and at a flop angle. - The
color measuring device 20 may determine the color values by illuminating the sample at a specific angle and measuring the reflectance at other angles. One preferred illumination angle is 45 degrees and the preferred observation angles are 25, 45, 75 and 110 degrees measured from the gloss angle. A non-limiting example of thecolor measuring device 20 is the XRite® Model MA58. Alternatively, a spherical geometry color measuring device typically used with solid color may be used or a digital camera. - The paint recipe
neural network 12 of the present invention uses the standard's color values 18 to determine a paint recipe that matches the color ofstandard 14. A startingpaint recipe 24 is provided as input to the paint recipeneural network 12. The startingpaint recipe 24 includes different paint compositions or bases, such as a black paint base, a white paint base, a blue paint base, and a red paint base. The starting paint recipe may be provided in a variety of ways, such as searching a database of historic color match formulations. Alternatively, a technician based on his experience or through the use of a formulation guideline may provide the starting paint recipe. In the preferred embodiment, a separate neural network provides the startingpaint recipe 24. - It should be understood that the present invention includes using many paint bases that are suitable for the color matching application at hand. For example, if a color of the standard14 is predominantly a blue color, then the starting
paint recipe 24 includes one or more blue paint bases, white and black, and possibly various effect pigments. - The paint recipe
neural network 12 examines the startingpaint recipe 24 relative to the color values 18 of the standard 14 via its neural network structure that is specially trained to evaluate thenon-linear interrelationship 29 between thepaint recipes 26 and the color values 28. In one embodiment of the present invention, the paint recipeneural network 12 predicts the color values of a particular paint recipe at angles that correspond to the different angles of thecolor measuring device 20. - Color
matching comparator module 31 compares predictedcolor values 30 at different angles from the paint recipeneural network 12 to the color values 18 of the standard 14 at corresponding angles to determine how different the predictedcolor values 30 are from the color values 18 of the standard 14. Colormatching comparator module 31 may utilize fuzzy logic to determine the significance of the difference between the predicted color values and color values of the standard 14.Decision block 32 evaluates whether the difference is within a preselected threshold. If the difference is within the preselected threshold, then anacceptable paint recipe 34 is provided as output so that it can be used to formulate paint to match the color of the standard. - If the difference is not within the preselected threshold as determined by the
decision block 32, then the current paint recipe is modified by a paintrecipe modification module 36. An adjustedpaint recipe 38 is provided to the paint recipeneural network 12 so that the new predictedcolor values 30 can be determined by the paint recipeneural network 12. The new predictedcolor values 30 are again compared with the standard's color values. The paint recipe is adjusted until the difference is within the preselected threshold. With each iteration, the present invention generates predicted color values that converge to thecolor value 18 of the standard 14. Paintrecipe modification module 36 may apply constraints to the modification process. These may be implemented via fuzzy logic techniques. Constraints are used to enhance the performance of the color matching system or to enforce rules of paint recipe formulation. Enforcement of rules, for example, may include specifications on the minimum and maximum usage amounts for a particular base. - In a preferred embodiment, the paint recipe
neural network 12 is a “modular network” with separate networks. The “modular network” provides a group of neural networks, each trained for particular regions of the color space. For example, a separate neural network is used for reds, blues, greens and yellows. Alternatively, a separate neural network can be established for light reds, dark reds, light blues, dark blues, etc. - Paint recipe
neural network 12 is used for color formulation correction, matching from scratch, searching databases for the closest match, identification of formula or measurement mistakes in databases, and enhancing paint formula conversion routines. Skilled artisans will appreciate that there are other uses of the paint recipeneural network 12. - FIG. 2 depicts a
neural network 50 diagram used in the paint color matching neural network system. Paint recipeneural network 50 includes three layers of neurons that include aninput layer 52, a hiddenlayer 54 and anoutput layer 56. Theinput layer 52 preferably has a number ofnodes 58 equal to the number of base paints of a region of the color space used by the modular network approach of the present invention. The hiddenlayer 54 preferably has a number of neurons equal to the number of input neurons. Theoutput layer 56 represents the color values. For example, in the embodiment that uses L*, a*, b* color values, the output layer contains three neurons representing L*, a*, and b* values for each angle of color measurement for each angle at which color is measured. - FIG. 3 depicts an alternate embodiment of the present invention wherein an inverse paint recipe
neural network 80 is used to generate the startingpaint recipe 24. The inverse paint recipeneural network 80 determines a paint recipe based upon input color values. The inverse paint recipeneural network 80 uses an inverted neural network structure to determine the startingpaint recipe 24 in that its input nodes correspond to the input color values (e.g., L*, a*, b*) and its output nodes correspond to paint bases. - FIG. 4 depicts a preferred embodiment of the present invention wherein the paint recipe
neural network 12 is used in a bias adjustment of the color values 18 of the standard 14 prior to recipe correction. The paint recipeneural network 12 generates the predictedcolor values 30 of the starting recipe based oncolor matching inputs 100. The predictedcolor values 30 are used to addbias 110 to the standard's color values. After the bias is added, therecipe adjustment step 114 is performed wherein the paint recipeneural network 12 generates predictedcolor values 30 based upon thepaint recipe 120 of the sample. The adding of bias to the standard's color values is used by the present invention to account for some of the variability present in the color matching processes. The bias compensates for such problems as instrumentation drift, minor variation in base color quality and imperfect fit of the neural network to the data set. The adding of bias to the standard's color values thereby enhances the performance of the paint color matching neural network system. The predictedcolor values 30 are then compared to the standard's color values at 130. Adecision block 140 determines whether an acceptable paint recipe is provided. If an acceptable paint recipe is provided as determined at 150, then the process ends; otherwise, recipe modification occurs at 160 andrecipe adjustment 114 iterates. - FIGS. 5a and 5 b are flow charts depicting training for the paint recipe neural networks. The paint recipe neural networks are trained using the back-propagation training method, although it should be appreciated that other types of training mechanisms could be used. Thousands of epochs (iterations through the training set) were performed for each network. The neural network systems were incorporated into a software program that performs a color correction routine using the relationship between paint recipes and color values learned by the networks. Both the training routines and the color correction program were written in the Java computer language.
- With reference to FIG. 5a, the training of the neural network is accomplished by feeding into inverse paint recipe
neural network 80 the color values 210 associated with network historic color recipes. Network historic color recipes are developed via the color matching process. The connection weights in the inverse paint recipeneural network 80 are modified until the difference between the predicted and actual recipe is sufficiently small. The adjustment of the weights of the inverse paint recipeneural network 80 is based on the difference. - With reference to FIG. 5b, the training of paint recipe
neural network 12 is accomplished by providing the network historic color recipes. The output of the paint recipeneural network 12 is the color values. The connection weights in paint recipeneural network 12 are modified until the difference between the predicted and measured (actual) color values is sufficiently small. - FIG. 6 depicts a color retrieval
neural network 320. Color retrievalneural network 320 selects a standard 322 that has the closest color to the color values of thesample 324. An advantage to using color retrievalneural network 320 is that through the training process, the color retrievalneural network 320 analyzes the color values for the significant features which distinguish the best retrieval. For example, if the reflectance values are provided as input, color retrievalneural network 320 learns to distinguish the important characteristics of the associated reflectance curves. This analysis ability is learned by color retrievalneural network 320 and does not have to be specifically programmed into the system. - One preferred network architecture is a self-organizing map network. A self-organizing map network uses “internal training” based on competitive learning. A self-organizing map network has one input layer and only one processing layer. Each neuron in the processing layer is connected to the other neurons in this layer. The network has no output layer. For each input vector, a neuron in the processing layer is selected as the best match. The mapping then is from input space to the set of neurons in the processing layer.
- For example, if the search database had 1000 members, then the network has 31 inputs (points on the reflectance curve), and contains 1000 neurons in the processing layer, and is trained on the data set. Afterwards, sample data is submitted to the network and the
neuron 326 corresponding to the best match member of the search database is selected. The network learns to identify which features of the reflectance curve are important for classifying the colors. - If a database becomes larger, a “modular network” composed of smaller self-organizing map networks can be utilized. This approach simplifies the training process and produces better results. One non-limiting example includes the color space of the search database being split into four parts. A neural network is established for each color space. A fifth network serves as the “conductor” sending the input data to the appropriate network based on L*, a*, b* or reflectance data.
- FIG. 7 depicts the training of the color retrieval
neural network 420. Color values 422 of samples are inputted into the color retrievalneural network 420 and a vector ofneuron responses 424 is generated. The vector ofneuron responses 424 is compared with the desired response. The comparison yields a difference which is used atblock 426 to modify the weights until each neuron responds only to one set of color values. If the network architecture is a self-organizing map network, then the self-organizing map network uses “internal training” based on competitive learning. - FIG. 8 depicts the “delta E” results of the color matching neural networks. Within the present invention, the term “delta E” is indicative of the difference between the target color value and another color value. Within the L*, a*, b* color value system, for example, the tem “delta E” represents the Euclidean distance between two sets of L*, a*, b* values. As demonstrated by FIG. 8, the CIE color value differences represented as dE25 (color value differences at 25 degrees), dE45 (color value differences at 45 degrees) and dE75 (color value differences at 75 degrees) between the target and the recipes (predicted by the present invention and sprayed out) decrease for the neural network as compared to the Kubleka-Munk approach.
- FIG. 9 shows the results of the training a paint recipe neural network with blue colors. The “delta E” represents the color difference between the standard's L*, a*, b* color values and network predicted L*, a*, b* color values. These color difference values were sorted into ranges of 1 unit. The “number of colors” associated with each color difference value is provided. For example, there were755 colors where the difference between predicted and measured color values was between 2.0 and 3.0 dE units, indicating the prediction capability of the paint color matching neural network for a particular training set from the blue color region.
- Those skilled in the art can now appreciate from the foregoing description that the broad teachings of the present invention can be implemented in a variety of forms. For example, the color matching neural networks of the present invention handles many different types of color values. Color values that are in cylindrical, spherical coordinates or any color value system derived from reflectance data may be used by the present invention for color matching. Alternatively, the reflectance data may be used. Also, the color matching neural networks of the present invention are applicable to color matching for a variety of paints, such as solid colors and metallic/pearl colors.
- Still further, the present invention handles color values derived from many different illuminants at many different angles (especially at the aforementioned “lower” angles). For example, color values at different angles can be measured using incandescent illumination and other types of illuminants (such as, fluorescent lighting). The color matching neural networks of the present invention can produce for a color matching application a paint recipe based upon color values from different illuminants at different angles. The use of different illuminants reduces the problem of metamerism in color matching.
- Therefore, while this invention has been described in connection with particular examples thereof, the true scope of the invention should not be so limited since other modifications will become apparent to the skilled practitioner upon a study of the drawings, specification, and following claims:
Claims (40)
1. A paint color matching system for matching a color standard using paint base colors, comprising:
an input device for entering an initial paint recipe for said color standard that includes one or more paint bases each having a weight;
a neural network that includes an input layer that having a plurality of input nodes that are associated with said paint bases, an output layer having a plurality of output nodes representing output color attribute components, and first weighted connections between said input nodes of said input layer with said output nodes of said output layer,
wherein said first weighted connections determine the contribution of said paint bases at said input layer to each of said output color attribute components; and
a color comparator for comparing input color attribute components associated with said color standard with said output color attribute components.
2. The paint matching system of claim 1 wherein said color attributes are color dimension components.
3. The paint matching system of claim 1 wherein said plurality of output nodes are first, second and third output nodes that represent first, second and third output color dimension components.
4. The paint color matching system of claim 1 further comprising a color measuring device that generates input color data from said color standard at a plurality of different angles, wherein said input color data includes a plurality of input color dimension components.
5. The paint color matching system of claim 4 wherein said plurality of input color dimension components are first, second and third input color dimension components.
6. The paint color matching system of claim 1 wherein output color dimension components are at a plurality of different angles.
7. The paint color matching system of claim 1 further comprising:
at least one hidden layer having nodes connected to said first weighted connections, said hidden layer being disposed between said input and output layers; and
second weighted connections connected to said hidden layer nodes and to said output layer nodes, each of said second weighted connections having a coefficient for weighting said outputs of said hidden layer nodes.
8. The paint color matching system of claim 1 wherein the color values are at angles selected from the group of 15 degrees, 20 degrees, 25 degrees, 45 degrees, 75 degrees, 110 degrees, and combinations thereof.
9. The paint color matching system of claim 1 wherein the color attributes are color values at a flop angle.
10. The paint color matching system of claim 1 wherein the input color attributes and the output color attributes are at angles of 25 degrees, 45 degrees, and a flop angle.
11. The paint color matching system of claim 1 wherein the color attributes are at angles that are less than 30 degrees.
12. The paint color matching system of claim 2 wherein the color dimension components are from a Cartesian coordinate system.
13. The paint color matching system of claim 1 wherein the first dimension of the color coordinate system is indicative of lightness-darkness color attribute, wherein the second dimension of the color coordinate system is indicative of redness-blueness color attribute, wherein the third dimension of the color coordinate system is indicative of yellowness-greenness color attribute.
14. The paint color matching system of claim 1 wherein the input color attribute components and the output color attribute components are derived from the L*, a*, b* color coordinate system.
15. The paint color matching system of claim 1 wherein the input color attribute components and the output color attribute components are derived from a cylindrical color coordinate system.
16. The paint color matching system of claim 1 wherein the input color attribute components and the output color attribute components are derived from a spherical color coordinate system.
17. The paint color matching system of claim 1 wherein the input data to the input layer includes percentages of at least two paint bases.
18. The paint color matching system of claim 1 wherein the input color attribute components and output color attribute components are a plurality of reflectance values each associated with a specific wavelength.
19. The paint color matching system of claim 1 further comprising:
a color matching comparator connected to the output layer, said comparator performing a comparison between the color values of the standard at different angles with the color values from the output layer at different angles, said comparison determining the level that the input data of paint bases matches the color of the standard.
20. The paint color matching system of claim 1 wherein the input data to the input layer includes percentages of at least two paint bases, said percentages of the at least two paint bases being at first percentages, said paint color matching system further comprising:
a color matching comparator connected to the output layer, said comparator performing a comparison between the color values of the standard at different angles with the color values from the output layer at different angles, said comparison determining the level that the input data of paint bases matches the color of the standard; and
a paint recipe modifier connected to the color matching comparator, said paint recipe modifier adjusting the percentages of the paint bases from the first percentages to second percentages based upon the comparison by the color matching comparator,
said second percentages of the paint bases being provided as input to the paint color matching system in order to generate second color value output data.
21. The paint color matching system of claim 1 further comprising:
a starting paint recipe system connected to the input layer, said starting paint recipe neural network determining a starting paint recipe based upon the color values of the standard.
22. A color matching system for matching a color of a standard using paint bases, said color of the standard being expressed as color values in a color coordinate system, comprising:
a color measuring device that generates input color values from said color standard at a plurality of different angles;
a neural network that includes an input layer having a plurality of input nodes that are associated with said color values, an output layer having at least one output node that represents a paint recipe for said color standard that includes one or more paint bases, and first weighted connections between said input nodes of said input layer with said output nodes of said output layer,
wherein said first weighted connections determine the contribution of said input color values at said input layer to each of said paint bases at said plurality of different angles; and
a color comparator for comparing said input color values with output color values related to said paint recipe.
23. The color matching system of claim 22 further comprising:
a paint neural network that includes a paint input layer having a plurality of paint input nodes that are associated with said paint bases, a paint output layer having at least one paint output node that represents paint output color attribute components, and first paint weighted connections between said paint input nodes of said paint input layer with said paint output nodes of said paint output layer, wherein said first paint weighted connections determine a contribution of said paint bases at said paint input layer to each of said output color attribute components.
24. A method for matching color of a standard using paint bases using a paint color matching system, said color of the standard being expressed as color values, said method comprising:
receiving input data related to the paint bases at an input layer having nodes, said input data based on color values that are generated at different angles;
assigning a first weighted connection to each of said nodes of said input layer, each of said first weighted connections having a coefficient for weighting said input data;
generating output data from an output layer related to color values, said output data based on paint bases, said output layer having nodes connected to said first weighted connections; and
whereby said output data is calculated from a non-linear relationship between said input data and said output data.
25. The method of claim 24 further comprises:
providing at least one hidden layer having nodes connected to said first weighted connections, said hidden layer being interposed between said input layer and said output layer; and
assigning second weighted connections to each of said hidden layer nodes, each of said second weighted connections having a coefficient for weighting said outputs of said hidden layer nodes.
26. The method of claim 24 wherein the output data is based on at least one of different angles.
27. The method of claim 26 wherein a color measuring device measures the color values of the standard at different angles.
28. The method of claim 26 wherein the color values are at angles selected from the group consisting of 15 degrees, 20 degrees, 45 degrees, 75 degrees, 110 degrees and a combination thereof.
29. The method of claim 26 wherein the color values are color values at a flop angle.
30. The method of claim 26 wherein the color values are at angles of 25 degrees, 45 degrees, and a flop angle.
31. The method of claim 26 wherein the color values are at angles that are less than 30 degrees.
32. The method of claim 26 wherein the color values are each a dimension of a three-dimensional coordinate system indicative of a color attribute.
33. The method of claim 26 wherein the three-dimensional coordinate system is a Cartesian coordinate system.
34. The method of claim 26 wherein the first dimension of the Cartesian coordinate system is indicative of lightness-darkness color attribute, wherein the second dimension of the Cartesian coordinate system is indicative of redness-blueness color attribute, wherein the third dimension of the Cartesian coordinate system is indicative of yellowness-greenness color attribute.
35. The method of claim 26 wherein the Cartesian coordinate system is an L*, a*, b* color coordinate system.
36. The method of claim 26 wherein the three-dimensional coordinate system is a cylindrical color coordinate system.
37. The method of claim 26 wherein the three-dimensional coordinate system is a spherical color coordinate system.
38. The method of claim 24 wherein the input data to the input layer includes percentages of at least two paint bases.
39. The method of claim 25 wherein the input data to the input layer includes percentages of at least two paint bases, said percentages of the at least two paint bases being at first percentages, said method further comprising:
comparing the color values of the standard at different angles with the color values from the output layer at different angles to determine a comparison indicating the level that the input data of paint bases matches the color of the standard;
adjusting the percentages of the paint bases from the first percentages to second percentages based upon the comparing of the color values; and
providing said second percentages of the paint bases being as input to the system in order to generate second color value output data.
40. The method of claim 24 further comprising:
determining a starting paint recipe based upon the color values of the standard via a starting paint recipe system, said starting paint recipe neural network connected to the input layer.
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/778,819 US6714924B1 (en) | 2001-02-07 | 2001-02-07 | Computer-implemented neural network color matching formulation system |
PCT/US2002/000408 WO2002063556A2 (en) | 2001-02-07 | 2002-01-08 | Computer-implemented neural network color matching formulation system |
EP02703079A EP1374166A2 (en) | 2001-02-07 | 2002-01-08 | Computer-implemented neural network color matching formulation system |
BR0207023-5A BR0207023A (en) | 2001-02-07 | 2002-01-08 | Color combination formulation system in a computer implemented neural network |
CA002434554A CA2434554C (en) | 2001-02-07 | 2002-01-08 | Computer-implemented neural network color matching formulation system |
AU2002236724A AU2002236724A1 (en) | 2001-02-07 | 2002-01-08 | Computer-implemented neural network color matching formulation system |
MXPA03005145A MXPA03005145A (en) | 2001-02-07 | 2002-01-08 | Computer-implemented neural network color matching formulation system. |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/778,819 US6714924B1 (en) | 2001-02-07 | 2001-02-07 | Computer-implemented neural network color matching formulation system |
Publications (2)
Publication Number | Publication Date |
---|---|
US6714924B1 US6714924B1 (en) | 2004-03-30 |
US20040073526A1 true US20040073526A1 (en) | 2004-04-15 |
Family
ID=25114481
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/778,819 Expired - Lifetime US6714924B1 (en) | 2001-02-07 | 2001-02-07 | Computer-implemented neural network color matching formulation system |
Country Status (7)
Country | Link |
---|---|
US (1) | US6714924B1 (en) |
EP (1) | EP1374166A2 (en) |
AU (1) | AU2002236724A1 (en) |
BR (1) | BR0207023A (en) |
CA (1) | CA2434554C (en) |
MX (1) | MXPA03005145A (en) |
WO (1) | WO2002063556A2 (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020184167A1 (en) * | 2001-06-05 | 2002-12-05 | Mcclanahan Craig J. | System and method for converting a color formula using an artificial intelligence based conversion model |
US20020184168A1 (en) * | 2001-06-05 | 2002-12-05 | Mcclanahan Craig J. | System and method for determining acceptability of proposed color solution using an artificial intelligence based tolerance model |
US20040030510A1 (en) * | 2002-03-28 | 2004-02-12 | Van Biemen Willem Frederik | Colour formulation method |
US20060012810A1 (en) * | 2001-08-16 | 2006-01-19 | Sun Chemical Corporation | System and method for controlling metamerism |
US20060031027A1 (en) * | 2004-08-03 | 2006-02-09 | Alman David H | Method and apparatus for predicting properties of a chemical mixture |
US6999615B2 (en) | 2001-06-05 | 2006-02-14 | Basf Corporation | Color management and solution distribution system and method |
US20070172113A1 (en) * | 2006-01-20 | 2007-07-26 | Kansai Paint Co., Ltd. | Effective pigment identification method, identification system, identification program, and recording medium therefor |
US20080052023A1 (en) * | 2006-08-22 | 2008-02-28 | Wilhelm Kettler | Method for color matching |
US20080060079A1 (en) * | 2004-08-11 | 2008-03-06 | Fuji Xerox Co., Ltd. | Authenticity Determination Method, Apparatus, and Program |
US20080192273A1 (en) * | 2001-08-16 | 2008-08-14 | Sun Chemical Corporation | System and Method For Disseminating Color Ink and Colorant Formulas |
JP2010501854A (en) * | 2006-08-22 | 2010-01-21 | イー・アイ・デュポン・ドウ・ヌムール・アンド・カンパニー | Color matching method |
JP2010528284A (en) * | 2007-05-24 | 2010-08-19 | イー・アイ・デュポン・ドウ・ヌムール・アンド・カンパニー | Color matching method |
US20130041858A1 (en) * | 2007-06-20 | 2013-02-14 | Kansai Paint Co., Ltd. | Coating color database creating method, search method using the database, their system, program, and recording medium |
US20160019208A1 (en) * | 2013-03-07 | 2016-01-21 | Akzo Nobel Coatings International B.V. | Process for matching paint |
US20170116517A1 (en) * | 2015-10-27 | 2017-04-27 | International Business Machines Corporation | System and method for generating material compositions |
CN107944549A (en) * | 2017-12-08 | 2018-04-20 | 成都谷问信息技术有限公司 | Data analysing method based on artificial intelligence |
KR20180074756A (en) * | 2015-10-29 | 2018-07-03 | 바스프 코팅스 게엠베하 | How to check the texture parameters of the paint |
US10613727B2 (en) | 2016-02-19 | 2020-04-07 | Ppg Industries Ohio, Inc. | Color and texture match ratings for optimal match selection |
US11062479B2 (en) | 2017-12-06 | 2021-07-13 | Axalta Coating Systems Ip Co., Llc | Systems and methods for matching color and appearance of target coatings |
US20220381615A1 (en) * | 2019-11-14 | 2022-12-01 | Basf Coatings Gmbh | Method and Device for Identification of Effect Pigments in a Target Coating |
WO2023076054A1 (en) * | 2021-10-26 | 2023-05-04 | Sekisui Kydex, Llc | Methods and system for adjusting formulation of pigments for dye sublimation |
US20240046444A1 (en) * | 2019-09-19 | 2024-02-08 | Ppg Industries Ohio, Inc. | Systems and methods for mapping coatings to a spatial appearance space |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4652535B2 (en) * | 2000-07-25 | 2011-03-16 | キヤノン株式会社 | Image processing apparatus and method |
US6714924B1 (en) * | 2001-02-07 | 2004-03-30 | Basf Corporation | Computer-implemented neural network color matching formulation system |
US6870614B2 (en) * | 2002-05-30 | 2005-03-22 | General Electric Company | Method, system and computer product for formulating a bi-directional color match |
US7171394B2 (en) * | 2003-10-30 | 2007-01-30 | Ford Motor Company | Global paint process optimization |
US20070026426A1 (en) * | 2005-04-26 | 2007-02-01 | Applera Corporation | System for genetic surveillance and analysis |
US20090157212A1 (en) * | 2007-12-12 | 2009-06-18 | Basf Corporation | System and method of determining paint formula having a effect pigment |
US20090276254A1 (en) * | 2008-04-30 | 2009-11-05 | Ppg Industries Ohio, Inc. | Color formulation selection process |
US20090274827A1 (en) * | 2008-04-30 | 2009-11-05 | Ppg Industries Ohio, Inc. | Color formulation selection process with visual display |
US8629882B2 (en) * | 2008-05-29 | 2014-01-14 | Ppg Industries Ohio, Inc. | Digital color chip |
EP2331921B1 (en) | 2008-09-29 | 2019-05-15 | Coatings Foreign IP Co. LLC | Method for color matching |
US8743364B2 (en) * | 2009-12-02 | 2014-06-03 | Axalta Coating Systems Ip Co., Llc | Method and system for matching color and coarseness appearance of coatings |
US8760462B2 (en) * | 2010-05-06 | 2014-06-24 | Columbia Insurance Company | Color management method for color representation with self-luminous color primaries |
US8782026B2 (en) | 2011-03-31 | 2014-07-15 | Honda Motor Co., Ltd. | Color harmony with process and environmental feedback |
US20140244558A1 (en) | 2011-06-20 | 2014-08-28 | Axal Ta Coating Systems Ip Co., Llc | Method for matching sparkle appearance of coatings |
EP2887275A1 (en) | 2013-12-20 | 2015-06-24 | BASF Coatings GmbH | Method and system for determining a color formula |
CN105701120B (en) | 2014-11-28 | 2019-05-03 | 华为技术有限公司 | The method and apparatus for determining semantic matching degree |
US10007863B1 (en) | 2015-06-05 | 2018-06-26 | Gracenote, Inc. | Logo recognition in images and videos |
JP6717058B2 (en) * | 2016-06-01 | 2020-07-01 | 凸版印刷株式会社 | Reproduction color profile correction system, reproduction color profile correction method and program |
WO2018064742A1 (en) | 2016-10-04 | 2018-04-12 | Spray-Net Canada Inc. | System and method for selecting paint compositions based on expected paint application conditions |
WO2018231982A1 (en) * | 2017-06-13 | 2018-12-20 | X-Rite, Incorporated | Hyperspectral imaging spectrophotometer and system |
CN114417736B (en) * | 2022-03-14 | 2022-08-09 | 深圳市玄羽科技有限公司 | Color formula evaluation method, system, device and medium |
CN116005157B (en) * | 2022-12-13 | 2023-12-19 | 苏州圆格电子有限公司 | Neodymium iron boron surface pretreatment method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5559173A (en) * | 1993-10-04 | 1996-09-24 | General Electric Company | System for controlling the color of compounded polymer(s) using in-process color measurements |
US5907495A (en) * | 1997-06-27 | 1999-05-25 | General Motors Corporation | Method of formulating paint through color space modeling |
Family Cites Families (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB1056358A (en) | 1962-10-19 | 1967-01-25 | Ciba Ltd | Improvements in and relating to the manufacture of colouring compositions |
EP0484564A1 (en) | 1990-11-05 | 1992-05-13 | Kansai Paint Co., Ltd. | Metered color matching method |
US5386496A (en) | 1991-02-15 | 1995-01-31 | Toyo Ink Mfg. Co., Ltd. | Method and device for nonlinear transformation of colour information by neural network |
US5410637A (en) | 1992-06-18 | 1995-04-25 | Color And Appearance Technology, Inc. | Color tolerancing system employing fuzzy logic |
FR2698982B1 (en) | 1992-12-09 | 1995-02-10 | Guillemin Jean Pierre | Method of improving the color quality, corresponding structure and use in the search for a shade to be matched. |
DE69324899T2 (en) | 1992-12-15 | 1999-10-21 | E.I. Du Pont De Nemours And Co., Wilmington | Color matching method and device |
US5424959A (en) * | 1993-07-19 | 1995-06-13 | Texaco Inc. | Interpretation of fluorescence fingerprints of crude oils and other hydrocarbon mixtures using neural networks |
EP0637731B1 (en) | 1993-08-06 | 1998-11-04 | Toyota Jidosha Kabushiki Kaisha | Method of color reproduction |
US5559604A (en) | 1993-09-27 | 1996-09-24 | Toyo Ink Manufacturing Co., Ltd. | Color matching apparatus for reproducing the same color under different illuminants |
JPH07160871A (en) | 1993-12-09 | 1995-06-23 | Mieko Nagashima | Method and device for correcting color picture |
US5729360A (en) | 1994-01-14 | 1998-03-17 | Fuji Xerox Co., Ltd. | Color image processing method and system |
JP3417051B2 (en) | 1994-05-20 | 2003-06-16 | 東洋インキ製造株式会社 | Color information processing method and apparatus using feature parameter values independent of light source |
US5546195A (en) | 1994-08-11 | 1996-08-13 | Toyo Ink Manufacturing Co., Ltd. | Apparatus for reproducing color images |
GB2293448B (en) | 1994-09-20 | 1996-12-11 | Honda Motor Co Ltd | Method of determining color tone of glitter-containing coating |
KR0183703B1 (en) * | 1994-11-30 | 1999-05-01 | 김광호 | Method and apparatus for defrosting ga-fuzzy theory using refrigeration-refrigerators |
US6081796A (en) * | 1995-01-31 | 2000-06-27 | Matsushita Electric Industrial Co., Ltd. | Proportion predicting system and method of making mixture |
US5680327A (en) | 1995-03-21 | 1997-10-21 | Light Source Computer Images, Inc. | Apparatus and process for a digital swatchbook |
US5687000A (en) | 1995-03-24 | 1997-11-11 | Toyo Ink Manufacturing Co., Ltd. | Colorant-amount transforming method |
JP3287177B2 (en) | 1995-05-17 | 2002-05-27 | 東洋インキ製造株式会社 | Color imaging method and apparatus |
JP3115508B2 (en) | 1995-06-21 | 2000-12-11 | シャープ株式会社 | Color image processing equipment |
US5680333A (en) | 1995-09-28 | 1997-10-21 | E. I. Du Pont De Nemours And Company | Predictive simulation of heather fabric appearance |
US5761070A (en) | 1995-11-02 | 1998-06-02 | Virginia Tech Intellectual Properties, Inc. | Automatic color and grain sorting of materials |
JPH09163382A (en) | 1995-12-07 | 1997-06-20 | Toyo Ink Mfg Co Ltd | Color slurring correction method and device |
US5808621A (en) | 1996-04-30 | 1998-09-15 | 3Dfx Interactive, Incorporated | System and method for selecting a color space using a neural network |
AU4316397A (en) | 1996-09-05 | 1998-04-14 | Wea Manufacturing Inc. | Spectrophotometric neural network |
DE19636774C2 (en) | 1996-09-10 | 1999-04-22 | Herberts Gmbh | Process for adjusting a color formulation |
US5899605A (en) | 1996-09-26 | 1999-05-04 | Xerox Corporation | Color mixing and color system for use in a printing machine |
US5813798A (en) * | 1997-03-28 | 1998-09-29 | Whiffen; Greg | Piecewise continuous control of groundwater remediation |
US6362808B1 (en) | 1997-07-03 | 2002-03-26 | Minnesota Mining And Manufacturing Company | Arrangement for mapping colors between imaging systems and method therefor |
JP3469767B2 (en) | 1998-01-26 | 2003-11-25 | 関西ペイント株式会社 | Classification method of metallic paint color |
JP2000311243A (en) | 1999-04-28 | 2000-11-07 | Sony Corp | Image color correction method and device |
US6714924B1 (en) * | 2001-02-07 | 2004-03-30 | Basf Corporation | Computer-implemented neural network color matching formulation system |
-
2001
- 2001-02-07 US US09/778,819 patent/US6714924B1/en not_active Expired - Lifetime
-
2002
- 2002-01-08 EP EP02703079A patent/EP1374166A2/en not_active Withdrawn
- 2002-01-08 CA CA002434554A patent/CA2434554C/en not_active Expired - Lifetime
- 2002-01-08 BR BR0207023-5A patent/BR0207023A/en not_active Application Discontinuation
- 2002-01-08 AU AU2002236724A patent/AU2002236724A1/en not_active Abandoned
- 2002-01-08 WO PCT/US2002/000408 patent/WO2002063556A2/en not_active Application Discontinuation
- 2002-01-08 MX MXPA03005145A patent/MXPA03005145A/en active IP Right Grant
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5559173A (en) * | 1993-10-04 | 1996-09-24 | General Electric Company | System for controlling the color of compounded polymer(s) using in-process color measurements |
US5907495A (en) * | 1997-06-27 | 1999-05-25 | General Motors Corporation | Method of formulating paint through color space modeling |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6993512B2 (en) | 2001-06-05 | 2006-01-31 | Basf Corporation | System and method for converting a color formula using an artificial intelligence based conversion model |
US20020184168A1 (en) * | 2001-06-05 | 2002-12-05 | Mcclanahan Craig J. | System and method for determining acceptability of proposed color solution using an artificial intelligence based tolerance model |
US20020184167A1 (en) * | 2001-06-05 | 2002-12-05 | Mcclanahan Craig J. | System and method for converting a color formula using an artificial intelligence based conversion model |
US6999615B2 (en) | 2001-06-05 | 2006-02-14 | Basf Corporation | Color management and solution distribution system and method |
US20060012810A1 (en) * | 2001-08-16 | 2006-01-19 | Sun Chemical Corporation | System and method for controlling metamerism |
US7268918B2 (en) * | 2001-08-16 | 2007-09-11 | Sun Chemical Corporation | System and method for controlling metamerism |
US8233189B2 (en) | 2001-08-16 | 2012-07-31 | Sun Chemical Corporation | System and method for disseminating color ink and colorant formulas |
US20080192273A1 (en) * | 2001-08-16 | 2008-08-14 | Sun Chemical Corporation | System and Method For Disseminating Color Ink and Colorant Formulas |
US20040030510A1 (en) * | 2002-03-28 | 2004-02-12 | Van Biemen Willem Frederik | Colour formulation method |
US20060031027A1 (en) * | 2004-08-03 | 2006-02-09 | Alman David H | Method and apparatus for predicting properties of a chemical mixture |
US20080010027A1 (en) * | 2004-08-03 | 2008-01-10 | Alman David H | Method and apparatus for predicting properties of a chemical mixture |
US7936914B2 (en) * | 2004-08-11 | 2011-05-03 | Fuji Xerox Co., Ltd. | Authenticity determination method, apparatus, and program |
US20080060079A1 (en) * | 2004-08-11 | 2008-03-06 | Fuji Xerox Co., Ltd. | Authenticity Determination Method, Apparatus, and Program |
US8290275B2 (en) * | 2006-01-20 | 2012-10-16 | Kansai Paint Co., Ltd. | Effective pigment identification method, identification system, identification program, and recording medium therefor |
US20070172113A1 (en) * | 2006-01-20 | 2007-07-26 | Kansai Paint Co., Ltd. | Effective pigment identification method, identification system, identification program, and recording medium therefor |
JP2010501854A (en) * | 2006-08-22 | 2010-01-21 | イー・アイ・デュポン・ドウ・ヌムール・アンド・カンパニー | Color matching method |
AU2007288330B2 (en) * | 2006-08-22 | 2012-07-12 | Coatings Foreign Ip Co. Llc | Method for color matching |
US20080052023A1 (en) * | 2006-08-22 | 2008-02-28 | Wilhelm Kettler | Method for color matching |
JP2010528284A (en) * | 2007-05-24 | 2010-08-19 | イー・アイ・デュポン・ドウ・ヌムール・アンド・カンパニー | Color matching method |
US20130041858A1 (en) * | 2007-06-20 | 2013-02-14 | Kansai Paint Co., Ltd. | Coating color database creating method, search method using the database, their system, program, and recording medium |
US8606731B2 (en) * | 2007-06-20 | 2013-12-10 | Kansai Paint Co. Ltd. | Coating color database creating method, search method using the database, their system, program, and recording medium |
US10152494B2 (en) * | 2013-03-07 | 2018-12-11 | Akxo Nobel Coatings International B.V. | Process for matching paint |
US20160019208A1 (en) * | 2013-03-07 | 2016-01-21 | Akzo Nobel Coatings International B.V. | Process for matching paint |
US20170115646A1 (en) * | 2015-10-27 | 2017-04-27 | International Business Machines Corporation | System and method for generating material compositions |
US20170116517A1 (en) * | 2015-10-27 | 2017-04-27 | International Business Machines Corporation | System and method for generating material compositions |
KR102073046B1 (en) | 2015-10-29 | 2020-02-04 | 바스프 코팅스 게엠베하 | How to check the texture parameters of the paint |
KR20180074756A (en) * | 2015-10-29 | 2018-07-03 | 바스프 코팅스 게엠베하 | How to check the texture parameters of the paint |
US10401224B2 (en) | 2015-10-29 | 2019-09-03 | Basf Coatings Gmbh | Method for ascertaining texture parameters of a paint |
US10969952B2 (en) | 2016-02-19 | 2021-04-06 | Ppg Industries Ohio, Inc. | Color and texture match ratings for optimal match selection |
US10613727B2 (en) | 2016-02-19 | 2020-04-07 | Ppg Industries Ohio, Inc. | Color and texture match ratings for optimal match selection |
US11062479B2 (en) | 2017-12-06 | 2021-07-13 | Axalta Coating Systems Ip Co., Llc | Systems and methods for matching color and appearance of target coatings |
US11568570B2 (en) | 2017-12-06 | 2023-01-31 | Axalta Coating Systems Ip Co., Llc | Systems and methods for matching color and appearance of target coatings |
US11692878B2 (en) | 2017-12-06 | 2023-07-04 | Axalta Coating Systems Ip Co., Llc | Matching color and appearance of target coatings based on image entropy |
CN107944549A (en) * | 2017-12-08 | 2018-04-20 | 成都谷问信息技术有限公司 | Data analysing method based on artificial intelligence |
US20240046444A1 (en) * | 2019-09-19 | 2024-02-08 | Ppg Industries Ohio, Inc. | Systems and methods for mapping coatings to a spatial appearance space |
US20220381615A1 (en) * | 2019-11-14 | 2022-12-01 | Basf Coatings Gmbh | Method and Device for Identification of Effect Pigments in a Target Coating |
WO2023076054A1 (en) * | 2021-10-26 | 2023-05-04 | Sekisui Kydex, Llc | Methods and system for adjusting formulation of pigments for dye sublimation |
GB2626888A (en) * | 2021-10-26 | 2024-08-07 | Sekisui Kydex Llc | Methods and system for adjusting formulation of pigments for dye sublimation |
Also Published As
Publication number | Publication date |
---|---|
AU2002236724A1 (en) | 2002-08-19 |
MXPA03005145A (en) | 2003-09-22 |
WO2002063556A3 (en) | 2003-10-16 |
CA2434554A1 (en) | 2002-08-15 |
EP1374166A2 (en) | 2004-01-02 |
BR0207023A (en) | 2004-06-22 |
US6714924B1 (en) | 2004-03-30 |
CA2434554C (en) | 2008-12-02 |
WO2002063556A2 (en) | 2002-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6714924B1 (en) | Computer-implemented neural network color matching formulation system | |
US6804390B2 (en) | Computer-implemented neural network color matching formulation applications | |
US6892194B2 (en) | System and method for organizing color values using an artificial intelligence based cluster model | |
EP2161555B1 (en) | Coating color database creating method, search method using the database, their system, program, and recording medium | |
US7536231B2 (en) | Method for determining acceptability of proposed color solution using an artificial intelligence model | |
EP2973247B1 (en) | Systems and methods for texture assessment of a coating formulation | |
Dupont | Study of the reconstruction of reflectance curves based on tristimulus values: comparison of methods of optimization | |
CA2439968C (en) | System and method for converting a color formula using an artificial intelligence based conversion model | |
WO2021132654A1 (en) | Method for producing paint material, method for predicting hue data, and computer color-mixing system | |
US6741260B2 (en) | Method for color matching of bright paint | |
JP6936416B1 (en) | How to make paint and how to predict color data | |
CN115151946A (en) | Methods and apparatus for deploying and using image similarity metrics with deep learning | |
JP4234963B2 (en) | Sample color chart for paint toning | |
JP2003294530A (en) | Calculation method of computer color matching | |
Ruiz et al. | Support Vector Machines for color adjustment in automotive basecoat. | |
US20240310213A1 (en) | Perceptual-realistic Colored Sparkle Evaluation And Measurement System For Image-based Matching Of Color And Appearance Of Coatings Containing Effect Pigments | |
WO2024163728A1 (en) | Image-based matching of color and appearance of coatings containing effect pigments, using a cosine comparison methodology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: BASF CORPORATION, MICHIGAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MCCLANAHAN, CRAIG J.;REEL/FRAME:011578/0800 Effective date: 20010202 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
REMI | Maintenance fee reminder mailed | ||
FPAY | Fee payment |
Year of fee payment: 8 |
|
FPAY | Fee payment |
Year of fee payment: 12 |