CN113128104A - Computer color measuring and matching method based on improved BP neural network - Google Patents
Computer color measuring and matching method based on improved BP neural network Download PDFInfo
- Publication number
- CN113128104A CN113128104A CN202110271796.4A CN202110271796A CN113128104A CN 113128104 A CN113128104 A CN 113128104A CN 202110271796 A CN202110271796 A CN 202110271796A CN 113128104 A CN113128104 A CN 113128104A
- Authority
- CN
- China
- Prior art keywords
- neural network
- sample
- color
- color matching
- matching
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012360 testing method Methods 0.000 claims abstract description 33
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 238000004043 dyeing Methods 0.000 claims abstract description 13
- 238000005259 measurement Methods 0.000 claims abstract description 8
- 239000000975 dye Substances 0.000 claims description 32
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 abstract description 2
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 description 10
- 239000000835 fiber Substances 0.000 description 7
- 238000005457 optimization Methods 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 239000004753 textile Substances 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/12—Cloth
Abstract
The invention discloses a computer color measuring and matching method based on an improved BP neural network, which measures and matches colors through a computer and comprises the following steps of S1: and acquiring a sample color matching result C corresponding to the dye matching proportion D and the dyeing matching proportion from the sample, and normalizing the dye matching proportion D and the sample color matching result C to obtain a training sample and a test sample for color measurement and color matching in a separated manner. According to the computer color measuring and matching method based on the improved BP neural network, the traditional color matching mode is improved by establishing a BP neural network model, and higher color matching accuracy and better generalization capability are obtained.
Description
Technical Field
The invention belongs to the technical field of computer color matching, and particularly relates to a computer color measuring and matching method based on an improved BP neural network.
Background
Traditional textile color matching is mainly carried out according to prior knowledge of a color matching master, the workload is large, a large amount of materials are consumed for trying, the requirement cannot be met by manual color matching along with the rapid change of the trend of the times, and computer color matching is rapidly developed in recent years. Computer color matching is a technique for color restoration, and has been successfully applied in the industries of printing, textile and the like.
The authorization notice number is: CN107766603B, entitled an invention patent of a color testing and matching method for a colored spun yarn computer, the technical proposal of which discloses that firstly, a color matching base database is established, an improved Friele model and a trained three-layer BP neural network are utilized, then, an initial formula of a target sample is calculated and corrected based on the improved Friele model and the trained three-layer BP neural network, and finally, the sample is drawn or further corrected; the method comprises the following specific steps:
(1) establishing a color matching base database, selecting a plurality of monochromatic fibers, spinning and preparing samples according to different mixing ratios, and measuring the color characteristic values and the reflectivity of the monochromatic fibers and yarns;
(2) improving a Friele model and training a three-layer BP neural network, wherein the improved Friele model is characterized in that a parameter sigma in the Friele model is replaced by a constant sigma corresponding to a yarn, the sigma is determined by programming according to a formula (I), a formula (II), a formula (III), a formula (IV) and a formula (V), the termination condition of the program is that the color difference rating of the fitting reflectivity and the actual reflectivity of the yarn is more than or equal to a set value, and the formulas (I) to (V) are specifically as follows:
R(λ)＝R(λ)(II)；
where i is the class number of the fiber, j is the color type of the monochromatic fiber in the yarn, e is a natural constant, R (λ) represents the reflectance of the yarn at the wavelength λ, f [ R (λ) ] is a function of the independent variable R (λ), R (λ) represents the fitted reflectance of the yarn at the wavelength λ, R (λ) represents the actual reflectance of the yarn at the wavelength λ, x represents the proportion of the monochromatic fiber of the d-th color to the total mass of the yarn, d 1,2,.
The training of the three-layer BP neural network refers to training of the three-layer BP neural network by adopting the fiber type, the yarn structure and the color characteristic value of the yarn with known formulas in the color matching base database, so that the weight w of the input layer and the hidden layer and the weight w of the hidden layer and the output layer are optimized;
(3) calculating an initial formula X of a target sample based on an improved Friele model, namely obtaining X which enables f [ R (lambda) ] to be equal to f [ R (lambda) ] through programming, namely the initial formula X, wherein the calculation formula of f [ R (lambda) ] and f [ R (lambda) ] is as follows:
(4) correcting an initial formula X of a target sample based on the trained three-layer BP neural network to obtain a formula C, namely inputting the fiber type, the yarn structure and the color characteristic value of the yarn of the target sample into the trained three-layer BP neural network to obtain a formula Y, and carrying out weighted average on the formula Y and the initial formula X to obtain the formula C;
(5) sampling according to the formula C to obtain a formula sample, measuring colorimetric values L, a and b of the formula sample and colorimetric values L, a and b of a target sample, calculating chromatic aberration, performing mass production if the chromatic aberration meets the requirement, and inputting the formula C into an intelligent database; otherwise, the next step is carried out;
(6) and correcting the formula C, namely firstly obtaining theoretical colorimetric values of a formula sample as L, a and b by an improved Friele model, then calculating L, a and b, wherein L is L-L + L, a is a-a + a, and b is b-b + b, finally inputting L, a and b into a trained three-layer BP neural network to obtain a corrected formula C, sampling according to the formula C to obtain a corrected formula sample, calculating the color difference between the corrected formula sample and a target sample, carrying out mass production if the color difference meets the requirement, and inputting the formula C into an intelligent database, otherwise, repeatedly correcting until the color difference meets the requirement.
Taking the above patent as an example, although color measurement and matching are mentioned through a BP neural network, the technical scheme of the invention is different from that of the invention, the invention improves the graphical method by using the BP neural network based on GA and LM algorithms, and can match colors with stable quality and small metamerism index by inputting processed dyeing data (including dye proportion and color value) into the neural network and continuously training the neural network. Computer color matching based on a neural network is an important technical path for efficient and rapid development of related industries, and can promote the development of the traditional textile printing and dyeing industry in China.
Disclosure of Invention
The invention mainly aims to provide a computer color measuring and matching method based on an improved BP neural network, which improves the traditional color matching mode by establishing a BP neural network model to obtain higher color matching precision and better generalization capability.
In order to achieve the above purposes, the invention provides a computer color measuring and matching method based on an improved BP neural network, which comprises the following steps of:
step S1: obtaining a sample color matching result C corresponding to a dye matching proportion D and a dyeing matching proportion from a certain batch of samples, and normalizing the dye matching proportion D and the sample color matching result C to obtain a training sample and a test sample for color measurement and matching in a separated manner;
step S2: constructing a BP neural network model, and setting related parameters in the BP neural network model;
step S3: training the BP neural network model according to the constructed BP neural network model and the obtained training sample and the test sample;
step S4: and applying the trained BP neural network model, and performing computer color measurement and color matching.
As a further preferable embodiment of the above technical means, step S1 is specifically implemented as the following steps:
step S1.1: obtaining the dye matching proportion D of a certain batch of samples, D ═ Dij1,2, …, N; j ═ 1,2,3}, where dijRepresenting the jth dye of the ith group of samplesProportion, N is the number of samples;
step S1.2: obtaining a color matching result C, C ═ C of the sample corresponding to the dye matching proportion Di1,2, …, N, where c isiAnd representing the color matching result of the ith group of samples by using a Lab color mode, specifically: c. Ci＝(Li,ai,bi)；
Step S1.3: normalizing the dye proportion D and the sample color matching result C, wherein the interval is [ -1,1 ];
step S1.4: separating the training sample from the test sample to obtain a training sample Dtrain,CtrainAnd test specimen Dtest,CtestWherein the training sample size is M and the test sample size is N-M.
As a further preferable embodiment of the above technical means, step S2 is specifically implemented as the following steps:
step S2.1: coding a network model Net according to a BPNN topological structure;
step S2.2: selecting a Sigmoid function and a Purelin function as a hidden layer activation function and an output layer transmission parameter of a network model Net respectively;
step S2.3: optimizing the weight W and the bias b by using a GA genetic algorithm;
step S2.4: the learning rate lr of the network model Net is set to 0.01, the maximum iteration number total _ epoch is set to 1000, the number node of hidden layer nodes is set to 12, and the mean square error MSE is set to 0.001.
As a further preferable embodiment of the above technical means, step S3 is specifically implemented as the following steps:
step S3.1: will train sample Dtrain,CtrainExpanding by a preset multiple (preferably 5 times), and randomly scrambling;
step S3.2: inputting the data of the expanded training sample into a network, and training a network model Net by using an LM algorithm, wherein a forward propagation process is used for calculating a numerical value, a backward propagation process is used for optimizing parameters, and each pair of data is trained once and recorded as an epoch;
step S3.3: after finishing one-time training, the use testTest specimen Dtest,CtestCalculating the mean square error, and stopping training if the MSE is less than or equal to 0.001; otherwise, step S3.2 is repeated until the mean square error meets the condition or the epoch reaches the prescribed value.
As a further preferable embodiment of the above technical means, step S4 is specifically implemented as the following steps:
step S4.1: obtaining the colour value C of the fabric to be matched using a colorimeterRGBConverting into Lab space to obtain color matching result Cuse＝(Luse,ause,buse)；
Step S4.2: match color result CuseInputting the data into a network model Net, and reasoning to obtain a dye proportion Duse＝{Dj|j＝1,2,3}；
Step S4.3: using the dye ratio DuseAnd mixing the dyes, and carrying out subsequent dyeing according to the procedures.
To achieve the above object, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the computer color matching method based on the modified BP neural network when executing the computer program.
To achieve the above object, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the computer color measuring and matching method based on the modified BP neural network.
The invention has the beneficial effects that: a BP neural network structure is optimized by using a Genetic Algorithm (GA) and a Levenberg-Marquardt Algorithm (LM), then processed dyeing data (including a dye proportion and a color value) are input into the neural network, the neural network is trained continuously, and the dye proportion can be obtained by inputting the required color value during application. The method utilizes the advantage of the neural network for processing the nonlinear problem, and after the GA and LM algorithms are used for optimization, the convergence speed of the neural network model can be increased, the color matching precision and the generalization capability are improved, and the color dyeing and matching effect is optimized.
Drawings
FIG. 1 is a flowchart of the BP neural network training after optimization of the computer color measuring and matching method based on the improved BP neural network.
FIG. 2 is a BP neural network topology diagram of a computer color measuring and matching method based on an improved BP neural network.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
In the preferred embodiments of the present invention, those skilled in the art should note that the electronic devices, computers, samples, and the like, to which the present invention relates, may be regarded as prior art.
Preferred embodiments.
The invention discloses a computer color measuring and matching method based on an improved BP neural network, which comprises the following steps of:
step S1: obtaining a sample color matching result C corresponding to a dye matching proportion D and a dyeing matching proportion from a certain batch of samples, and normalizing the dye matching proportion D and the sample color matching result C to obtain a training sample and a test sample for color measurement and matching in a separated manner;
step S2: constructing a BP neural network model, and setting related parameters in the BP neural network model;
step S3: training the BP neural network model according to the constructed BP neural network model and the obtained training sample and the test sample;
step S4: and applying the trained BP neural network model, and performing computer color measurement and color matching.
Specifically, step S1 is implemented as the following steps:
step S1.1: obtaining the dye matching proportion D of a certain batch of samples, D ═ Dij1,2, …, N; j ═ 1,2,3}, where dijRepresenting the proportion of jth dye in ith group of samples, and N is the number of samples;
step S1.2: obtaining a color matching result C, C ═ C of the sample corresponding to the dye matching proportion Di1,2, …, N, where c isiAnd representing the color matching result of the ith group of samples by using a Lab color mode, specifically: c. Ci＝(Li,ai,bi)；
Step S1.3: normalizing the dye proportion D and the sample color matching result C, wherein the interval is [ -1,1 ];
step S1.4: separating the training sample from the test sample to obtain a training sample Dtrain,CtrainAnd test specimen Dtest,CtestWherein the training sample size is M and the test sample size is N-M.
More specifically, step S2 is specifically implemented as the following steps:
step S2.1: coding a network model Net according to a BPNN topological structure;
step S2.2: selecting a Sigmoid function and a Purelin function as a hidden layer activation function and an output layer transmission parameter of a network model Net respectively;
step S2.3: optimizing the weight W and the bias b by using a GA genetic algorithm;
step S2.4: the learning rate lr of the network model Net is set to 0.01, the maximum iteration number total _ epoch is set to 1000, the number node of hidden layer nodes is set to 12, and the mean square error MSE is set to 0.001.
Further, step S3 is specifically implemented as the following steps:
step S3.1: will train sample Dtrain,CtrainExpanding by a preset multiple (preferably 5 times), and randomly scrambling;
step S3.2: inputting the data of the expanded training sample into a network, and training a network model Net by using an LM algorithm, wherein a forward propagation process is used for calculating a numerical value, a backward propagation process is used for optimizing parameters, and each pair of data is trained once and recorded as an epoch;
step S3.3: after completing one training, test sample D was usedtest,CtestCalculating the mean square error, and stopping training if the MSE is less than or equal to 0.001; otherwise, step S3.2 is repeated until the mean square error meets the condition or the epoch reaches the prescribed value.
Further, step S4 is implemented as the following steps:
step S4.1: obtaining the colour value C of the fabric to be matched using a colorimeterRGBConverting into Lab space to obtain color matching result Cuse＝(Luse,ause,buse)；
Step S4.2: match color result CuseInputting the data into a network model Net, and reasoning to obtain a dye proportion Duse＝{Dj|j＝1,2,3}；
Step S4.3: using the dye ratio DuseAnd mixing the dyes, and carrying out subsequent dyeing according to the procedures.
The invention also discloses an electronic device which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the steps of the computer color measuring and matching method based on the improved BP neural network when executing the program.
The invention also discloses a non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the computer color matching method based on the improved BP neural network.
As can be seen from fig. 2, the steps for training and optimizing the BP neural network are as follows:
1. determining a network topological structure of BPNN, and coding network connection weight;
2. decoding the optimized connection weights;
3. initializing a BP neural network model;
4. optimizing a BP neural network model through an LM algorithm;
5. adding the training sample into a training model, judging whether a training target reaches the expectation, if not, continuing training, and if so, testing the trained model through the test sample;
6. and obtaining the color matching scheme after simulation verification.
The invention firstly uses Genetic Algorithm (GA) and Levenberg-Marquardt Algorithm (LM) to optimize BP neural network structure, then uses the processed dyeing data (including dye proportion and color value) to input into the neural network, and continuously trains the neural network, and only needs to input the required color value when in application, thus obtaining the dye proportion. By utilizing the advantages of the neural network for processing the nonlinear problem and using the GA and LM algorithms for optimization, the convergence speed of the neural network model can be increased, the color matching precision (metamerism index) and the generalization capability are improved, and the color dyeing and matching effect is optimized.
It should be noted that the technical features of the electronic device, the computer, the sample, and the like related to the present patent application should be regarded as the prior art, and the specific structure, the operation principle, the control mode and the spatial arrangement mode of the technical features may be selected conventionally in the field, and should not be regarded as the invention point of the present patent, and the present patent is not further specifically described in detail.
It will be apparent to those skilled in the art that modifications and equivalents may be made in the embodiments and/or portions thereof without departing from the spirit and scope of the present invention.
Claims (7)
1. A computer color measuring and matching method based on an improved BP neural network is characterized by comprising the following steps of:
step S1: obtaining a sample color matching result C corresponding to the dye matching proportion D and the dyeing matching proportion from the sample, and normalizing the dye matching proportion D and the sample color matching result C to obtain a training sample and a test sample for color measurement and color matching in a separated manner;
step S2: constructing a BP neural network model, and setting related parameters in the BP neural network model;
step S3: training the BP neural network model according to the constructed BP neural network model and the obtained training sample and the test sample;
step S4: and applying the trained BP neural network model, and performing computer color measurement and color matching.
2. The computer color matching and measuring method based on the improved BP neural network as claimed in claim 1, wherein the step S1 is implemented as the following steps:
step S1.1: obtaining the dye matching proportion D, D ═ D of the sampleij1,2, …, N; j ═ 1,2,3}, where dijRepresenting the proportion of jth dye in ith group of samples, and N is the number of samples;
step S1.2: obtaining a color matching result C, C ═ C of the sample corresponding to the dye matching proportion Di1,2, …, N, where c isiAnd representing the color matching result of the ith group of samples by using a Lab color mode, specifically: c. Ci＝(Li,ai,bi)；
Step S1.3: normalizing the dye proportion D and the sample color matching result C, wherein the interval is [ -1,1 ];
step S1.4: separating the training sample from the test sample to obtain a training sample Dtrain,CtrainAnd test specimen Dtest,CtestWherein the training sample size is M and the test sample size is N-M.
3. The computer color matching method based on the improved BP neural network as claimed in claim 2, wherein the step S2 is implemented as the following steps:
step S2.1: coding a network model Net according to a BPNN topological structure;
step S2.2: selecting a Sigmoid function and a Purelin function as a hidden layer activation function and an output layer transmission parameter of a network model Net respectively;
step S2.3: optimizing the weight W and the bias b by using a GA genetic algorithm;
step S2.4: the learning rate lr of the network model Net is set to 0.01, the maximum iteration number total _ epoch is set to 1000, the number node of hidden layer nodes is set to 12, and the mean square error MSE is set to 0.001.
4. The computer color matching method based on the improved BP neural network as claimed in claim 3, wherein the step S3 is implemented as the following steps:
step S3.1: will train sample Dtrain,CtrainExpanding preset multiples and randomly disordering;
step S3.2: inputting the data of the expanded training sample into a network, and training a network model Net by using an LM algorithm, wherein a forward propagation process is used for calculating a numerical value, a backward propagation process is used for optimizing parameters, and each pair of data is trained once and recorded as an epoch;
step S3.3: after completing one training, test sample D was usedtest,CtestCalculating the mean square error, and stopping training if the MSE is less than or equal to 0.001; otherwise, step S3.2 is repeated until the mean square error meets the condition or the epoch reaches the prescribed value.
5. The computer color matching method based on the improved BP neural network as claimed in claim 4, wherein the step S4 is implemented as the following steps:
step S4.1: obtaining the colour value C of the fabric to be matched using a colorimeterRGBConverting into Lab space to obtain color matching result Cuse＝(Luse,ause,buse)；
Step S4.2: match color result CuseInputting the data into a network model Net, and reasoning to obtain a dye proportion Duse＝{Dj|j＝1,2,3}；
Step S4.3: using the dye ratio DuseAnd mixing the dyes, and carrying out subsequent dyeing according to the procedures.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the computer color matching method based on an improved BP neural network according to any one of claims 1 to 5.
7. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a computer color matching method based on an improved BP neural network according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110271796.4A CN113128104A (en) | 2021-03-12 | 2021-03-12 | Computer color measuring and matching method based on improved BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110271796.4A CN113128104A (en) | 2021-03-12 | 2021-03-12 | Computer color measuring and matching method based on improved BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113128104A true CN113128104A (en) | 2021-07-16 |
Family
ID=76773102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110271796.4A Pending CN113128104A (en) | 2021-03-12 | 2021-03-12 | Computer color measuring and matching method based on improved BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128104A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114417736A (en) * | 2022-03-14 | 2022-04-29 | 深圳市玄羽科技有限公司 | Color formula evaluation method, system, device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04235322A (en) * | 1991-01-10 | 1992-08-24 | Kurabo Ind Ltd | Method and apparatus for color matching |
| JPH0894442A (en) * | 1994-09-20 | 1996-04-12 | Toto Ltd | Computerrized color matching method |
| CN104504716A (en) * | 2014-12-31 | 2015-04-08 | 广州厚邦木业制造有限公司 | Solid wood floor paint automatic color blending method based on BP neural network |
| CN107766603A (en) * | 2017-04-24 | 2018-03-06 | 东华大学 | A kind of colour-spun yarns computer is measured color method |
-
2021
- 2021-03-12 CN CN202110271796.4A patent/CN113128104A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04235322A (en) * | 1991-01-10 | 1992-08-24 | Kurabo Ind Ltd | Method and apparatus for color matching |
| JPH0894442A (en) * | 1994-09-20 | 1996-04-12 | Toto Ltd | Computerrized color matching method |
| CN104504716A (en) * | 2014-12-31 | 2015-04-08 | 广州厚邦木业制造有限公司 | Solid wood floor paint automatic color blending method based on BP neural network |
| CN107766603A (en) * | 2017-04-24 | 2018-03-06 | 东华大学 | A kind of colour-spun yarns computer is measured color method |
Non-Patent Citations (2)
| Title |
|---|
| JIAQIANG WEI，ET AL: "Evaluation of a Novel Computer Color Matching System Based on the Improved Back-Propagation Neural Network Model", 《JOURNAL OF PROSTHODONTICS OFFICIAL JOURNAL OF THE AMERICAN COLLEGE OF PROSTHODONTICS》, vol. 27, no. 8, pages 775 - 783 * |
| 赵琦琳，等: "《人工神经网络在环境科学与工程中的设计应用》", 中国环境出版集团·北京, pages: 231 - 232 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114417736A (en) * | 2022-03-14 | 2022-04-29 | 深圳市玄羽科技有限公司 | Color formula evaluation method, system, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002686B (en) | Multi-grade chemical process soft measurement modeling method capable of automatically generating samples | |
| CN107766603A (en) | A kind of colour-spun yarns computer is measured color method | |
| CN109582994B (en) | Intelligent color selection and matching method for colored spun yarn | |
| CN106355192A (en) | Support vector machine method based on chaos and grey wolf optimization | |
| CN108431561B (en) | Method and data processing device for computer-aided determination of hair color properties | |
| CN111553114B (en) | Intelligent color matching method for textile printing and dyeing based on data driving | |
| CN100595701C (en) | Robust multivariable predicting control method based on uncertain color model | |
| CN109934295A (en) | A kind of image classification and method for reconstructing based on the hidden feature learning model that transfinites | |
| CN113128104A (en) | Computer color measuring and matching method based on improved BP neural network | |
| Chaouch et al. | Application of genetic algorithm to color recipe formulation using reactive and direct dyestuffs mixtures | |
| WO2017103056A1 (en) | Method and data processing device for the computer-assisted determination of a hair dyeing agent for dyeing hair in a desired hair color and device for producing an individually determined hair dyeing agent | |
| CN112819322A (en) | Power transmission line path scheme evaluation method based on improved fuzzy analytic hierarchy process | |
| US20020184167A1 (en) | System and method for converting a color formula using an artificial intelligence based conversion model | |
| CN110289987B (en) | Multi-agent system network anti-attack capability assessment method based on characterization learning | |
| CN105787275B (en) | A kind of computer for colouring method of leather coloring | |
| CN113128689A (en) | Entity relationship path reasoning method and system for regulating knowledge graph | |
| CN109946245B (en) | Computer color matching method of dye | |
| CN113192034B (en) | Mixed dye solution concentration detection method based on counter-propagation neural network | |
| JP3212101B2 (en) | Color matching method and apparatus | |
| CN114092784A (en) | Mixed dye liquor concentration spectrum detection method based on long-term and short-term memory neural network | |
| JP2018191073A (en) | Calculation method for blending quantities of coloring materials | |
| CN109726850B (en) | Method for establishing resultant yarn quality prediction model | |
| CN109885910A (en) | A kind of cowboy's embroidery pattern rinsing colour fading technological parameter modeling method | |
| CN117973433A (en) | Intelligent color matching artificial neural network for textile printing and dyeing | |
| CN111310907A (en) | Microwave assembly fault diagnosis method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |