CN114285955B - Color gamut mapping method based on dynamic deviation map neural network - Google Patents
Color gamut mapping method based on dynamic deviation map neural network Download PDFInfo
- Publication number
- CN114285955B CN114285955B CN202111620261.XA CN202111620261A CN114285955B CN 114285955 B CN114285955 B CN 114285955B CN 202111620261 A CN202111620261 A CN 202111620261A CN 114285955 B CN114285955 B CN 114285955B
- Authority
- CN
- China
- Prior art keywords
- color
- mapping
- printing
- dyeing
- xyz
- 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.)
- Active
Links
Images
Landscapes
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Color Image Communication Systems (AREA)
Abstract
The color gamut mapping method based on the dynamic deviation map neural network comprises the following steps: 1) Collecting a color sample of a printing and dyeing printer; 2) Building and training a neural network from XYZ to CMKY color space deviation mapping chart; 3) Performing coarse-grained local mapping reinforcement based on a mask; 4) Adjusting the optimization for a machine-specific map neural mapping network; 5) Mask-based machine-specific local mapping enforcement; 6) Mapping from CMYK to XYZ color space; 7) Color gamut mapping based on local range matching. According to the color gamut mapping method based on the dynamic deviation graph neural network established in the steps, the dynamic deviation is introduced into the neural network, and the accurate mapping of colors from the color space of the printing and dyeing printer to the standard color space is realized while the color mapping from the color space of the printing and dyeing printer to the standard color space is learned from a large number of collected printing and dyeing samples.
Description
Technical Field
The invention belongs to the field of color mapping, and provides a color gamut mapping method based on a dynamic deviation diagram neural network aiming at the problems of uneven current color space and inaccurate color mapping between a printing and dyeing printer and a standard color space CIE XYZ.
Background
With the rapid development of deep learning technology, a series of breakthrough progresses of a deep model in the fields of computers and intersections are achieved. In the deep learning field, the graph neural network makes some progress in spatial mapping: mapping of clothing key points between tiled clothing and human body dressed clothing is achieved by using a graph neural network, such as in document 1 (Xin Gao, zhenjiang Liu, zunlei Feng, chengji Shen, kairi Ou, haihong Tang, mingli Song, shape Controllable Virtual Try-on for Underwear Models, ACM Multimedia 2021); in document 2 (Wang N, zhang Y, li Z, et al, pixel2Mesh: generation 3D Mesh Models from Single RGB images [ C ]// European Conference on Computer Vision. Springer, cham, 2018), the mapping from an image to the vertex of a 3D Mesh is solved by a graph neural network, and the reconstruction from a Single image to a three-dimensional Mesh is realized. Current graph neural networks have proven effective in many areas to implement mapping of different spaces, and then color gamut mapping based on graph neural networks works less, mainly because of variations in the printed color rendering from one printer to another, and from different time periods of the same printer.
In terms of color gamut mapping, the existing color gamut mapping methods mainly include two main categories: image dependent dynamic color gamut mapping methods, fixed color gamut mapping methods. The dynamic color gamut mapping method related to the image mainly considers the characteristics of color values in the image, realizes the minimum error aiming at the color conversion of the image, needs to combine the color characteristics of the image, dynamically adjusts the mapping relation of color points among color spaces, can obtain better color presenting effect, but has slower processing time, and is not suitable for large-scale popularization. Fixed color gamut mapping methods mainly include three categories: physical conversion model, numerical quantization conversion model and 3D LUT method. The physical conversion model generally assumes the conditions of mutual independence of color channels, constant chromaticity, uniform color space and the like, but when human eyes observe real colors, the color difference is not uniform; the numerical value quantization conversion model learns the conversion relation between the relevant color space of the equipment and the irrelevant color space of the equipment through a numerical value model, and the numerical value model mainly comprises a polynomial regression method, a neural network method, a continuous linear interpolation method, a radial basis function method and the like, for example, a color consistency mapping method for textile inkjet printing based on image color blocks is disclosed in document 3 (Song Ming Li, sheng nan, feng Zun, and the like), and CN110418030A [ P ]. 2019) adopts an RBF neural network to realize the mapping from a printing and dyeing machine CMYK to a display RGB color space, however, the limited learning capability of RBF limits the accuracy of color mapping, and the work does not consider the deviation of colors of different machines and different time. The 3D LUT method establishes a conversion relationship between the device-independent color space and the device-dependent color space in a table, and the accuracy of the 3D LUT method mainly depends on the number of colors measured and the interpolation method selected at the time of color conversion. In addition, some european companies implement color mapping among multiple points in a color space, and obtain better accuracy, but due to commercial privacy, the adopted technology is not disclosed, and the technical route is not detailed.
Disclosure of Invention
The invention aims to solve the problem of printing and dyeing color deviation of different printers and the same printer at different time and realize accurate mapping of colors from the printing and dyeing printer color space to the standard color space.
The textile printing and dyeing printer always has the challenges of unstable color printing and dyeing and larger difference of an original color space, and the main problems are that the color space is not uniformly distributed and the color of the printer shows deviation. The invention provides a color gamut mapping method based on a dynamic deviation graph neural network, which realizes the accurate mapping of colors from a printing and dyeing printer color space to a standard color space while learning the color mapping from the printing and dyeing printer color space to the standard color space from a large number of collected printing and dyeing samples by introducing dynamic deviation into the neural network.
The color gamut mapping method based on the dynamic deviation map neural network comprises the following steps:
1) Collecting a color sample of a printing and dyeing printer;
collecting color samples of printing and dyeing printers mainly comprises collecting color samples of different printers and collecting different colors of the same printer, wherein the printing and dyeing printers collect the samples of P printers, and each printing and dyeing printer collects Q times; for the four color channels of C, M, Y and K of each printing and dyeing printer, each channel collects T color points once, and the color points are respectively processed by
The ink amount is taken as a central point, the (-d%, d%) is taken as a disturbance sampling interval, and the T is obtained by combining four channels 4 A color sample point; for P printers, Q times are collected by each print to obtain P × Q × T 4 A color sample point; for the printed and dyed sample, measuring color points corresponding to all sample points CIE XYZ color space through a color measuring instrument i1Pro 2;
2) Building and training a neural network from XYZ to CMYK color space deviation maps;
and (4) aiming at Q times of color point sampling of each dyeing machine, arranging according to the sequence of C, M, Y and K and the size of the ink amount in each channel to obtain T 4 *4, the color value matrix D of the CIE XYZ color space corresponding to the color value matrix D is S, and T is constructed according to the adjacent relation in the four color spaces of C, M, Y and K 4 An adjacency matrix A of feature points; using graph convolution networks H l+1 ＝σ(AH l W l ) Performing three-layer convolution operation on an input color value matrix S to obtain a predicted input O = H 3 In which H 0 = S, σ is the ReLU activation function; mapping the loss function L with the following bias 1 Obtaining a biased mapping relation for all samples:
wherein e is a threshold value for color deviation, O i And D i Is the sample color value of the ith row; obtaining a preliminary color mapping network by performing R iterations on all samples;
3) Performing coarse-grained local mapping reinforcement based on a mask;
for constructed T 4 Graph neural network of nodes, using graph convolution, by progressively randomly masking out 10%,20%,30%,40%,50%,60%,70%,80%,90%,95% of sample points in R iterationsNetwork H l+1 ＝σ(A'H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a predicted input O' = H 3 Where A' is the masked adjacency matrix H 0 Where m is a random mask with increasing iteration number, the gradual increase proportion of the random mask is evenly and gradually distributed in R iteration numbers, and for obtaining a mask input O', a loss function L is strengthened by using masked coarse-grained local mapping 2 Training is carried out:
wherein | m | is a color sample point reserved after the mask;
4) Adjusting optimization for a machine-specific map neural mapping network;
for the preliminary color mapping network obtained in step 3), for a specific machine, the input color values are incremented by [ -u, u ] by random using the Q samples collected]To increase the noise immunity of the network, using a specific accurate mapping loss function L as follows 3 ：
In the first R 'iteration optimization, the color sample added with noise disturbance is used for training the network, and then in the subsequent R' iteration optimization, the color sample without noise disturbance is used for training the network, so that an XYZ- > CMYK accurate color mapping network for a specific machine is obtained;
5) Mask-based specific machine local mapping enforcement;
for the refined color mapping network obtained in the step 4), 90% and 95% of sample points are respectively randomly masked in the first R '/2 iteration and the second R'/2 iteration, and a graph convolution network H is utilized l+1 ＝σ(A'H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a predicted input O' = H 3 Wherein A' is maskedAdjacency matrix, H 0 = mS, m being a random mask with increasing number of iterations, the penalty function L being enhanced with mask-specific machine local fine mapping for obtaining a mask input O 4 Training is carried out:
wherein | m | is a color sample point reserved after the mask;
6) Mapping from CMYK to XYZ color space;
mapping from XYZ to CMYK color space is realized by steps 2), 3), 4), 5), and mapping from CMYK to XYZ color space is realized by constructing a color space deviation map neural network of the mapping from CMYK to XYZ by using CMYK as color input sample points and XYZ as output color sample points, and through four steps of step 2) similar deviation coarse-grained mapping, step 3) mask-based coarse-grained local mapping enhancement, step 4) adjustment and optimization of the map neural mapping network for a specific machine, and step 5) mask-based specific machine local mapping enhancement;
7) Color gamut mapping based on local range matching;
in practical applications, the mapping of color values requires coarse-grained matching of the input color gamut, and for the input CMYK color values, the input CMYK color values need to be matched to T 4 In the node of the individual graph
The graph nodes within the ink volume need to be matched to T for the input XYZ color values 4 In a node of a graph
The color bidirectional mapping of CMYK to XYZ is realized by setting the mask to 0 for a color value point that does not need to be mapped with a map node of an internal color difference value in the above manner.
Preferably, the threshold value e for the color deviation of step 2) is set to 3.
Preferably, the number of printers P in step 1) is 100, the number of print acquisition times Q is 100, and the number of color dots T is 10.
The method is a color gamut mapping method based on a dynamic deviation diagram neural network, and is used for mapping and converting color values between a CMYK color space and a standard CIE XYZ color space of a textile printing and dyeing printer.
According to the color gamut mapping method based on the dynamic deviation graph neural network established in the steps, the dynamic deviation is introduced into the neural network, and the accurate mapping of colors from the color space of the printing and dyeing printer to the standard color space is realized while the color mapping from the color space of the printing and dyeing printer to the standard color space is learned from a large number of collected printing and dyeing samples.
The invention has the beneficial effects that: based on the strong learning ability of the graph neural network, on the basis of collecting a large number of samples, the dynamic accurate mapping of colors is realized by modeling the color deviation of different printing and dyeing printers and the same printer at different times to a graph neural network color mapping model.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
The invention relates to a color gamut mapping method based on a dynamic deviation map neural network, which comprises the following steps:
1) Collecting a color sample of a printing and dyeing printer;
the collecting of the color samples of the printing and dyeing printers mainly comprises collecting the color samples of different printers and collecting the color samples of the same printer, wherein the collecting of the color samples of 100 printers is carried out for 100 times by each printing and dyeing printer; for four color channels of C, M, Y and K of each printing and dyeing printer, taking {5%,15%,25%,35%,45%,55%,65%,75%,85%,95% } ink quantity as a central point and (-5%, 5%) as a disturbance sampling interval for each channel, collecting 10 color points for each channel at a time, and combining the four channels to obtain 10000 color sample points; for 100 printers, 100 times per print acquisition, yielding 100 × 10000 color sample dots in total; for the printed and dyed sample, measuring color points corresponding to all sample points CIE XYZ color space through a color measuring instrument i1Pro 2;
2) Building and training a neural network from XYZ to CMYK color space deviation mapping;
sampling 100 color points of each dyeing machine, arranging the color values according to the sequence of C, M, Y and K and the size of ink in each channel to obtain 10000 × 4 color value matrixes D, setting the color value matrixes of CIE XYZ color spaces corresponding to the color value matrixes D as S, and constructing an adjacency matrix A of 10000 feature points according to the adjacency relation among the four color spaces of C, M, Y and K; using graph convolution networks H l+1 ＝σ(AH l W l ) Performing a triple-layer convolution operation on the input color value matrix S to obtain a predicted input O = H 3 In which H is 0 = S, σ is the ReLU activation function; mapping the loss function L with the following bias 1 Obtaining biased mapping relationships for all samples:
where e is a threshold value for color deviation (set to 3 in the present invention), O i And D i Is the sample color value of the ith row; obtaining a preliminary color mapping network through 50 iterations for all samples;
3) Performing coarse-grained local mapping reinforcement based on a mask;
for the constructed 10000-node graph neural network, 10%,20%,30%,40%,50%,60%,70%,80%,90%,95% of sample points are gradually randomly masked out in 50 iterations, and a graph convolution network H is utilized l+1 ＝σ(A'H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a predicted input O' = H 3 Where A' is the masked adjacency matrix H 0 Where m is a random mask with increasing iteration number, the gradual increase proportion of the random mask is evenly and gradually distributed in 50 iteration numbers, and for obtaining a mask input O', a loss function is strengthened by using masked coarse-grained local mappingNumber L 2 Training is carried out:
wherein | m | is a color sample point reserved after the mask;
4) Adjusting the optimization for a machine-specific map neural mapping network;
for the preliminary color mapping network obtained in step 3), for a specific machine, the input color values are incremented by [ -0.1, by random, using 100 samples taken]To increase the noise immunity of the network, using a specific accurate mapping loss function L as follows 3 ：
In the previous 10 times of iterative optimization, training the network by using the color sample with increased noise disturbance, and then in the subsequent 10 times of iterative optimization, training the network by using the color sample without noise disturbance to obtain an XYZ- > CMYK accurate color mapping network for a specific machine;
5) Mask-based specific machine local mapping enforcement;
for the refined color mapping network obtained in the step 4), 90% and 95% of sample points are respectively randomly masked in the first 5 iterations and the last 5 iterations, and a graph convolution network H is utilized l+1 ＝σ(A'H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a predicted input O' = H 3 Where A' is the masked adjacency matrix H 0 = MS, M is a random mask with increasing number of iterations, for obtaining a mask input O', a penalty function L is enforced using mask-specific machine local fine mapping 4 Training is carried out:
wherein | M | is a color sample point reserved after the mask;
6) Mapping from CMYK to XYZ color space;
mapping from XYZ to CMYK color space is realized through steps 2), 3), 4), 5), and mapping from CMYK to XYZ color space is realized through four steps of constructing a color space deviation mapping neural network of CMYK to XYZ mapping by using CMYK as color input sample points and XYZ as output color sample points, and realizing mapping from CMYK to XYZ color space through step 2) similar deviation coarse-grained mapping, step 3) coarse-grained local mapping enhancement based on masks, step 4) adjustment and optimization of the mapping neural mapping network for a specific machine, and step 5) specific machine local mapping enhancement based on masks;
7) Color gamut mapping based on local range matching;
in practical application, coarse-grained matching needs to be performed on an input color domain to realize mapping of color values, graph nodes within 5% of ink amount in 10000 graph nodes need to be matched to input CMYK color values, graph nodes within 20% of color difference values in 10000 graph nodes need to be matched to input XYZ color values, mask codes are set to be 0 for color value points which do not need mapping, and CMYK-XYZ color bidirectional mapping is realized through the above mode.
The method is a color gamut mapping method based on a dynamic deviation diagram neural network, and is used for mapping and converting color values between a CMYK color space and a standard CIE XYZ color space of a textile printing and dyeing printer.
The invention has the beneficial effects that: based on the strong learning ability of the graph neural network, on the basis of collecting a large number of samples, the dynamic accurate mapping of colors is realized by modeling color deviation of different printing and dyeing printers and the same printer at different times to a graph neural network color mapping model.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (3)
1. The color gamut mapping method based on the dynamic deviation map neural network comprises the following steps:
1) Collecting a color sample of a printing and dyeing printer;
collecting color samples of the printing and dyeing printers comprises collecting color samples of different printing and dyeing printers and collecting different colors of the same printing and dyeing printer, collecting the samples of P printing and dyeing printers, and collecting Q times of each printing and dyeing printer; for the four color channels of C, M, Y and K of each printing and dyeing printer, each channel collects T color points once, and the color points are respectively processed by
The ink amount is taken as a central point, (-d%, d%) is taken as a disturbance sampling interval, and T is obtained by combining four channels 4 A color sample point; for P printing printers, Q times are collected by each printing printer to obtain P × Q × T 4 A color sample point; for the printed and dyed sample, measuring color points corresponding to all sample points CIE XYZ color space through a color measuring instrument i1Pro 2;
2) Building and training a neural network from XYZ to CMYK color space deviation mapping;
and (3) sampling Q times of color points of each printing and dyeing printer, and arranging the color points according to the sequence of C, M, Y and K and the size of the ink in each channel to obtain T 4 *4, the color value matrix D of the CIE XYZ color space corresponding to the color value matrix D is S, and T is constructed according to the adjacent relation in the four color spaces of C, M, Y and K 4 An adjacency matrix A of feature points; using graph convolution networks H l+1 ＝σ(AH l W l ) Performing three-layer convolution operation on an input color value matrix S to obtain a predicted input O = H 3 In which H is 0 = S, σ is the ReLU activation function; mapping the loss function L with the following bias 1 Obtaining a deviation mapping relation for all samples:
where e is the threshold value for the color deviation, O i And D i Is the sample color value of the ith row; obtaining a preliminary color mapping network by performing R iterations on all samples;
3) Strengthening coarse-grained local mapping based on a mask;
for constructed T 4 The graph neural network of nodes utilizes graph convolution network H by progressively randomly masking out 10%,20%,30%,40%,50%,60%,70%,80%,90%,95% of the sample points in R iterations l+1 ＝σ(A′H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a predicted input O' = H 3 Where A' is the masked adjacency matrix, H 0 Where m is a random mask with increasing iteration number, the gradual increase proportion of the random mask is evenly and gradually distributed in R iteration numbers, and for obtaining a mask input O', a loss function L is strengthened by using masked coarse-grained local mapping 2 Training is carried out:
wherein | m | is a color sample point reserved after the mask;
4) Adjusting the optimization for a machine-specific map neural mapping network;
for the preliminary color mapping network obtained in step 2), for a particular machine, the input color values are incremented by [ -u, u ] by random using the Q samples collected]To increase the noise immunity of the network, using a specific accurate mapping loss function L as follows 3 ：
In the previous R 'iteration optimization, the color sample added with noise disturbance is used for training the network, and then in the subsequent R' iteration optimization, the color sample without noise disturbance is used for training the network, so that an XYZ- > CMYK accurate color mapping network for a specific machine is obtained;
5) Mask-based specific machine local mapping enforcement;
with respect to XYZ->The CMYK accurate color mapping network utilizes a graph convolution network H by masking out 90% and 95% of sample points randomly in the first R '/2 and the last R'/2 iterations, respectively l+1 ＝σ(A′H l W l ) Performing three-layer convolution operation on the M-masked input color value matrix S to obtain a prediction input O = H 3 Where A' is the masked adjacency matrix, H 0 = mS, m being a random mask with increasing number of iterations, for obtaining a mask input O', a penalty function L is enforced using mask-specific machine local fine mapping 4 Training is carried out:
wherein | m | is a color sample point reserved after the mask;
6) Mapping from CMYK to XYZ color space;
constructing a color space deviation mapping graph neural network for mapping CMYK to XYZ by using CMYK as a color input sample point and XYZ as an output color sample point, so as to realize the mapping from CMYK to XYZ color space;
7) Color gamut mapping based on local range matching;
in practical applications, coarse-grained matching of input color fields is required to realize mapping of color values, and matching of input CMYK color values to T is required 4 In a node of a graph
The graph nodes within the ink volume need to be matched to T for the input XYZ color values 4 An imageIn the node
The color bidirectional mapping of CMYK to XYZ is realized by setting the mask to 0 for a color value point that does not need to be mapped with a map node of an internal color difference value in the above manner.
2. The dynamic deviant graph neural network-based color gamut mapping method of claim 1, wherein: the threshold e for the color deviation of step 2) is set to 3.
3. The dynamic deviant map neural network-based color gamut mapping method of claim 1, wherein: the number P of the printing and dyeing printers in the step 1) is 100, the collection times Q of each printing and dyeing printer is 100, and the number T of the color points is 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111620261.XA CN114285955B (en) | 2021-12-28 | 2021-12-28 | Color gamut mapping method based on dynamic deviation map neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111620261.XA CN114285955B (en) | 2021-12-28 | 2021-12-28 | Color gamut mapping method based on dynamic deviation map neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114285955A CN114285955A (en) | 2022-04-05 |
| CN114285955B true CN114285955B (en) | 2022-12-09 |
Family
ID=80876699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111620261.XA Active CN114285955B (en) | 2021-12-28 | 2021-12-28 | Color gamut mapping method based on dynamic deviation map neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114285955B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106937018A (en) * | 2017-01-12 | 2017-07-07 | 浙江大学 | It is used for the color mapping method of textile inkjet printing and dyeing based on RBF neural |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6480299B1 (en) * | 1997-11-25 | 2002-11-12 | University Technology Corporation | Color printer characterization using optimization theory and neural networks |
| CN102110428B (en) * | 2009-12-23 | 2015-05-27 | 新奥特（北京）视频技术有限公司 | Method and device for converting color space from CMYK to RGB |
| CA3043621C (en) * | 2018-05-18 | 2020-03-24 | The Governing Council Of The University Of Toronto | Method and system for color representation generation |
| CN109147048B (en) * | 2018-07-23 | 2021-02-26 | 复旦大学 | Three-dimensional mesh reconstruction method by utilizing single-sheet colorful image |
| US20210227095A1 (en) * | 2018-09-05 | 2021-07-22 | Hewlett-Packard Development Company, L.P. | Modeling a printed halftone image |
| CN112085668B (en) * | 2020-08-14 | 2023-10-10 | 深圳大学 | Image tone mapping method based on region self-adaptive self-supervision learning |
-
2021
- 2021-12-28 CN CN202111620261.XA patent/CN114285955B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106937018A (en) * | 2017-01-12 | 2017-07-07 | 浙江大学 | It is used for the color mapping method of textile inkjet printing and dyeing based on RBF neural |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114285955A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105528589B (en) | Single image crowd's counting algorithm based on multiple row convolutional neural networks | |
| CN103873736B (en) | Color closed-loop correction method and system based on multi-dimensional table | |
| CN103839079B (en) | A kind of similar image colorization processing method based on classification learning | |
| CN109671124B (en) | Mineral flotation froth image color correction method and froth color detection system | |
| CN107079077A (en) | It is configured like system | |
| CN109685743A (en) | Image mixed noise removing method based on noise learning neural network model | |
| CN106937018A (en) | It is used for the color mapping method of textile inkjet printing and dyeing based on RBF neural | |
| CN110418030A (en) | The colour consistency mapping method of textile inkjet printing and dyeing is used for based on image color lump | |
| CN102945556B (en) | Seven look algorithm of color separations of Neugebauer equation are divided based on cell element | |
| CN103002193B (en) | Digital image adjusting system and digital image adjusting method | |
| Humayun et al. | MaGNET: Uniform sampling from deep generative network manifolds without retraining | |
| CN110475043A (en) | A kind of conversion method of CMYK to Lab color space | |
| CN102975502B (en) | Printer calibration steps and device for color management | |
| JP2021017034A (en) | Information processing device, method and program | |
| CN114285955B (en) | Color gamut mapping method based on dynamic deviation map neural network | |
| CN107330188B (en) | Split modeling method and system for multicolor halftone equipment facing copied object | |
| CN102529388B (en) | Total ink amount measuring method and device for ink jet printing equipment | |
| CN102075667A (en) | Method for reversely converting color space based on table lookup method | |
| CN110310266A (en) | A kind of acetes chinensis method based on T-S fuzzy neural network | |
| CN112270397B (en) | Color space conversion method based on deep neural network | |
| CN102238297A (en) | Method and system for generating international color consortium profile file | |
| CN103862858B (en) | A kind of multi-color printing print system spectrum color separation method | |
| CN101442602B (en) | Color space transition method based on fuzzy theory | |
| JP2018082312A (en) | Image control device, patch chart, image forming method, and program | |
| CN103646393B (en) | Oil painting base colors of pigment Forecast of Spectra method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |