CN116738717B - Product color matching design method and system based on color image migration - Google Patents
Product color matching design method and system based on color image migration Download PDFInfo
- Publication number
- CN116738717B CN116738717B CN202310696128.5A CN202310696128A CN116738717B CN 116738717 B CN116738717 B CN 116738717B CN 202310696128 A CN202310696128 A CN 202310696128A CN 116738717 B CN116738717 B CN 116738717B
- Authority
- CN
- China
- Prior art keywords
- color matching
- color
- product
- gene
- evaluation
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 65
- 230000005012 migration Effects 0.000 title claims abstract description 65
- 238000013461 design Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 139
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 112
- 230000004424 eye movement Effects 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 239000003086 colorant Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 abstract description 11
- 230000019771 cognition Effects 0.000 abstract description 7
- 239000000284 extract Substances 0.000 abstract 1
- 238000005034 decoration Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000010422 painting Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/20—Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a product color matching design method and a system based on color image migration, wherein the method extracts color characteristics from excellent color matching case samples, and selects corresponding excellent color matching case representatives and color matching combination representatives thereof from each evaluation dimension according to subjective objective evaluation; carrying out relevance expression on the product color matching gene programming influence factors and the evaluation dimension to form a product color matching gene programming scheme library; migrating the color matching combination representation to a product color matching gene planning scheme according to the product color image demand, and selecting an optimal color migration scheme through the satisfaction evaluation of a testee; according to the invention, the association between the excellent color matching case and the product color matching in the artistic works is established through the color image, the subjective and objective dimensions are fused, the color image cognition evaluation of the testee on the excellent color matching case is comprehensively and accurately quantified, the emotion demand of the user on the color is mapped, the uncertainty and the ambiguity of the emotion of the user are solved, an effective reference is provided for the product color matching design, and the quality of the product color matching design is improved.
Description
Technical Field
The invention relates to a product color matching design method and system, in particular to a product color matching design method and system based on color image migration.
Background
With the continuous development of modern designs, strong market competition leads the emotion demands of users to be focused widely, as an important component in product design, emotion interaction between users and product color matching is affected by a plurality of factors, and designers usually refer to excellent color cases as inspiration to develop the product color matching design, but often rely on personal experience to not meet all user demands. In the prior art, the method of clustering and the like is used for extracting the product intention evaluation vocabulary, only objective evaluation data can be obtained, and emotion feedback of color intention to a user is ignored, even if emotion factors are considered in color matching design, emotion can only be related to a single color, and the color matching efficiency is improved, but reference to appreciation artistic works is lacking, so that the color matching scheme is single, the attractiveness is poor, and emotion requirements of the user are difficult to truly reflect.
Disclosure of Invention
The invention aims to: the invention aims to provide a method and a system for applying color image migration in an excellent color matching case to product color matching design, and the quality of the product color matching design is improved.
The technical scheme is as follows: the invention relates to a product color matching design method based on color image migration, which comprises the following steps:
(1) Establishing an excellent color matching case sample library, and extracting color features from the excellent color matching case sample;
(2) Obtaining subjective evaluation scores of a testee on excellent color matching case samples in a plurality of evaluation dimensions, and sequencing the excellent color matching case samples from high to low in each evaluation dimension according to the subjective evaluation score mean;
(3) Selecting a superior color matching case sample with highest subjective evaluation score mean value order as a superior color matching case representation of each evaluation dimension, arranging and combining color features extracted from the superior color matching case representation to obtain color matching combinations, acquiring subjective evaluation and objective eye movement data of a tested person on all the color matching combinations in each evaluation dimension, calculating image contribution degree of the color matching combinations according to the subjective evaluation and objective eye movement data, and selecting the color matching combination with highest image contribution degree as the color matching combination representation;
(4) Selecting a product color matching gene programming influence factor according to the product modeling, performing color matching gene programming of color image migration according to the product color matching gene programming influence factor, and establishing a product color matching gene programming whole sample library;
(5) Encoding the influence factors of each product color matching gene planning sample, and calculating the association coefficient of the product color matching gene planning influence factors and the evaluation dimension according to a quantitative I-type theory to obtain the mapping relation between the product color matching gene planning samples and the evaluation dimension; purifying the product color matching gene planning whole sample library according to the mapping relation to obtain a product color matching gene planning scheme library;
(6) Migrating the color matching combination representation to a product color matching gene planning scheme according to the main color, the auxiliary color and the spot color, obtaining a color migration scheme library of the color matching combination representation in each evaluation dimension, calculating satisfaction scores according to subjective evaluation of testers, respectively calculating gray correlation between the satisfaction scores and the area occupation ratio of the characteristic colors represented by each excellent color matching case and the image contribution degree represented by the color matching combination, and selecting and combining according to the gray correlation scores to generate an optimal color migration scheme of the product.
Further, the product color matching gene programming influence factors comprise color matching duty ratio, color area linking mode and color area combination mode.
Further, the step (3) includes the following:
obtaining measured values K of subjective questionnaire of i color matching combinations in excellent color matching case samples of testees in each evaluation dimension i Calculating the subjective matching degree Z of each color matching combination i ＝K i *W i The method comprises the steps of carrying out a first treatment on the surface of the Wherein W is i For K i Normalized value of inverse complex correlation coefficient;
obtaining the measured value E of objective eye movement experiment of i color matching combinations in the excellent color matching case sample of the tested person in each evaluation dimension i ；
Calculating the image contribution degree Q of each color combination in the excellent color matching case sample of each evaluation dimension i ，Q i ＝Z i *E i ；
Color combination representative of the excellent color matching case samples corresponding to each evaluation dimension is selected according to the high-to-low ranking.
Further, the step (6) calculates satisfaction scores according to subjective evaluation of the testee, and calculates the satisfaction scores and the area ratio of each product color matching gene planning scheme and the image contribution degree Q represented by the color matching combination respectively i Gray correlation degree between the color components is selected and combined according to the gray correlation degree score to generate the optimal color migration scheme of the product, and the optimal color migration scheme comprises the following contents:
obtaining satisfaction scores of testees on each color migration scheme;
calculating the satisfaction degree score of each color migration scheme and the area ratio of the characteristic color represented by each excellent color matching case and the image contribution degree Q represented by the color matching combination i Gray correlation between;
and selecting a main color, an auxiliary color and an interspersed color from the color matching combination representation according to the maximum gray correlation degree to obtain an optimal color migration scheme of the product corresponding to each evaluation dimension.
Further, before the gray correlation between the satisfaction degree score of each color migration scheme and the area ratio represented by each color matching combination and the image contribution degree represented by the color matching combination is calculated, the method further comprises the step of respectively carrying out the area ratio of the characteristic color represented by each excellent color matching case and the image contribution degree Q represented by the color matching combination i And (5) performing min-max standardization treatment.
Further, the step (5) includes the following:
and obtaining a partial regression coefficient of the product color matching gene programming influence factor and the evaluation dimension through multiple linear regression calculation, and selecting the product color matching gene programming influence factor with the maximum partial regression coefficient in each evaluation dimension to form a product color matching gene programming scheme library.
Further, the evaluation dimension is a color image vocabulary.
The invention relates to a product color matching design system based on color image migration, which comprises:
the excellent color matching case selection module is used for extracting color features from the excellent color matching case samples; obtaining subjective evaluation scores of a testee on excellent color matching case samples in a plurality of evaluation dimensions, and sequencing the excellent color matching case samples from high to low in each evaluation dimension according to the subjective evaluation score mean;
the color matching combination representation selection module is used for selecting an excellent color matching case sample with highest subjective evaluation score average value sequence for each evaluation dimension as an excellent color matching case representation of each evaluation dimension, arranging and combining color features extracted from the excellent color matching case representation to obtain color matching combinations, acquiring subjective evaluation and objective eye movement data of a tested person on all the color matching combinations in each evaluation dimension, calculating the image contribution degree of the color matching combinations according to the subjective evaluation and objective eye movement data, and selecting the color matching combination with highest image contribution degree score as the color matching combination representation;
the product gene planning whole sample library building module is used for selecting product color matching gene planning influence factors according to product modeling, carrying out color matching gene planning of color image migration according to the product color matching gene planning influence factors, and building a product color matching gene planning whole sample library;
the product gene planning scheme library building module is used for coding the influence factors of each product color matching gene planning sample, calculating the association coefficient of the product color matching gene planning influence factors and the evaluation dimension according to a quantitative I-type theory, and obtaining the mapping relation between the product color matching gene planning samples and the evaluation dimension; purifying the product color matching gene planning whole sample library according to the mapping relation to obtain a product color matching gene planning scheme library;
the optimal color migration scheme selection module is used for migrating color matching combination representations to a product color matching gene planning scheme according to the main color, auxiliary color and spot color modes, obtaining a color migration scheme library of the color matching combination representations in each evaluation dimension, calculating satisfaction scores according to subjective evaluation of testees, respectively calculating gray correlation between the satisfaction scores and the area ratio of characteristic colors represented by each excellent color matching case and the image contribution degree represented by the color matching combination, and selecting and combining according to the gray correlation scores to generate an optimal color migration scheme of the product.
The electronic equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the product color matching design method based on color image migration when being loaded into the processor.
The computer readable storage medium of the present invention stores a computer program which, when executed by a processor, implements the color matching design method for a product based on color image migration.
The beneficial effects are that: compared with the prior art, the invention has the advantages that: according to the invention, subjective and objective dimensions are combined, subjective evaluation and eye movement data indexes are synthesized, the image cognition evaluation of a tested person on an excellent color matching case is accurately and comprehensively obtained and quantified, the emotion demand of a user on color is mapped, the uncertainty and the ambiguity of the emotion of the user are solved, an effective application reference is provided for the color matching design of a product, and specifically: (1) The invention carries out color matching combination representative extraction based on the excellent color matching case, fully considers the excellent color matching of the excellent color matching case and provides reference for the color matching design of the product; (2) The invention analyzes the perception cognition of the user on the color in the excellent color matching case by integrating subjective and objective evaluation data, and combines the fusion analysis of the product color matching gene programming influence factors to form a product color matching gene programming scheme library; (3) According to the invention, the color matching combination representation of the excellent color matching case sample is migrated to the product gene planning design scheme in a color-imparting manner, and the mapping association of the color matching combination representation and the product gene planning design scheme is established through quantization treatment, so that the uncertainty and the ambiguity of the traditional method are overcome, and an effective reference is provided for optimizing the color matching design of the product.
Drawings
FIG. 1 is a flow chart of a method for designing color matching of a product according to the present invention.
Fig. 2 is a matching degree ranking chart of each excellent matching case sample under different evaluation dimensions in an embodiment of the present invention.
FIG. 3 is a color matching combination representation of one evaluation dimension in an embodiment of the present invention.
FIG. 4 is a schematic diagram of a product color matching gene planning scheme library according to an embodiment of the invention.
FIG. 5 is a schematic diagram of an optimal color migration scheme with "reduced" color image and evaluation dimensions according to an embodiment of the present invention.
FIG. 6 is a schematic diagram of an optimal color migration scheme of color image and evaluation dimension "science and technology" in an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
The colors have vivid characteristics and unique charm, and can attract attention to the people in the first place, arouse emotion cognition and give an impressive impression no matter appreciation art works or functional products. The appreciation art works are rich in excellent color matching cases, such as Chinese traditional painting, ornaments, jewelry, fabrics and the like, and can be used as color matching inspiration sources of functional products. However, the artistic works and the products are characterized by the difference between the creator and the audience, the affective interaction between the users and the color matching of the products is also affected by a plurality of factors, and the color matching of the artistic works cannot be carried out on the products. The invention aims to provide a product color matching design method based on color image migration, which builds a bridge from color matching reference of an artistic work to product matching, and establishes association between excellent color matching cases in the artistic work and product color matching through color images, so that excellent color experience wisdom in the art field can be applied and contributed to current design, the artistic value of modern design is improved, and the quality of product color matching design is improved.
As shown in fig. 1, the product color matching design method based on color image migration includes:
(1) Extraction of basic color features by color clustering
And collecting excellent color matching case pictures, preprocessing, removing information irrelevant to colors, and clustering i main color features by using a K-means clustering algorithm, wherein the color features are color values in the embodiment.
(2) Calculating the matching degree of the excellent color matching case sample to obtain a color matching combination
Based on the main of n testees in k evaluation dimensionsObserving actual measurement values of evaluation data, and establishing an evaluation matrix U k ；
k=1, 2..k, the evaluation dimension expressed as different color image vocabulary, n=1, 2..n, M expressed as the number of excellent color matching case samples, m=1, 2..m; subjective evaluation data are the Lickte scale scores;
wherein U is nm The ranking score of the Lickt scale of the nth subject in the kth evaluation dimension for the mth excellent color matching case sample is represented by the 7-level Lickt scale in this embodiment, and the score is (-3, -2, -1,0,1,2,3), which can further represent the negative, neutral and positive values of the user evaluation.
Calculating the average value of the Liket scale scores of different excellent color matching case samples in k dimensionsThe sample matching degree ordering condition of the excellent sample cases under each evaluation dimension can be obtained, the excellent color matching case sample with the highest matching degree of each evaluation dimension is selected as the excellent color matching case representation, and the extracted color features are arranged and combined to obtain the color matching combination.
(3) Calculating image contribution of color matching combination
According to the matching degree subjective questionnaire actual measurement value K of n testees on i color matching combinations in the K-th dimension to excellent color matching case sample i (i=1, 2,., 6) performing independent weight calculation on the color, taking a single color as a single index, if the complex correlation coefficient R between the single index and other indexes is larger, the co-linearity relation between the single index and other indexes is stronger, the co-linearity relation between the single index and other indexes is easier to be represented by linear combination of other indexes, and the more repeated information is, so the weight of the index should be smaller. The single-dimension complex correlation coefficient calculation formula is as follows:
wherein the method comprises the steps ofSubjective questionnaire parameter mean for matching degree, +.>Parameters values are to be estimated for subjective questionnaires of matching degree. Selecting the reciprocal of the negative correlation coefficient, and obtaining a final weight value R through standardized processing and calculation:
for R i Taking the reciprocal and carrying out normalization processing to obtain each index weight W i ：
Obtaining the subjective matching degree Z of the color matching combination i The method comprises the following steps:
Z i ＝K i *W i
obtaining gazing duration according to the measured values of the eye movement data of n testees in each evaluation dimensionAnd number of gazing timesCalculating the product to obtain the objective dimension matching degree of the color matching combination>The method comprises the following steps:
finally obtain the meaning of the color matching combinationImage contribution degree Q i The method comprises the following steps:
Q i ＝Z i *E i
(4) Screening color matching combination representatives
And selecting the excellent color matching case representative color matching combination representative of each evaluation dimension according to the image contribution degree of the color matching combination from high to low.
(5) Carrying out color matching gene planning on the product, and establishing a product color matching gene planning whole sample library
According to the modeling structure of the product, analyzing the product color matching gene programming influence factors Ω, wherein the category number of each product color matching gene programming influence factor is denoted as J, j=1, 2 j ，O j ，R j The number of the product color matching gene programming influence factors included in omega is increased or decreased according to actual conditions, namely the number r of the product color matching gene programming influence factors is a positive integer larger than zero, and one product color matching gene programming influence factor can include multiple grades, so that the product is subjected to color matching gene programming, a product color matching gene programming whole sample library is established, and then the sample schemes P of the color matching gene programming of different products are obtained k The expression can be as follows:
P k ＝S j +O j +R j
(6) The subjective color image cognition evaluation of the product in each evaluation dimension is obtained, the product color matching image cognition rule is analyzed, the multiple regression analysis results of different product color matching gene programming influence factors in each dimension are calculated, corresponding samples are selected from a product color matching gene programming whole sample library, and a product color matching gene programming scheme library is established.
(6-1) scoring different product color matching gene planning samples in a product color matching gene planning whole sample library, so as to obtain subjective color image cognition evaluation data of the product of the tested person in each dimension, and establishing an evaluation matrix F k
Wherein: f (F) ak -subjective color image cognitive assessment value of the kth dimension of the kth color scheme.
(6-2) simultaneously combining the image evaluation matrix F according to the product color matching gene planning influence factors omega and the grades j of the different product color matching gene planning samples k Carrying out relevance expression on a product color matching gene programming influence factor omega and an evaluation dimension according to a quantitative I type theory, wherein the mapping expression relationship is as follows:
(6-3) then performing multiple linear regression calculation to obtain correlation between the different product color matching gene programming influence factors omega and the grades j thereof and the evaluation dimension, namely the different product color matching gene programming influence factors omega and the grades j thereof and the partial regression coefficient beta of the evaluation dimension K a 。
(6-4) for the multiple linear regression results, the partial regression coefficient β a And the contribution degree of the color matching gene programming influence factor of the r-th product to different evaluation dimensions is shown, and the larger the partial regression coefficient is, the larger the contribution degree is. And selecting the product color matching gene programming influence factors with the largest contribution degree under each evaluation dimension, selecting corresponding samples from a product color matching gene programming whole sample library, and establishing a product color matching gene programming scheme library.
(7) And determining color matching combination representation and a product color matching gene planning scheme according to the color image vocabulary, and developing color image migration based on the three color-imparting areas.
Finding out corresponding evaluation dimensions according to product color image requirements, and transferring color matching combination representations represented by excellent color matching case samples in the corresponding evaluation dimensions to a product color matching gene planning scheme in a main color, auxiliary color and spot color mode, wherein each color migration scheme can be described as follows:
MVP＝{(D c ，V d ，X e ) First ，(D c ，V d ，X e ) Second ，(D c ，V d ，X e ) Third }
wherein (D) c ，V d ，X e ) First Color expression for dominant color region, (D) c ，V d ，X e ) Second To aid in color expression of the color region, (D) c ，V d ，X e ) Third Color expression for the interspersed color region; d (D) c For colour numbering, V d For color D c Area ratio, X in original excellent color matching case sample e For color D c The image contribution degree represented by the color matching combination in the original excellent color matching case sample is calculated according to the formula Q in the step (3) i And (5) calculating to obtain the product.
(8) Obtaining satisfaction evaluation of testees, and carrying out gray correlation analysis on the color mapping relation
(8-1) obtaining a subject satisfaction evaluation
And scoring satisfaction degree aiming at different color migration schemes, wherein the obtained matrix Y is as follows:
wherein Y is gh Satisfaction scores for the h product color matching gene planning scheme for the g excellent color matching case sample are given, and g and h are positive integers.
(8-2) data normalization processing
To more truly count actual data, the adverse effect caused by the difference of data units or data sizes is reduced, firstly, V is calculated d Q and i and (5) performing min-max standardization treatment.
(8-3) calculating gray correlation
Calculating the color area ratio V by taking the color area ratio represented by the color matching combination and the image contribution degree as key indexes d Image contribution degree Q i Gray correlation between satisfaction evaluation scores of different evaluation dimensions.
(9) Optimal color migration scheme for output products
According to gray correlation analysis, the color matching relationship between the color combination representation represented by the excellent color matching case sample and the product color matching gene planning scheme in the evaluation dimension of the product color image demand pair can be obtained. The matching of the main color, the auxiliary color and the decoration color should be respectively selected and transferred by excellent color matching case indexes with higher gray correlation degree, so as to obtain the optimal color transfer scheme of the excellent color matching case corresponding to each evaluation dimension, namely the optimal product color matching scheme.
The method of the invention is verified by specific experimental data below.
A sample library of excellent color matching cases is established by taking Chinese painting as an example, and color image migration design is carried out on the product by taking an electric cooker as an example.
(1) And (3) screening and processing the pictures to determine 30 Chinese painting pictures as excellent color matching case samples, namely M=30, and performing color clustering on the Chinese painting pictures to obtain color values and color duty ratios of 6 characteristic colors.
(2) The 42 students 22-28 years old were invited to be tested, i.e. n=42, in this example 26 color image evaluation dimensions, i.e. k=26, which were clustered based on collected image vocabulary of related chinese drawings and products, and are rich, brief, warm, cool, orderly, tense, relaxed, heavy, lively, serious, clear, dull, soft, positive, happy, painful, elegant, luxurious, light, steady, mild, atmospheric, plain, scientific, safe, dangerous, respectively.
Subjective evaluation and objective eye movement experiments are respectively carried out on the testee, the matching degree of the excellent color matching cases and the image contribution degree of the color matching combination are calculated according to experimental data, and the matching degree ordering condition of the excellent color matching cases under different evaluation dimensions is shown in figure 2.
Calculating the contribution degree Q of the color matching combination image represented by the excellent color matching case i The color combination image contribution score for a representative excellent color matching case is shown in table 1.
TABLE 1
(3) The excellent color matching case representations corresponding to each evaluation dimension are selected in a sequence from high to low according to the matching degree, and then the color matching combination representations of the excellent color matching case representations are selected in a sequence from high to low according to the image contribution degree of the color matching combination, as shown in fig. 3, the color matching combination representations of the corresponding excellent color matching case representations with the "rich" evaluation dimension are shown.
(4) Analyzing gene programming influence factors of electric cooker products and summarizing into color matching duty ratio S j Color zone linking mode O j Color region combination pattern R j And (5) increasing the grade, and planning the color matching gene of the product.
The color matching proportion of the product is classified into 5 large grades, wherein S 1 Representing that the main color accounts for 50-65%, and the total auxiliary color and the decoration color accounts for 50-35%; s is S 2 Representing that the main color accounts for 65-75%, and the total auxiliary color and the decoration color accounts for 30-25%; s is S 3 Representing that the main color accounts for 75-85 percent, and the total auxiliary color and the decoration color accounts for 25-15 percent; s is S 4 Representing that the main color accounts for 85% -95% and the total auxiliary color and the decoration color accounts for 15% -5%; s is S 5 Representing that the main color accounts for 95% -100% and the total auxiliary color and the spot color accounts for 5% -0%.
Dividing the color region connection mode into 4 large grades, wherein O 1 Indicating contact; o (O) 2 Representing the interval; o (O) 3 Representing separation; o (O) 4 The representations are unified.
Dividing the color region combination mode into 2 large grades, wherein R 1 Representing a primary color + a secondary color; r is R 2 Representing the primary + secondary + interspersed.
And (3) establishing a product color matching gene programming whole sample library according to the product color matching gene programming influence factors, wherein the whole sample library is shown in table 2.
TABLE 2
(5) And carrying out relevance expression on the product color matching gene planning sample and the evaluation dimension through a quantitative I-type theory to obtain a mapping relation between the product color matching gene planning sample and the evaluation dimension, purifying a product color matching gene planning whole sample library, and establishing a product color matching gene planning scheme library, as shown in figure 4. (6) Develop market research, obtain the color image demand of the electric cooker product is brief and scientific,
finding out a color matching combination representative of excellent color matching case sample representative in the corresponding evaluation dimension and a product color matching gene planning scheme, and developing color image migration based on three color-imparting modes of main color, auxiliary color and spot color. And (3) carrying out satisfaction evaluation on the obtained scheme to obtain color mapping matching degree, and generating an optimal color migration scheme of a product, wherein the optimal color migration scheme is shown in fig. 5-6, the optimal color migration scheme of the color image and evaluation dimension is 'simple', and the optimal color migration scheme of the color image and evaluation dimension is 'technological'.
The invention relates to a product color matching design system based on color image migration, which comprises:
the excellent color matching case selection module is used for extracting color features from the excellent color matching case samples; obtaining subjective evaluation scores of a testee on excellent color matching case samples in a plurality of evaluation dimensions, and sequencing the excellent color matching case samples from high to low in each evaluation dimension according to the subjective evaluation scores;
the color matching combination representation selection module is used for selecting an excellent color matching case sample with highest subjective evaluation score equipartition order as an excellent color matching case representation of each evaluation dimension, carrying out permutation and combination on color features extracted from the excellent color matching case representation to obtain color matching combinations, acquiring subjective evaluation and objective eye movement data of a tested person on all the color matching combinations in each evaluation dimension, calculating image contribution degree of the color matching combinations according to the subjective evaluation and objective eye movement data, and selecting the color matching combination with highest image contribution degree as the color matching combination representation;
the product gene planning whole sample library building module is used for selecting product color matching gene planning influence factors according to product modeling, carrying out color matching gene planning of color image migration according to the product color matching gene planning influence factors, and building a product color matching gene planning whole sample library;
the product gene planning scheme library building module is used for coding the influence factors of each product color matching gene planning sample, calculating the association coefficient of the product color matching gene planning influence factors and the evaluation dimension according to a quantitative I-type theory, and obtaining the mapping relation between the product color matching gene planning samples and the evaluation dimension; purifying the product color matching gene planning whole sample library according to the mapping relation to obtain a product color matching gene planning scheme library;
the optimal color migration scheme selection module is used for migrating color matching combination representations to a product color matching gene planning scheme according to the main color, auxiliary color and spot color modes, obtaining a color migration scheme library of the color matching combination representations in each evaluation dimension, calculating satisfaction scores according to subjective evaluation of testees, respectively calculating gray correlation between the satisfaction scores and the area ratio of characteristic colors represented by each excellent color matching case and the image contribution degree represented by the color matching combination, and selecting and combining according to the gray correlation scores to generate an optimal color migration scheme of the product.
The electronic equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the product color matching design method based on color image migration when being loaded into the processor.
The computer readable storage medium of the present invention stores a computer program which, when executed by a processor, implements the color matching design method for a product based on color image migration.
The computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The processor is configured to execute the computer program stored in the memory to implement the steps in the method according to the above-mentioned embodiments.
Claims (9)
1. The product color matching design method based on color image migration is characterized by comprising the following steps of:
(1) Establishing an excellent color matching case sample library, and extracting color features from the excellent color matching case sample;
(2) Obtaining subjective evaluation scores of a testee on excellent color matching case samples in a plurality of evaluation dimensions, and sequencing the excellent color matching case samples from high to low in each evaluation dimension according to the subjective evaluation score mean;
(3) Selecting a superior color matching case sample with highest subjective evaluation score mean value order as a superior color matching case representation of each evaluation dimension, arranging and combining color features extracted from the superior color matching case representation to obtain color matching combinations, acquiring subjective evaluation and objective eye movement data of a tested person on all the color matching combinations in each evaluation dimension, calculating image contribution degree of the color matching combinations according to the subjective evaluation and objective eye movement data, and selecting the color matching combination with highest image contribution degree as the color matching combination representation;
(4) Selecting a product color matching gene programming influence factor according to the product modeling, performing color matching gene programming of color image migration according to the product color matching gene programming influence factor, and establishing a product color matching gene programming whole sample library; the product color matching gene programming influence factors comprise color matching duty ratio, color area linking mode and color area combination mode;
(5) Encoding the influence factors of each product color matching gene planning sample, and calculating the association coefficient of the product color matching gene planning influence factors and the evaluation dimension according to a quantitative I-type theory to obtain the mapping relation between the product color matching gene planning samples and the evaluation dimension; purifying the product color matching gene planning whole sample library according to the mapping relation to obtain a product color matching gene planning scheme library;
(6) Migrating the color matching combination representation to a product color matching gene planning scheme according to the main color, the auxiliary color and the spot color, obtaining a color migration scheme library of the color matching combination representation in each evaluation dimension, calculating satisfaction scores according to subjective evaluation of testers, respectively calculating gray correlation between the satisfaction scores and the area occupation ratio of the characteristic colors represented by each excellent color matching case and the image contribution degree represented by the color matching combination, and selecting and combining according to the gray correlation scores to generate an optimal color migration scheme of the product.
2. The color matching design method for color image migration based product according to claim 1, wherein said step (3) comprises the following steps:
obtaining measured values K of subjective questionnaire of i color matching combinations in excellent color matching case samples of testees in each evaluation dimension i Calculating the subjective matching degree Z of each color matching combination i ＝K i *W i The method comprises the steps of carrying out a first treatment on the surface of the Wherein W is i For K i Normalized value of inverse complex correlation coefficient;
obtaining the measured value E of objective eye movement experiment of i color matching combinations in the excellent color matching case sample of the tested person in each evaluation dimension i ；
Calculating the image contribution degree Q of each color combination in the excellent color matching case sample of each evaluation dimension i ，Q i ＝Z i *E i ；
Color combination representative of the excellent color matching case samples corresponding to each evaluation dimension is selected according to the high-to-low ranking.
3. The color matching design method for color image migration based product according to claim 2, wherein said step (6) saidCalculating satisfaction scores according to subjective evaluation of testees, and respectively calculating area occupation ratios of the satisfaction scores and characteristic colors represented by each excellent color matching case and image contribution degree Q represented by color matching combination i Gray correlation degree between the color components is selected and combined according to the gray correlation degree score to generate the optimal color migration scheme of the product, and the optimal color migration scheme comprises the following contents:
obtaining satisfaction scores of testees on each color migration scheme;
calculating the satisfaction degree score of each color migration scheme and the area ratio of the characteristic color represented by each excellent color matching case and the image contribution degree Q represented by the color matching combination i Gray correlation between;
and selecting a main color, an auxiliary color and an interspersed color from the color matching combination representation according to the maximum gray correlation degree to obtain an optimal color migration scheme of the product corresponding to each evaluation dimension.
4. The method of claim 3, further comprising the step of determining the area ratio of each product color matching gene plan and the image contribution degree Q of the color matching combination before calculating the gray correlation degree between the satisfaction degree score of each color migration scheme and the area ratio of the characteristic color represented by each excellent color matching case and the image contribution degree represented by the color matching combination i And (5) performing min-max standardization treatment.
5. The color matching design method for color image migration based product according to claim 1, wherein said step (5) comprises the following steps:
and obtaining a partial regression coefficient of the product color matching gene programming influence factor and the evaluation dimension through multiple linear regression calculation, and selecting the product color matching gene programming influence factor with the maximum partial regression coefficient in each evaluation dimension to form a product color matching gene programming scheme library.
6. The color image migration based product color matching design method of claim 1, wherein the evaluation dimension is a color image vocabulary.
7. A color matching design system for a product based on color image migration, comprising:
the excellent color matching case selection module is used for extracting color features from the excellent color matching case samples; obtaining subjective evaluation scores of a testee on excellent color matching case samples in a plurality of evaluation dimensions, and sequencing the excellent color matching case samples from high to low in each evaluation dimension according to the subjective evaluation score mean;
the color matching combination representation selection module is used for selecting an excellent color matching case sample with highest subjective evaluation score average value sequence for each evaluation dimension as an excellent color matching case representation of each evaluation dimension, arranging and combining color features extracted from the excellent color matching case representation to obtain color matching combinations, acquiring subjective evaluation and objective eye movement data of a tested person on all the color matching combinations in each evaluation dimension, calculating the image contribution degree of the color matching combinations according to the subjective evaluation and objective eye movement data, and selecting the color matching combination with highest image contribution degree score as the color matching combination representation;
the product color matching gene planning whole sample library building module is used for selecting product color matching gene planning influence factors according to product modeling, carrying out color matching gene planning of color image migration according to the product color matching gene planning influence factors, and building a product color matching gene planning whole sample library; the product color matching gene programming influence factors comprise color matching duty ratio, color area linking mode and color area combination mode;
the product color matching gene planning scheme library building module is used for coding the influence factors of each product color matching gene planning sample, calculating the association coefficient of the product color matching gene planning influence factors and the evaluation dimension according to the quantitative I-type theory, and obtaining the mapping relation between the product color matching gene planning samples and the evaluation dimension; purifying the product color matching gene planning whole sample library according to the mapping relation to obtain a product color matching gene planning scheme library;
the optimal color migration scheme selection module is used for migrating color matching combination representations to a product color matching gene planning scheme according to the main color, auxiliary color and spot color modes, obtaining a color migration scheme library of the color matching combination representations in each evaluation dimension, calculating satisfaction scores according to subjective evaluation of testees, respectively calculating gray correlation between the satisfaction scores and the area ratio of characteristic colors represented by each excellent color matching case and the image contribution degree represented by the color matching combination, and selecting and combining according to the gray correlation scores to generate an optimal color migration scheme of the product.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when loaded into the processor implements the color image migration based product color matching design method according to any of claims 1-6.
9. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the color matching design method for color image migration-based product according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696128.5A CN116738717B (en) | 2023-06-13 | 2023-06-13 | Product color matching design method and system based on color image migration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696128.5A CN116738717B (en) | 2023-06-13 | 2023-06-13 | Product color matching design method and system based on color image migration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116738717A CN116738717A (en) | 2023-09-12 |
| CN116738717B true CN116738717B (en) | 2024-03-22 |
Family
ID=87912835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310696128.5A Active CN116738717B (en) | 2023-06-13 | 2023-06-13 | Product color matching design method and system based on color image migration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116738717B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015022533A (en) * | 2013-07-19 | 2015-02-02 | 東日本旅客鉄道株式会社 | Tint design evaluation device, and tint design evaluation method |
| CN109978837A (en) * | 2019-03-07 | 2019-07-05 | 青岛大学 | A kind of fit degree evaluation method based on the dressing image vision factor |
| JP2020091591A (en) * | 2018-12-04 | 2020-06-11 | 東日本旅客鉄道株式会社 | Indoor space design evaluation system and indoor space design evaluation method |
| CN112598761A (en) * | 2020-12-30 | 2021-04-02 | 东华大学 | Textile and garment color collocation collaborative design and intelligent recommendation method |
| CN113743109A (en) * | 2021-09-09 | 2021-12-03 | 浙江工业大学 | Product intelligent color matching design system based on user emotion |
-
2023
- 2023-06-13 CN CN202310696128.5A patent/CN116738717B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015022533A (en) * | 2013-07-19 | 2015-02-02 | 東日本旅客鉄道株式会社 | Tint design evaluation device, and tint design evaluation method |
| JP2020091591A (en) * | 2018-12-04 | 2020-06-11 | 東日本旅客鉄道株式会社 | Indoor space design evaluation system and indoor space design evaluation method |
| CN109978837A (en) * | 2019-03-07 | 2019-07-05 | 青岛大学 | A kind of fit degree evaluation method based on the dressing image vision factor |
| CN112598761A (en) * | 2020-12-30 | 2021-04-02 | 东华大学 | Textile and garment color collocation collaborative design and intelligent recommendation method |
| CN113743109A (en) * | 2021-09-09 | 2021-12-03 | 浙江工业大学 | Product intelligent color matching design system based on user emotion |
Non-Patent Citations (5)
| Title |
|---|
| 公务机驾驶舱内饰布局设计感性评价;陆蔚华 等;计算机集成制造系统;正文第1-21页 * |
| 基于灰色关联分析的产品色彩方案多意象优选;孙志学;;机械设计(第01期);第120-122页 * |
| 基于视觉感知的灰色设计决策方法;陆蔚华，孙天琪;中国机械工程;第32卷(第23期);第2890-2897页 * |
| 眼动仪在服装配色视觉评价中应用;吴亚丽;穆红;;轻纺工业与技术(第05期);第67-69页 * |
| 饮料色彩营销的配色设计研究;陈眉;;中国包装(第04期);第35-37页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116738717A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629338B (en) | Face beauty prediction method based on LBP and convolutional neural network | |
| Li et al. | Aesthetic visual quality assessment of paintings | |
| Sartori et al. | Who's afraid of itten: Using the art theory of color combination to analyze emotions in abstract paintings | |
| Kagian et al. | A humanlike predictor of facial attractiveness | |
| CN109299372A (en) | A kind of wisdom curricula-variable recommended method based on collaborative filtering | |
| KR20110110390A (en) | User preference applied emotion-based image color control method using interactive genetic algorithm | |
| CN108596051A (en) | A kind of intelligent identification Method towards product style image | |
| Yang et al. | Selecting representative affective dimensions using Procrustes analysis: An application to mobile phone design | |
| CN107743225A (en) | It is a kind of that the method for carrying out non-reference picture prediction of quality is characterized using multilayer depth | |
| CN111062260A (en) | Automatic generation method of facial cosmetic recommendation scheme | |
| Lemarchand | Fundamental visual features for aesthetic classification of photographs across datasets | |
| CN106485266A (en) | A kind of ancient wall classifying identification method based on extraction color characteristic | |
| Amirshahi et al. | Judging aesthetic quality in paintings based on artistic inspired color features | |
| CN116738717B (en) | Product color matching design method and system based on color image migration | |
| CN111241372B (en) | Method for predicting color harmony degree according to user preference learning | |
| Li et al. | Saliency consistency-based image re-colorization for color blindness | |
| CN107194727A (en) | The user's request factor based on Kano model is characterized and extracting method | |
| Lu et al. | Research on product design education based on evaluation grid method | |
| Li et al. | AR-CNN: an attention ranking network for learning urban perception | |
| CN114186497B (en) | Intelligent analysis method, system, equipment and medium for value of art work | |
| CN115438871A (en) | Ice and snow scenic spot recommendation method and system integrating preference and eliminating popularity deviation | |
| Hu et al. | The study of the double color matching of the elderly assistive products based on the Kansei engineering | |
| Ogino | A design support system for indoor design with originality suitable for interior style | |
| CN113378885A (en) | New user aesthetic preference calibration and classification method based on preferred image pair | |
| CN112417288A (en) | Task cross-domain recommendation method for crowdsourcing software testing |
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 |