CN113240765A - Color matching method and device, computer equipment and storage medium - Google Patents

Abstract

The application relates to a method, a system and a computer storage medium for color collocation layout. The method comprises the following steps: receiving a commodity graph input by a user, and constructing an alternative library; respectively extracting the colors of all the alternative templates in the commodity map and the alternative library and the color ratio of the colors, and determining the theme color; judging whether the maximum color ratio of the commodity image is greater than a first threshold value, matching the commodity image with the maximum color ratio greater than the first threshold value with the alternative templates respectively, judging the commodity saliency, removing the alternative templates with low commodity saliency, and updating the alternative library; converting the color information of the theme color to obtain a color system of the commodity image and a color system of each alternative template; and calculating the color system intersection number of the commodity picture and each alternative template, sequencing the color system intersection number, and determining the matching template of the commodity picture. The invention converts the collocation mode into machine language, the color collocation effect is harmonious, and the color difference of the effect picture of the commodity with different colors is larger, thereby achieving the effect of thousands of people.

Description

Color matching method and device, computer equipment and storage medium

Technical Field

The application relates to the technical field of artificial intelligence design, relates to a method and a system for color matching, and particularly relates to color matching in an intelligent synthesis banner (banner advertisement) image.

Background

In recent years, with the popularity of popular science and technology terms such as artificial intelligence, neural networks, deep learning and the like, "artificial intelligence design" is gradually attracting attention and pursuing. Marketing promotion is one of the most common rapid delivery means of the e-commerce, and the banner demand is rapidly increased due to the high frequency of 618 promotion, 818 promotion, 11 promotion, 12 promotion, middle-aged promotion, end-of-year promotion and legal holiday promotion … … promotion. Through the development of the last two years, the intelligent synthesis Banner function has achieved a good result, and an attractive Banner can be automatically designed according to a commodity graph input by a user. The above functions can be realized at present, but some defects still exist, for example, even if the quality of the banner template is higher, the overall effect of the banner is poor due to the fact that the color tone of the commodity image is not matched with the color tone of the banner template.

At present, many Banner maps are carefully designed by designers, and both color matching and layout are perfect, but if the Banner maps are used as templates of intelligent synthesis Banner maps, the overall color matching of the Banner maps can be greatly changed and even be very disfavored once the commodity maps are replaced.

In addition, in the intelligent synthesis process of the banner map, template screening is an extremely key step, however, the screening process based on the color scale is closely related to whether the synthesis effect map is attractive, and the observation of the current large number of E-commerce platforms banner shows that the colors of the commodity map correspond to the colors of the banner map, possibly the colors of characters, possibly commodity tables and possibly ornaments, and the whole effect of the banner is harmonious and attractive due to the correspondence between the colors.

Disclosure of Invention

In order to solve the problems, the artificially designed banner map is compared, the overall effect of the banner is found to be closely related to the color matching of the commodity and the banner template, and the colors of most of the artificially designed banner commodity map have certain responses to the elements in the banner, so that the invention provides a scheme for matching the commodity and the material colors, which comprises the following steps:

a method of color matching, the method comprising:

receiving a commodity graph input by a user, and constructing an alternative library comprising all alternative templates;

respectively extracting the colors of all the alternative templates in the commodity image and the alternative library and the color ratio of the colors, and determining the theme colors of the commodity image and the alternative templates;

judging whether the maximum color ratio of the commodity image is greater than a first threshold value, respectively matching the commodity image with the candidate templates in the candidate library, judging the commodity visibility, removing the candidate templates with low commodity visibility, and updating the candidate library, wherein the maximum color ratio of the commodity image is greater than the first threshold value;

respectively converting the color information of the theme colors of the alternative templates in the commodity picture and the alternative library to obtain the color system of the commodity picture and the color system of each alternative template;

and calculating the color system intersection number of the commodity picture and each alternative template, sequencing the color system intersection number, and determining the matching template of the commodity picture.

2. The method of claim 1, wherein constructing the alternative library including all of the alternative templates comprises preprocessing the alternative templates, the preprocessing comprising combining all layers of the alternative templates except the commodity image layer into one map.

3. The method according to claim 1, wherein determining the theme color comprises extracting the colors of the same number of the commodity map and the alternative template and a color proportion of the color, respectively, and outputting the color with the color proportion larger than the second threshold value as the theme color of the commodity map or the alternative template.

4. The method of claim 1, wherein the color with the largest color ratio is the first theme color;

judging commodity visibility, removing the alternative template with low commodity visibility, updating the alternative library,

respectively calculating the color difference of the first theme color of the commodity map and the first theme color of each candidate template in an LAB color space;

if the color difference is not larger than the third threshold, removing the alternative template corresponding to the color difference and updating the alternative library, and if the color difference is larger than the third threshold, keeping the alternative template corresponding to the color difference.

5. The method of claim 1, wherein the theme color of each candidate template in the commodity map and the candidate library is converted to HSV space separately;

and establishing mapping between the hue component and the color system, and determining the color system of the commodity image and the color system of each alternative template according to the hue component.

6. A method as claimed in claim 5, characterized in that the method divides 14 color systems.

7. The method according to claim 5, characterized in that the color system of the commodity map is compared with the color system of each candidate template respectively, and the number of color system intersections with each candidate template is calculated;

sorting the intersection number of the color systems in a descending order, and outputting the sorted alternative templates;

and determining a matching template of the commodity map.

8. A color matching apparatus, comprising:

the input module is used for receiving the commodity graph input by the user and constructing an alternative library comprising all the alternative templates;

the extraction module is used for respectively extracting the colors of all the alternative templates in the commodity image and the alternative library and the color proportion of the colors, and determining the theme colors of the commodity image and the alternative templates;

the judging module is used for judging whether the maximum color ratio of the commodity image is larger than a first threshold value or not, matching the commodity image with the maximum color ratio larger than the first threshold value with the alternative templates in the alternative library respectively, judging the commodity visibility, removing the alternative template with low commodity visibility and updating the alternative library;

the conversion module is used for respectively converting the color information of the theme colors of the alternative templates in the commodity image and the alternative library to obtain the color system of the commodity image and the color system of each alternative template;

and the screening module is used for calculating the color system intersection number of the commodity image and each alternative template, sequencing the color system intersection number and determining the matched template of the commodity image.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented by the processor when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.

The color matching method, the device, the computer equipment and the storage medium are a method for matching colors of commodities and materials in the intelligent synthesis process of the e-commerce platform, the colors and the color ratios of the commodity images are extracted according to the commodity images input by a user, then the commodity images are matched with the colors of the banner templates in the material library, and the attractive banner templates are screened out, so that the coordination of color matching is ensured, and the effect of thousands of people is realized.

Drawings

FIG. 1 is a schematic diagram illustrating a color matching method according to an embodiment;

FIG. 2 is a schematic overall flow chart of a color matching method according to an embodiment;

FIG. 3 is a block diagram of a color matching apparatus according to an embodiment;

FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The color matching method provided by the application is a color matching method of a commodity and a material, and in one embodiment, as shown in fig. 1 to 4, the color matching method comprises the following steps:

and S100, receiving the commodity map input by the user, and constructing an alternative library comprising all the alternative templates.

In this embodiment, a commodity map input by a user is received, specifically, the commodity map input by the user is read by using a PIL library and is recorded as image _ goods, an alternative library including all alternative templates is constructed, all the alternative templates are preprocessed, the template library is analyzed by using a psd-tools library, all the layers of the alternative templates from which the commodity layer is removed are combined into one map and recorded as image _ banner

S200, extracting the colors of all the alternative templates in the commodity map and the alternative library and the color ratio of the colors respectively, and determining the theme colors of the commodity map and the alternative templates.

In this embodiment, a fast octree method (fast octree) is used to extract a color and a color ratio of the color for each of the product drawings image _ goods and the candidate templates image _ banner in the template library, and a color with the color ratio greater than a second threshold is output as a subject color of the product drawings or the candidate templates.

Preferably, 10 output color RGB values are extracted, colors with a ratio less than 0.1% are ignored, and colors with a ratio greater than 0.1% are selected as the subject colors of image _ goods and image _ banner.

S300, judging whether the maximum color ratio of the commodity image is larger than a first threshold value or not, respectively matching the commodity image with the maximum color ratio larger than the first threshold value with the alternative templates in the alternative library, judging the commodity visibility, removing the alternative template with low commodity visibility, and updating the alternative library.

In this embodiment, the maximum color ratio of the product image is first compared with a first threshold, and if the maximum color ratio is greater than the first threshold, the product saliency is determined, that is, whether the product image and the alternative template matching are conspicuous is determined.

Preferably, the color with the largest color ratio is used as the first theme color, and the commodity saliency of the commodity map with the first theme color ratio larger than 70% is judged to avoid the risk of commodity unobtrusiveness.

Specifically, the commodity saliency is judged, the alternative template with low commodity saliency is removed, and the updating of the alternative library comprises the following steps:

and respectively calculating the color difference of the first theme color of the commodity map and the first theme color of each candidate template in the LAB color space.The LAB color space is based on the perception of human eyes to colors and can represent all colors which can be felt by human eyes, L represents lightness, A represents red-green color difference, B represents blue-yellow color difference, and the calculation formula is as follows, C₁、C₂Two RGB values representing input are respectively a first theme color of the commodity picture and a first theme color of the alternative template, and deltaC represents C₁、C₂Color difference in LAB color space:

ΔR＝C_1,R-C_2,R，

ΔG＝C_1,G-C_2,G，

ΔB＝C_1,B-C_2,B，

if the color difference is not larger than the third threshold, removing the alternative template corresponding to the color difference and updating the alternative library, and if the color difference is larger than the third threshold, keeping the alternative template corresponding to the color difference. Preferably, the third threshold is 50, Δ C < ═ 50, which represents that the commodity map is not obvious on the alternative template, and the template is discarded, whereas the template remains.

S400, respectively converting the color information of the theme colors of the commodity image and the alternative templates in the alternative library to obtain the color system of the commodity image and the color system of each alternative template.

In this embodiment, after the commodity saliency is determined in step S300, the template library is updated, and color information conversion is performed on the candidate templates that meet the requirement.

Specifically, the theme color of each alternative template in the commodity map and the alternative library is converted into HSV space due to RGB respectively. And establishing mapping between the hue component and the color system, determining the color system of the commodity drawing and the color system of each alternative template according to the hue component, and preferably, obtaining the RGB color system corresponding to the HSV color wheel according to the H component.

In one embodiment, a color mapping is performed based on the color wheel and the H value. Preferably, 14 color systems are divided. Black and white were further defined in addition to the 12 color systems on the color wheel.

S500, calculating the color system intersection number of the commodity image and each alternative template, sequencing the color system intersection number, and determining the matching template of the commodity image.

In this embodiment, the color system of the product map obtained in step S400 and the color system of each candidate template are used to calculate the number of color system intersections between the product map and each candidate template, and then all the candidate templates are sorted according to the number of color system intersections, preferably, sorted from large to small, and the top template is the best matching template.

It should be understood that, although the steps in the flowchart are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 3, there is provided a color matching apparatus applying the above method, including: an input module 100, an extraction module 200, a judgment module 300, a conversion module 400 and a screening module 500. Wherein:

and the input module 100 is used for receiving the commodity map input by the user and constructing an alternative library comprising all the alternative templates.

And the extracting module 200 is configured to extract colors of all candidate templates in the commodity map and the candidate library and a color ratio of the color, respectively, and determine theme colors of the commodity map and the candidate templates.

The judging module 300 is configured to judge whether the maximum color ratio of the commodity map is greater than a first threshold, match the commodity map with the maximum color ratio greater than the first threshold with the alternative templates in the alternative library, perform commodity visibility judgment, remove the alternative template with low commodity visibility, and update the alternative library.

The conversion module 400 is configured to convert the color information of the theme colors of the candidate templates in the commodity map and the candidate library respectively to obtain the color system of the commodity map and the color system of each candidate template.

And the screening module 500 is configured to calculate the color intersection number of the commodity map and each candidate template, sort the color intersection numbers, and determine a matching template of the commodity map.

For the specific limitations of the color matching device, reference may be made to the limitations of the color matching method above, and further description is omitted here. The various modules in the above-described system may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a data management server, and its internal structure diagram may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer equipment is used for communicating with an external data source terminal through network connection so as to receive data uploaded by the data source terminal. The computer program is executed by a processor to implement a color matching method.

Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the color matching method when executing the computer program.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The invention discloses a color matching method, a color matching system, computer equipment and a storage medium. The invention provides a method for quantifying the visibility of a commodity image, which carries out preliminary screening of a template by calculating a color distance in a Lab space; meanwhile, the invention provides collocation logic of the commodity map and the banner template, the method respectively obtains color systems contained in the commodity map and the banner template in HSV space, and then the intersection number of the commodity map color system set and the banner template color system set is used as a template screening basis. The invention converts the matching mode of the commodity picture and the banner template into machine language, and the machine language is used as a screening rule in the intelligent synthesis process of the banner, so that the color matching effect is harmonious, and the effect pictures of commodities with different colors have larger color difference, thereby achieving the effect of thousands of people.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method of color matching, the method comprising:

receiving a commodity graph input by a user, and constructing an alternative library comprising all alternative templates;

respectively extracting the colors of all the alternative templates in the commodity map and the alternative library and the color ratio of the colors, and determining the theme colors of the commodity map and the alternative templates;

judging whether the maximum color ratio of the commodity image is larger than a first threshold value or not, respectively matching the commodity image with the maximum color ratio larger than the first threshold value with the alternative templates in the alternative library, judging the commodity visibility, removing the alternative templates with low commodity visibility, and updating the alternative library;

respectively converting the color information of the theme colors of the commodity image and the alternative templates in the alternative library to obtain a color system of the commodity image and a color system of each alternative template;

and calculating the color intersection number of the commodity picture and each alternative template, sequencing the color intersection number, and determining the matching template of the commodity picture.

2. The method according to claim 1, wherein the constructing of the alternative library including all the alternative templates comprises preprocessing the alternative templates, wherein the preprocessing comprises combining all layers of the alternative templates except the commodity image layer into one image.

3. The method according to claim 1, wherein the determining the theme color comprises extracting the colors of the commodity map and the alternative template in the same number and the color proportion of the color respectively, and outputting the color with the color proportion larger than the second threshold value as the theme color of the commodity map or the alternative template.

4. The method of claim 1, wherein the color with the largest color proportion is a first theme color;

the commodity saliency is judged, the alternative template with low commodity saliency is removed, the alternative library is updated to include,

respectively calculating the color difference of the first theme color of the commodity map and the first theme color of each candidate template in an LAB color space;

if the color difference is not larger than a third threshold, removing the alternative template corresponding to the color difference and updating the alternative library, and if the color difference is larger than the third threshold, reserving the alternative template corresponding to the color difference in the alternative library.

5. The method according to claim 1, characterized in that the theme color of each alternative template in the commodity map and the alternative library is converted into HSV space;

and establishing mapping between the hue component and the color system, and determining the color system of the commodity image and the color system of each alternative template according to the hue component.

6. The method of claim 5, wherein the method divides 14 color systems, the color systems comprising black and white.

7. The method according to claim 5, wherein the color system of the commodity map is compared with the color system of each candidate template respectively, and the number of color system intersections with each candidate template is calculated;

sorting the color system intersection numbers in a descending order, and outputting sorted alternative templates;

and determining a matching template of the commodity map.

8. A color matching apparatus, comprising:

the input module is used for receiving the commodity graph input by the user and constructing an alternative library comprising all the alternative templates;

the extraction module is used for respectively extracting the colors of all the alternative templates in the commodity map and the alternative library and the color proportion of the colors, and determining the theme colors of the commodity map and the alternative templates;

the judging module is used for judging whether the maximum color ratio of the commodity image is larger than a first threshold value or not, matching the commodity image with the maximum color ratio larger than the first threshold value with the alternative templates in the alternative library respectively, judging the commodity visibility, removing the alternative template with low commodity visibility and updating the alternative library;

the conversion module is used for respectively converting the color information of the theme colors of the commodity image and the alternative templates in the alternative library to obtain the color system of the commodity image and the color system of each alternative template;

and the screening module is used for calculating the color intersection number of the commodity map and each alternative template, sequencing the color intersection number and determining the matched template of the commodity map.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.

Images