Advertisement identification pattern generation method and device, electronic equipment and storage medium

Abstract

The application provides an advertisement logo generation method and device, electronic equipment and storage medium, and relates to the technical field of computer-aided design.The application obtains user demand data, filters images meeting the requirements from an image library to form a first image set, extracts feature parameters of the image set, calculates a readability index, a color specification index and a negative space balance index based on the feature parameters, comprehensively generates an image quality evaluation index, corrects the image quality evaluation index according to the length-width ratio and shape complexity of the images in the first image set, obtains a correction value, and finally selects an image with the largest image quality evaluation index correction value as the optimal selection of the user according to the priority order.The application realizes high-quality design of the advertisement logo through feature extraction and correction priority order.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer-aided design, in particular to an advertisement logo generation method and device, electronic equipment and storage medium. BACKGROUND

[0002] Current pattern generation methods mainly involve the cross-application of computer graphics, artificial intelligence, machine learning, and visual perception. Traditional advertisement logo design relies on the experience and creativity of human designers, but with the advancement of digital technology, algorithm-based pattern generation has gradually become a trend. Using computerized analysis, image recognition, and feature extraction techniques, efficient advertisement logo design can be achieved, improving the quality and efficiency of design. In addition, intelligent design methods can automatically generate advertisement patterns that meet design requirements based on visual saliency, color matching, readability, and negative space parameters.

[0003] Currently, the development of advertisement logo generation technology is gradually moving towards intelligence, individualization, and automation. By building a multi-modal material database and combining deep learning technology, advertisement design can not only be automatically optimized according to user input requirements, but also can be creatively innovative and recommended based on historical data. Especially in the context of the continuous progress of big data analysis and AI algorithms, designers can use AI-assisted tools to more accurately match suitable materials, reduce design time costs, and improve design consistency and creative performance.

[0004] In the prior art, traditional advertisement design often relies on experience and human creativity, resulting in low design efficiency, unstable quality, and difficulty in systematically evaluating the visual effects and practicality of the design. Moreover, traditional advertisement logo generation often lacks flexibility in design, making it difficult to make personalized adjustments according to user-specific needs, resulting in generated patterns that cannot fully meet the diverse needs of the market.

[0005] Therefore, it is necessary to provide an advertisement logo generation method, device, electronic equipment, and storage medium to solve the above problems.

[0006] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The present application aims to provide an advertisement logo generation method, device, electronic equipment, and storage medium to solve the problems raised in the background.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0009] An advertisement logo generation method, the specific steps include:

[0010] Step 1: Obtain the design requirement data of the user, the design requirement data includes the aspect ratio of the logo, the color combination, the graphic element and the application scene category, select multiple images from the image library that meet the design requirement data to obtain a first image set;

[0011] Step 2: Obtain the feature parameters of the images in the first image set, the feature parameters include the length-width ratio of the image, the shape complexity, the color coordination, the color focus degree, the blank area ratio and the negative space distribution uniformity;

[0012] Step 3: Calculate the related feature indexes for representing the image quality according to the extracted feature parameters, the feature indexes include the readability index, the color specification index and the negative space balance index, and generate an image quality evaluation index by comprehensively using the readability index, the color specification index and the negative space balance index;

[0013] Step 4: Correct and adjust the image quality evaluation index based on the length-width ratio and the shape complexity of the images in the first image set to obtain an image quality evaluation index correction value, sort the image quality evaluation index correction values according to the priority size order, and take the one with the largest image quality evaluation index correction value as the optimal selection of the user.

[0014] Further, the method for obtaining the feature parameters of the images in the first image set is as follows:

[0015] Use the edge detection and contour analysis in computer comprehensive feature extraction technology to detect the patterns of the images in the first image set, identify the outer contour of the image, obtain the length and width of the image, and the ratio of the length to the width is the length-width ratio ; Obtain the perimeter and area of the image, and the ratio of the perimeter to the area is the shape complexity ;

[0016] Based on the dominant color extraction technology in computer comprehensive feature extraction technology, use clustering algorithm to extract the dominant color tone, obtain the dominant color tone of each image, and through color space conversion technology, obtain the brightness and color component of the image color, and calculate the color coordination and color focus degree, the formula is as follows:

[0017]

[0018]

[0019]

[0020]

[0021] wherein, , respectively represent the color harmony and color focus of the image, is the index of the dominant color tone in the image, and , is the total number of the extracted dominant color tones in the image, , , is the third component in the Lab color space of the first dominant color tone, , , is the third component in the Lab color space of the first other color, is the index of the other color, and , is the proportion of the first dominant color tone in the image, is the maximum color harmony between the dominant color tone and the other color, is the color harmony of the first dominant color tone in the image;

[0022] Based on the layout data of the images in the first image set, the images are evenly divided into grids by using target detection and segmentation techniques in computer synthesis feature extraction technology, and then the total area of the images and the area of the negative space are obtained to calculate the blank area ratio and the negative space distribution uniformity, according to the formula:

[0023]

[0024]

[0025] wherein, , respectively represent the blank area ratio and the negative space distribution uniformity, , respectively are the total area of the negative space and the total area of the image, represents the area of each grid, is the total number of the divided grids, is the index of the grid number, , is the area of the negative space in the first grid.

[0026] Further, the related feature indexes for representing the quality of the advertising logo pattern are calculated and generated according to the extracted feature parameters of the related design requirements, and the method is as follows:

[0027] The readability index of the advertising logo pattern is calculated based on the blank area ratio, color coordination degree and color focusing degree of the advertising logo pattern, and the formula is:

[0028]

[0029] wherein, represents the readability index of the advertising logo pattern;

[0030] The color specification index of the advertising logo pattern is calculated based on the color coordination degree and color focusing degree of the advertising logo pattern, and the formula is:

[0031]

[0032] wherein, represents the color specification index of the advertising logo pattern, is an ideal color coordination degree, is an ideal color focusing degree;

[0033] The negative space balance index of the advertising logo pattern is calculated based on the blank area ratio and negative space distribution uniformity of the advertising logo pattern, and the formula is:

[0034]

[0035] wherein, represents the negative space balance index of the advertising logo pattern.

[0036] Further, the image quality evaluation index is generated by comprehensively using the readability index, the color specification index and the negative space balance index, and the formula is:

[0037]

[0038] wherein, represents the image quality evaluation index.

[0039] Further, the image quality evaluation index is corrected and adjusted based on the length-width ratio and shape complexity of the images in the first image set to obtain an image quality evaluation index correction value, and the image quality evaluation index correction values are sorted according to the priority size order, and the image with the largest image quality evaluation index correction value is selected as the optimal selection of the user, and the method is:

[0040] According to the different style requirements of the user for the logo pattern and in combination with the length-width ratio and shape complexity of the images in the first image set, the image quality evaluation index is corrected, and the formula is:

[0041]

[0042] wherein, an image quality evaluation index correction value, a shape complexity of an image in the first image set, a length-width ratio of an image in the first image set, an ideal length-width ratio;

[0043] The image quality evaluation index correction value is prioritized according to the shape complexity of the style required by the user, the optimal selection of the user is obtained, and the feature parameters of the image in the first image set corresponding to the optimal selection are used as the design parameters of the advertising logo pattern for design.

[0044] The application further provides an advertising logo pattern generation device, which is used for executing the above-mentioned advertising logo pattern generation method and comprises:

[0045] A design requirement analysis module is configured to obtain design requirement data of a user, the design requirement data comprising a length-width ratio, a color combination, a graphic element and an application scene category of a logo pattern, filter a plurality of images meeting the design requirement data from an image library to obtain a first image set;

[0046] A feature extraction generation module is configured to obtain feature parameters of images in the first image set, the feature parameters comprising a length-width ratio, a shape complexity, a color coordination degree, a color focus degree, a blank area ratio and a negative space distribution uniformity of the images;

[0047] An image quality evaluation index calculation module is configured to calculate relevant feature indexes for representing image quality according to the extracted feature parameters, the feature indexes comprising a readability index, a color specification index and a negative space balance index, and generate an image quality evaluation index by comprehensively using the readability index, the color specification index and the negative space balance index;

[0048] A calibration correction and optimal pattern selection module is configured to correct and adjust the image quality evaluation index based on the length-width ratio and the shape complexity of the images in the first image set to obtain an image quality evaluation index correction value, and sort the image quality evaluation index correction values according to the priority size order, so that the image quality evaluation index correction value with the maximum value is taken as the optimal selection of the user.

[0049] The application further provides an electronic device, which comprises:

[0050] a processor and a memory connected with the processor in communication; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor to make the processor execute the above-mentioned advertising logo pattern generation method.

[0051] The application further provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the advertisement logo generation method.

[0052] Compared with the prior art, the application has the following beneficial effects:

[0053] The application significantly improves the efficiency and quality of advertisement logo design. Through comprehensive feature extraction technology, it can quickly analyze user needs and extract key parameters, thereby reducing the time and effort required for manual design. At the same time, based on the evaluation of quantitative feature indexes, the generated design achieves higher standards in visual effect and practicality. In addition, the personalized design capability is enhanced, making the advertisement logo better fit the diversified market demand, improving the emotional resonance with the target audience, and thus improving the attractiveness and propagation effect of the advertisement;

[0054] The advertisement logo generation method of the application accurately obtains user design requirement data, combines multi-dimensional feature parameters such as aspect ratio, shape complexity, color coordination, and comprehensively generates image quality evaluation indexes. Such design not only meets the user's individual needs, but also ensures the visual appeal of the logo and the clarity of information transmission, improving user satisfaction and advertisement propagation effect.

[0055] In addition, the system uses advanced computer vision technology for feature extraction, making image analysis more scientific and efficient. By correcting and prioritizing the image quality evaluation index, the optimal choice is quickly identified, ensuring the professionalism and optimization effect of the design. This method is not only suitable for various application scenarios, but also has good market promotion potential, which helps to improve the efficiency and quality of designers' works.

[0056] The application realizes efficient and personalized advertisement logo design through comprehensive computer feature extraction technology and quantitative evaluation system, improves design quality and ensures copyright compliance. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 The figure is a schematic diagram of the overall method flow of the application.

[0058] Figure 2 The figure is a schematic diagram of the system module flow of the application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical scheme and advantages of the application clearer, the application is further described in detail below with specific examples.

[0060] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the same meaning as those commonly understood by one of ordinary skill in the art to which the present application belongs. The terms "first", "second", and similar terms are used herein merely to distinguish one element from another, and are not intended to imply any order or sequence. The terms "include", "contain", and similar terms are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or apparatuses that consist of, include, or contain the recited elements, or their equivalents, are within the scope of the present application. The terms "connect" and "couple" and similar terms are not limited to a direct connection or coupling, but also include an indirect connection or coupling, such as through an intermediary. The terms "upper", "lower", "left", "right", and the like are used only to indicate relative positions, and can change accordingly when the absolute positions of the described objects change.

[0061] Embodiment:

[0062] Referring to Figure 1 The present application provides a technical solution:

[0063] An advertisement logo generation method, the specific steps comprising:

[0064] Step 1: Obtain the design requirement data of the user, the design requirement data including the aspect ratio, color combination, graphic element and application scenario category of the logo, filter a plurality of images from the image library that meet the design requirement data to obtain a first image set;

[0065] Step 2: Obtain the feature parameters of the images in the first image set, the feature parameters including the aspect ratio, shape complexity, color coordination, color focus, blank area ratio and negative space distribution uniformity of the images;

[0066] Step 3: Calculate the related feature indexes for representing the image quality according to the extracted feature parameters, the feature indexes including the readability index, color specification index and negative space balance index, and generate an image quality evaluation index by comprehensively using the readability index, color specification index and negative space balance index;

[0067] Step 4: Correct and adjust the image quality evaluation index based on the aspect ratio and shape complexity of the images in the first image set to obtain an image quality evaluation index correction value, sort the image quality evaluation index correction values according to the priority size order, and take the one with the largest image quality evaluation index correction value as the optimal selection of the user.

[0068] It should be noted that in the design of the logo, the aspect ratio, color combination, graphic elements and application scenario category can be specified according to actual needs, and the following are the recommended specific ranges. The aspect ratio of the logo can be designed according to different pattern shapes, for example, the aspect ratio of a classic rectangular pattern is set to 3:2 or 2:1. The basic colors that can be selected in the color combination include red, blue, yellow, green, black and white. It is recommended that no more than 4-5 main colors be used to maintain visual unity. The graphic elements should include geometric shapes, natural elements, abstract elements and text elements. The application scenario category is limited to a single business scenario.

[0069] It should be noted that by comprehensively applying computer vision technology, the geometric features, color characteristics and layout of the image are analyzed in depth to ensure that the generated logo has high-quality visual performance and effective information transmission. By accurately calculating the aspect ratio, shape complexity, color coordination and negative space distribution, designers can better understand user needs and optimize design solutions to improve the recognizability and appeal of advertising logos, ultimately enhancing brand communication effectiveness and market competitiveness.

[0070] Therefore, the feature parameters of the images in the first image set need to be obtained, and the method is as follows:

[0071] Edge detection and contour analysis in computer comprehensive feature extraction technology are used to detect patterns in the images in the first image set, identify the outer contour of the image, and obtain the length and width of the image. The ratio of the length to the width of the image is the aspect ratio ; the perimeter and area of the image are obtained, and the ratio of the perimeter to the area of the image is the shape complexity ;

[0072] Based on the main color extraction technology in computer comprehensive feature extraction technology, a clustering algorithm is used to extract the main color tone, obtain the main color tone of each image, and through color space conversion technology, obtain the brightness and color components of the image color. The color coordination and color focus are calculated according to the following formula:

[0073]

[0074]

[0075]

[0076]

[0077] wherein, , respectively represent the color coordination and color focus of the image, is the index of the main color tone in the image, and , the total number of dominant colors extracted in the image, 、 、 is the third component in the Lab color space of the first dominant color, 、 、 is the third component in the Lab color space of the first other color, is the index of the other color, and , is the proportion of the first dominant color in the image, is the maximum color harmony between the dominant color and the other color, is the color harmony of the first dominant color in the image;

[0078] In the above formula for calculating the color harmony of the image, the smaller the better, because the value reflects the visual difference between colors, and the smaller the visual difference means that they are more visually harmonious and unified, and these colors can better blend together to form a harmonious visual effect; in the above formula for calculating the color focus of the image, the larger the better, because the value of indicates the concentration and harmony of the dominant color in the image, and a higher means that the dominant color occupies a larger proportion in the image and has smaller differences between each other. This situation will make some colors more visually prominent, thereby attracting the attention of the audience, making the image more attractive.

[0079] Based on the layout data of the images in the first image set, using target detection and segmentation techniques in computer feature extraction technology, the image is evenly divided into grid, and then the total area and negative space area of the image are obtained to calculate the blank area ratio and negative space distribution uniformity, according to the formula:

[0080]

[0081]

[0082] wherein, , respectively represent the blank area ratio and the negative space distribution uniformity, , respectively the total area of the negative space, the total area of the image, represents the area of each grid, to divide the total number of grids, to index the number of grids, , to the area of the negative space in the first grid; in the above formula, The smaller the better, a smaller white area ratio means that the negative space in the image is relatively small compared to the total area of the image, which can make the image more compact and concise, thus reducing the visual clutter and helping the audience focus more easily on the main content or information; The larger the better, because a larger value indicates that the negative space is more evenly distributed in the image. This uniformity helps to achieve visual balance, making each part of the image look more coordinated, and uniform negative space can avoid the feeling of visual congestion, making the audience's gaze more comfortable in the entire image.

[0083] It should be noted that in advertising design, it is crucial to evaluate the quality of the advertising logo pattern, therefore, based on the calculation of relevant feature parameters such as white area ratio, color coordination, color focus, color coordination, color focus and negative space distribution uniformity, readability index, color specification index and negative space balance index can be generated, which can effectively quantify the visual effect and information transmission ability of the design work. These indexes not only help designers optimize the composition and color use of advertising logos, but also ensure their effectiveness in attracting the attention of target audiences and improving brand recognition. Through these quantitative indicators, designers can more scientifically evaluate and adjust design schemes, thus creating high-quality advertising works that meet market demand.

[0084] Therefore, it is necessary to calculate the relevant feature index for representing the quality of the advertising logo pattern according to the extracted relevant design requirement feature parameters, and the method is:

[0085] Based on the white area ratio, color coordination and color focus of the advertising logo pattern, the readability index of the advertising logo pattern is calculated, and the formula is:

[0086]

[0087] where, represents the readability index of the advertising logo pattern; in the above formula, The smaller the better, The larger the better, which means that a smaller white area ratio indicates that the negative space in the advertising logo pattern is relatively small, and the design is more compact. This situation usually makes it easier for the audience to read and understand the information in the pattern, thus improving the overall readability; increase, Increase, meaning that due to the increase in color focus, the visual difference between the text and the background becomes more obvious, and the audience can more easily distinguish the text content. Such high contrast helps to improve the readability of the information, so that the audience can quickly identify and understand the information in the advertising logo; Decrease, Increase, meaning that smaller color differences can make the overall visual experience smoother, and the audience is less likely to be distracted by the jarring color contrast when watching the advertisement. Such design is easier to guide the audience's gaze, so that it focuses on the core information of the advertisement.

[0088] Based on the color coordination and color focus of the advertising logo pattern, the color specification index of the advertising logo pattern is calculated, and the formula is:

[0089]

[0090] Among them, The color specification index of the advertising logo pattern is represented by The ideal color coordination, The ideal color focus; in the above formula, Decrease, Increase, meaning that the colors in the advertising logo become more consistent and unified, and such color consistency helps to improve the visual harmony, so that the advertising logo conveys a professional and reliable image to the audience; Increase, Increase, meaning that the color contrast in the advertising logo is enhanced, and the audience can more clearly distinguish the text and patterns, and the information in the advertising logo is more explicit, reducing the visual blur. Such clarity improves the audience's ability to grasp the core information of the advertisement in a short time, enhancing the efficiency of information transmission.

[0091] Based on the blank area ratio and negative space distribution uniformity of the advertising logo pattern, the negative space balance index of the advertising logo pattern is calculated, and the formula is:

[0092]

[0093] Among them, The negative space balance index of the advertising logo pattern is represented by The greater, The greater, the greater The value indicates that the distribution of negative space is more uniform, so that the advertising logo has more space in the visual sense. Such space helps to avoid visual congestion and clutter, thereby improving the overall design aesthetics and enhancing the audience's visual experience; Decrease, Increasing means that the proportion of white space or negative space in the design is relatively reduced, and in the case of negative space reduction, the main graphics and text can be better highlighted.

[0094] It should be noted that the image quality evaluation index combines the readability index, color specification index and negative space balance index to provide a comprehensive quality evaluation tool for advertising design. By integrating these three key factors, designers can optimize the advertising logo, improve the clarity and visual appeal of information transmission, enhance user experience, and thus improve brand awareness and influence in the competitive market.

[0095] Therefore, it is necessary to generate an image quality evaluation index by comprehensively combining the readability index, color specification index and negative space balance index, and the formula is as follows:

[0096]

[0097] wherein, represents the image quality evaluation index; in the above formula, The larger the better, The larger the value of indicates a higher readability index , making it easier for the audience to understand the information, and also indicating that the color specification index is better, enhancing the visual appeal, while the optimization of the negative space balance index makes the design more balanced and harmonious, which comprehensively reflects the professionalism and appeal of image design, helping to improve brand image and advertising effect.

[0098] It should be noted that different style requirements of users for logo patterns include two types of simple fashion and gorgeous splendor. Different style requirements will result in different image quality evaluation indexes, that is, different characteristic parameters as design parameters, so it is necessary to correct the image quality evaluation index according to the style requirements of the user. This process not only optimizes the design to meet the specific needs of the user and improve user satisfaction, but also enhances the visual appeal and information transmission effect of the image. Through data-driven correction calculation, design decisions become more scientific and systematic, reducing subjective bias. In addition, according to the priority ranking of the corrected image quality evaluation index, it is helpful to quickly identify the optimal choice, improve work efficiency, and ensure the consistency of brand visual expression, thereby improving brand recognition and market competitiveness.

[0099] Therefore, the image quality evaluation index needs to be adjusted based on the aspect ratio and shape complexity of the images in the first image set to obtain a corrected image quality evaluation index value. These values ​​are then sorted according to priority, with the image with the largest corrected value being the user's optimal choice. The method used is as follows:

[0100] The image quality evaluation index is adjusted based on users' different style requirements for the logo pattern and the aspect ratio and shape complexity of the images in the first image set. The formula used is as follows:

[0101]

[0102] in, This represents the correction value for the image quality evaluation index. Let the shape complexity of the images in the first image set be denoted as . The aspect ratio of the images in the first image set. For the ideal aspect ratio;

[0103] Based on the shape complexity of the style required by the user, the image quality evaluation index correction values ​​are prioritized and sorted to obtain the user's optimal choice. The feature parameters of the first image set corresponding to the optimal choice are then used as the design parameters for the advertising logo.

[0104] In the above modified formula, the modified calculation logic is as follows: This is the absolute difference between the actual aspect ratio and the ideal aspect ratio. The smaller this difference, the closer the image's aspect ratio is to the user's needs; conversely, the larger the difference, the greater the deviation. This factor acts as a "penalty" in the formula, preventing images with excessively large aspect ratio deviations from receiving excessively high quality evaluation indices. Shape complexity... This reflects the complexity of the image design; more complex images tend to be more appealing. The value will be larger, while for simple images, The value will be too small, and the shape complexity plays a positive role in correcting the quality of the corrected image.

[0105] Based on the shape complexity of the desired style, the image quality evaluation index correction values ​​are prioritized and sorted to obtain the user's optimal choice. The feature parameters of the images in the first image set corresponding to the optimal choice are then used as the design parameters for the advertising logo. If the user's desired style is a fashionable and minimalist style, then the first image set... Arrange them in ascending order, and select the smallest one. As the optimal choice; if the user's desired style is gorgeous and dazzling, then the first image set will be selected. Arrange them in descending order, and select the largest one. As the best choice.

[0106] Please refer to Figure 2 The application further provides an advertisement logo pattern generation device for executing the above-mentioned advertisement logo pattern generation method, comprising:

[0107] A design requirement analysis module is configured to acquire design requirement data of a user, the design requirement data comprising an aspect ratio, color combination, graphic element and application scenario category of a logo pattern, filter a plurality of images from an image library that meet the design requirement data to obtain a first image set;

[0108] A feature extraction generation module is configured to acquire feature parameters of images in the first image set, the feature parameters comprising an aspect ratio, shape complexity, color coordination, color focus, blank area ratio and negative space distribution uniformity of the images;

[0109] An image quality evaluation index calculation module is configured to calculate relevant feature indexes for representing image quality according to the extracted feature parameters, the feature indexes comprising a readability index, a color specification index and a negative space balance index, and to generate an image quality evaluation index by comprehensively using the readability index, the color specification index and the negative space balance index;

[0110] A calibration correction and optimal pattern selection module is configured to correct and adjust the image quality evaluation index based on the aspect ratio and shape complexity of the images in the first image set to obtain an image quality evaluation index correction value, sort the image quality evaluation index correction values according to priority size order, and select the image with the largest image quality evaluation index correction value as the optimal choice of the user.

[0111] The application further provides an electronic device comprising:

[0112] a processor; and a memory connected to the processor in communication; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor to cause the processor to execute the above-mentioned advertisement logo pattern generation method.

[0113] The application further provides a non-transient computer readable storage medium storing computer instructions for causing a computer to execute the above-mentioned advertisement logo pattern generation method.

[0114] The above-mentioned formulas are dimensionless numerical calculations, the formulas are obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0115] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art can be aware that units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and design constraints of the technical solutions.

[0116] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, and can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0117] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. An advertisement sign pattern generation method characterized by comprising: The specific steps include: Step 1: Obtain the design requirement data of the user, the design requirement data including the aspect ratio of the identification pattern, color combination, graphic element and application scene category, screen multiple images meeting the design requirement data from the image library to obtain a first image set; Step 2: Obtain the feature parameters of the images in the first image set, the feature parameters including the aspect ratio of the image, shape complexity, color coordination degree, color focusing degree, blank area ratio and negative space distribution uniformity; Step 3: Calculate the related feature indexes for representing the image quality according to the extracted feature parameters, the feature indexes including readability index, color specification index and negative space balance index, and comprehensively generate the image quality evaluation index by using the readability index, color specification index and negative space balance index; Step 4: Correct and adjust the image quality evaluation index based on the aspect ratio and shape complexity of the images in the first image set to obtain the image quality evaluation index correction value, sort the image quality evaluation index correction value according to the priority size order, and take the maximum image quality evaluation index correction value as the optimal selection of the user; The method for obtaining the feature parameters of the images in the first image set is as follows: The edge detection and contour analysis in the computer integrated feature extraction technology are used to detect the pattern of the images in the first image set, identify the outer contour of the images, obtain the length and width of the images, and the ratio of the length and width of the images is the length-width ratio ; the perimeter and area of the images are obtained, and the ratio of the perimeter and area of the images is the shape complexity ; Based on the main color extraction technology in computer comprehensive feature extraction technology, the main color tone is extracted by using clustering algorithm, the main color tone of each image is obtained, and the brightness and color component of the image color are obtained by color space conversion technology, and the color coordination degree and color focusing degree are calculated, the formula is as follows: ； ； ； ； wherein, , respectively represent the color harmony and the color focus of the image, is an index of the dominant color tone in the image, and , is the total number of dominant color tones extracted in the image, , , is the three components in the Lab color space of the first dominant color tone, , , is the three components in the Lab color space of the first other color, is an index of the other color, and , is the proportion of the first dominant color tone in the image, is the maximum color harmony between the dominant color tone and the other color, is the color harmony of the first dominant color tone in the image; Based on the layout data of the images in the first image set, the images are evenly divided into grid cells by using target detection and segmentation techniques in computerized feature extraction technology, and then the total area and the negative space area of the images are obtained to calculate the blank area ratio and the negative space distribution uniformity, according to the formula: ； ； in, , These represent the ratio of blank area and the uniformity of negative spatial distribution, respectively. , These represent the total area of ​​the negative space and the total area of ​​the image, respectively. This represents the area of ​​each grid cell. The total number of grids, The index of the number of grid cells. , For the first The area of ​​the negative space in each grid; The related feature indexes for representing the quality of the advertisement identification pattern are calculated according to the extracted feature parameters of the related design requirements, and the method is as follows: The readability index of the advertisement identification pattern is calculated based on the blank area ratio, color coordination degree and color focusing degree of the advertisement identification pattern, and the formula is as follows: ； wherein, represents the legibility index of the advertising logo pattern; The color specification index of the advertisement identification pattern is calculated based on the color coordination degree and color focusing degree of the advertisement identification pattern, and the formula is as follows: ； wherein, represents a color specification index of the advertising identification pattern, is an ideal color harmony degree, is an ideal color focus degree; The negative space balance index of the advertisement identification pattern is calculated based on the blank area ratio and negative space distribution uniformity of the advertisement identification pattern, and the formula is as follows: ； wherein, represents the negative space balance index of the advertising identification pattern.

2. The method of claim 1, wherein The image quality evaluation index is comprehensively generated by using the readability index, color specification index and negative space balance index, and the formula is as follows: ； wherein denotes the image quality evaluation index.

3. The method of claim 2, wherein The image quality evaluation index is corrected and adjusted based on the aspect ratio and shape complexity of the images in the first image set to obtain the image quality evaluation index correction value, and the image quality evaluation index correction value is sorted according to the priority size order, and the maximum image quality evaluation index correction value is taken as the optimal selection of the user, and the method is as follows: The image quality evaluation index is corrected according to the different style requirements of the user for the identification pattern and combined with the aspect ratio and shape complexity of the images in the first image set, and the formula is as follows: ； wherein, denotes an image quality evaluation index correction value, is a shape complexity of the image in the first image set, is an aspect ratio of the image in the first image set, is an ideal aspect ratio; The priority size of the image quality evaluation index correction value is sorted according to the shape complexity of the required style of the user to obtain the optimal selection of the user, and the feature parameters of the first image set corresponding to the optimal selection are taken as the design parameters of the advertisement identification pattern for design.

4. An advertisement mark pattern generating apparatus characterized by comprising: The pattern generation device is used to execute the advertisement identification pattern generation method of any one of claims 1-3, comprising: a design requirement analysis module, the design requirement analysis module is used for obtaining the design requirement data of the user, the design requirement data includes the aspect ratio, color combination, graphic element and application scene category of the identification pattern, a plurality of images meeting the design requirement data are screened from the image library, and a first image set is obtained; a feature extraction generation module, the feature extraction generation module is used for obtaining the feature parameters of the images in the first image set, the feature parameters include the aspect ratio, shape complexity, color coordination, color focusing degree, blank area ratio and negative space distribution uniformity of the images; an image quality evaluation index calculation module, the image quality evaluation index calculation module is used for calculating the related feature indexes for representing the image quality according to the extracted feature parameters, the feature indexes include the readability index, color specification index and negative space balance index, and the image quality evaluation index is generated by comprehensively using the readability index, color specification index and negative space balance index; a calibration correction and optimal pattern selection module, the calibration correction and optimal pattern selection module corrects and adjusts the image quality evaluation index based on the aspect ratio and shape complexity of the images in the first image set, to obtain an image quality evaluation index correction value, the image quality evaluation index correction value is sorted according to the priority size order, and the image with the largest image quality evaluation index correction value is taken as the optimal selection of the user.

5. An electronic device, comprising: comprise: a processor; and a memory connected in communication with the processor; wherein the memory stores instructions executable by the processor, the instructions executed by the processor to cause the processor to execute the advertisement identification pattern generation method of any one of claims 1-3.

6. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer execute the advertisement identification pattern generation method of any one of claims 1-3.

Images