CN116090163A - A method of color selection for mosaic tiles and related equipment - Google Patents

Abstract

The invention discloses a mosaic tile color selection method and related equipment. The method includes: establishing a set coverage model, forming a set of colors of existing tiles and colors in a first color space image and a second color space image, and ensuring that the colors in the first and second color space images are covered by at least any subset of the set; calculating the average distance between the colors in the first and second color space images and existing tile colors, Get the first part to increase the color; establish a cluster analysis model, divide the colors in the second color space image into classes, and calculate the membership matrix and cluster center of the second color space image; combine the second color space image with the clustering The color with the closest Euclidean distance between the cluster centers is assigned to one category, and the center point of each category is a new cluster center, and the second part of the added color is obtained. According to the original image provided by the user, the present invention obtains the tile color closest to the color produced by the manufacturer.

Description

Mosaic tile color selection method and related equipment

Technical Field

The present invention relates to the technical field of image processing, and in particular to a mosaic tile color selection method, system, terminal and computer-readable storage medium.

Background Art

Mosaic is one of the oldest known decorative arts. With the development of modern science and technology, mosaic tiles that make full use of computer technology and image processing technology have become one of the hottest choices for laying home walls and floor tiles. In terms of appearance, mosaic tiles are small and exquisite, rich in color, and a wide variety of types. They can be matched at will to form countless beautiful patterns; in terms of performance, it has strong waterproof performance, stable chemical properties, high temperature resistance, no heat absorption, radiation protection, and good decorative effect. Therefore, it is widely used in science and technology museums, cinemas, clubs and other places.

However, the color of mosaic tiles is restricted by craftsmanship and cost, and it is almost impossible to make it completely consistent with the color in the picture provided by the user. The user can only select tiles with the closest color to the original picture within a certain range for splicing. This greatly increases the customer's workload and often makes it difficult for the customer to choose the color.

There is a mosaic tile manufacturer that can produce 22 colors of mosaic tiles. In order to reduce the workload of customers' manual color selection, it is necessary to study a mosaic tile color selection method that can automatically match the tile color that is closest to the color that the manufacturer can produce based on the original image color. Color is an important visual property of an image. For image color, the color mode is an existing universal color standard, representing red, green, and blue respectively. In the format, a total of 16777216 different colors can be generated by matching these three colors. The method required by the manufacturer is to be able to output the tile color number that is closest to any of the 22 colors produced by the manufacturer.

Therefore, the prior art still needs to be improved and developed.

Summary of the invention

The main purpose of the present invention is to provide a mosaic tile color selection method, system, terminal and computer-readable storage medium, aiming to solve the problem in the prior art that it is impossible to automatically match the tile color that is closest to the original picture color among the colors that can be produced by the manufacturer.

To achieve the above object, the present invention provides a mosaic tile color selection method, the mosaic tile color selection method comprising the following steps:

Establishing a set coverage model, forming a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set;

In the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting them according to the average distances;

Establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining cluster centers;

The colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one category, and the center point of each category is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

Optionally, the mosaic tile color selection method, wherein a set coverage model is established, the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image form a set, and it is ensured that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set;

The establishing of the set coverage model, forming a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, specifically includes:

其中x_j为决策变量，T_j为集合T中的任一种颜色，C_n为集合C中的覆盖子集，otherwise代表不在集合C覆盖范围内；The colors in the first color space distribution image and the second color space distribution image form a set T, which has 416 colors in total. The colors of the existing tiles and the colors in set T form a set C, and the decision variables are introduced:

Where _xj is a decision variable, _Tj is any color in set T, _Cn is a covering subset in set C, and otherwise represents a color not in the coverage of set C;

x_j＝0，j＝1，2，...，416，其中约束条件用于确保集合T中的每一元素T_j都被集合C的至少任一子集C_n覆盖住。Build a collection coverage model:

x _j =0, j=1, 2, . . . , 416, where the constraint is used to ensure that every element T _j in the set T is covered by at least any subset C _n of the set C.

The method of establishing a set coverage model, combining the colors of the existing tiles with the colors in the first color space distribution image and the second color space distribution image to form a set, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, further includes:

The RGB values of the colors in the first color space distribution image and the second color space distribution image and the colors of the existing tiles are converted into HSV values.

Optionally, in the mosaic tile color selection method, in the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors are sorted according to the average distance to obtain the first part of tile colors that need to be added;

In the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting according to the average distance, specifically including:

其中，d_jn表示第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色与已有瓷砖颜色之间的欧氏距离；Calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, d _jn represents the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color;

The multiple average distances are sorted from large to small, and corresponding colors are obtained according to the positions of the multiple average distances in the color space, and colors are selected therefrom to fill the blanks of the existing tile colors, so as to obtain the first part of tile colors that need to be added.

The step of calculating the average distance between each color in the first color space distribution image and the second color space distribution image and the color of the existing tiles specifically includes:

其中，h_j，s_j，v_j分别为HSV色彩空间中所述第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色的坐标值，h_n，s_n，v_n分别为HSV色彩空间中所述已有瓷砖颜色的坐标值；Get the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, _hj , _sj , _vj are respectively the coordinate values of each color in the first color space distribution image and the second color space distribution image in the HSV color space, and _hn , _sn , _vn are respectively the coordinate values of the existing tile colors in the HSV color space;

The average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color is obtained.

Optionally, a cluster analysis model is established to divide the colors in the second color space distribution image into classes, and a membership matrix of the second color space distribution image is calculated by a fuzzy clustering method to obtain cluster centers;

The step of establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining cluster centers specifically includes:

其中，目标函数J(U，C)表示所述第二色彩空间分布图像中的颜色所对应的坐标到每个聚类中心距离的加权平方和，隶属度矩阵U＝[u_jn]表示所述第二色彩空间分布图像中的颜色属于每个类的程度大小，M是所述第二色彩空间分布图像中的颜色的个数，N是聚类中心个数，f是加权指数，dist(c_n，k_j)是指所述第二色彩空间分布图像中的颜色与每个聚类中心的距离，c_n是聚类中心对应的坐标，k_j是所述第二色彩空间分布图像中的颜色对应的坐标；A cluster analysis model is established to divide the colors in the second color space distribution image into classes, and the objective function of fuzzy clustering is obtained:

Wherein, the objective function J(U, C) represents the weighted sum of squares of the distances from the coordinates corresponding to the colors in the second color space distribution image to each cluster center, the membership matrix U=[u _jn ] represents the degree to which the colors in the second color space distribution image belong to each class, M is the number of colors in the second color space distribution image, N is the number of cluster centers, f is a weighted index, dist(c _n , k _j ) refers to the distances from the colors in the second color space distribution image to each cluster center, c _n is the coordinates corresponding to the cluster center, and k _j is the coordinates corresponding to the colors in the second color space distribution image;

其中，m是所述第二色彩空间分布图像中的颜色对应的个数，dist² _nj是指所述第二色彩空间分布图像中的颜色所对应的坐标与每个聚类中心的距离的平方；After obtaining the objective function of fuzzy clustering, the Lagrange method is used to obtain the membership matrix u _jn ,

Wherein, m is the number of colors in the second color space distribution image, and dist ² _nj refers to the square of the distance between the coordinates corresponding to the colors in the second color space distribution image and each cluster center;

其中，u_nj＝1/u_jn。Obtain the cluster center _En :

Among them, u _nj =1/u _jn .

Optionally, the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one category, and the center point of each category is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added;

The step of classifying the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculating the center point of each category to obtain a new cluster center, wherein the color corresponding to the new cluster center is the second part of tile colors that need to be added, specifically includes:

Calculating the Euclidean distance between the colors in the second color space distribution image and the cluster center, obtaining N distances for each color in the second color space distribution image, and classifying the colors in the second color space distribution image that have the closest Euclidean distance to the cluster center into one category;

The center point of each class is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

In addition, to achieve the above-mentioned purpose, the present invention also provides a mosaic tile color selection system, wherein the mosaic tile color selection system comprises:

A color set module, used to establish a set coverage model, to form a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and to ensure that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set;

A first color selection module is used to calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors in the set coverage model, and sort them according to the average distance to obtain the first part of tile colors that need to be added;

A cluster analysis module, used to classify the colors in the second color space distribution image into classes, calculate the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtain cluster centers;

The second color selection module is used to classify the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculate the center point of each category to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a mosaic tile color selection program stored in the memory and executable on the processor, wherein the mosaic tile color selection program, when executed by the processor, implements the steps of a mosaic tile color selection method as described above.

In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for mosaic tile color selection, and when the program for mosaic tile color selection is executed by a processor, the steps of a mosaic tile color selection method as described above are implemented.

In the present invention, a set coverage model is established, and the colors of existing tiles and the colors in the first color space distribution image and the second color space distribution image form a set, and it is ensured that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set; in the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors are sorted according to the average distance to obtain the first part of tile colors that need to be added; a cluster analysis model is established, and the colors in the second color space distribution image are divided into classes, and the membership matrix of the second color space distribution image is calculated by the fuzzy clustering method to obtain the cluster center; the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one class, and the center point of each class is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the second part of tile colors that need to be added. The present invention converts the RGB values of the colors in the first color space image, the second color space image and the existing tiles into HSV values. On the one hand, by calculating the distance between the corresponding positions of the colors of the first color space image and the second color space image in the color space and the corresponding positions of the colors of the existing tiles in the color space, a color close to the existing tile color is obtained. On the other hand, by finding the color corresponding to the cluster center position in the second color space image, the diversity of tile colors and the expressiveness of the spliced image are increased, while also meeting the customer's demand for color.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a preferred embodiment of a mosaic tile color selection method of the present invention;

FIG2 is a first color space distribution diagram of the mosaic tile color selection method of the present invention;

FIG3 is a second color space distribution diagram of the mosaic tile color selection method of the present invention;

FIG4 is a schematic diagram of the RGB color adjustment principle of the mosaic tile color selection method of the present invention;

FIG5 is a schematic diagram of the principle of a preferred embodiment of a system for selecting color of mosaic tiles of the present invention;

FIG. 6 is a schematic diagram of an operating environment of a preferred embodiment of a terminal of the present invention.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

A mosaic tile color selection method according to a preferred embodiment of the present invention, as shown in FIG1 , comprises the following steps:

Step S10, establish a set coverage model, form a set with the colors of existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensure that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set.

2 and 3 respectively give 216 and 200 colors and RGB values corresponding to the first color space distribution image and the second color space distribution image. It can be seen that the color distribution in FIG2 is relatively uniform, and is composed of a fixed combination of 6 values for R, G, and B, respectively. It is regular and equally spaced data, wherein R takes 6 values of 0, 43, 86, 129, 172, and 215; G takes 6 values of 20, 63, 106, 149, 192, and 235; and B takes 6 values of 39, 82, 125, 168, 211, and 254.

The color distribution in Figure 3 is relatively more random, and the overall color changes as the coordinate value in the spatial color system increases. At this time, the R, G, and B values are not fixed, so the color changes are more complicated than in Figure 2. It can be seen that the color corresponding to image 3 appears more frequently in some segments of color, and less frequently in some segments of color.

The RGB values of the colors in the first color space distribution image and the second color space distribution image and the colors of the existing tiles are converted into HSV values.

Among them, finding the tile color that is closest to the 22 colors produced by existing manufacturers is essentially to calculate the similarity between two colors.

In the RGB color space, the value range of R, G, and B is [0, 255]. In the HSV color space, the value range of H is [0°, 360°], the value range of S is [0, 1], and the value range of V is [0, 255], where H represents hue, S represents saturation, and V represents brightness.

The reason why the RGB value of the color is converted into the HSV value is that the boundaries between R, G, and B in the RGB format are not very clear. When using RGB to calculate color difference, there is an overlap problem, which is easily affected by factors such as lighting and difficult to accurately segment. HSV, on the other hand, is not affected by lighting. This problem is avoided by adjusting the hue H, saturation S, and brightness V to describe the color. HSV can be regarded as a three-dimensional space coordinate system. The color type is determined by measuring the distance between the coordinate points corresponding to different colors in space and calculating the Euclidean distance.

其中x_j为决策变量，T_j为集合T中的任一种颜色，C_n为集合C中的覆盖子集，otherwise代表不在集合C覆盖范围内，1代表“是”，0代表“不是”。Specifically, the colors in the first color space distribution image and the second color space distribution image form a set T, which has 416 colors in total. The colors of the existing tiles and the colors in set T form a set C, and the decision variables are introduced:

Where _xj is the decision variable, _Tj is any color in set T, _Cn is the covering subset in set C, otherwise means it is not within the coverage of set C, 1 represents “yes” and 0 represents “no”.

x_j＝0，j＝1，2，...，416，其中约束条件

用于确保集合T中的每一元素T_j都被集合C的至少任一子集C_n覆盖住。Build a collection coverage model:

x _j = 0, j = 1, 2, ..., 416, where the constraints

Used to ensure that every element _Tj in the set T is covered by at least any subset _Cn of the set C.

Among them, the set coverage model can cover all color types in the first color space and the second color space through the newly added tile colors and the existing tile colors. The modeling method is simple, easy to understand, and clear.

Step S20: In the set coverage model, calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors, sort them according to the average distance, and obtain the first part of tile colors that need to be added.

其中，h_j，s_j，v_j分别为HSV色彩空间中所述第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色的坐标值，h_n，s_n，v_n分别为HSV色彩空间中所述已有瓷砖颜色的坐标值。Specifically, the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color is obtained:

Wherein, _hj , _sj , and _vj are respectively the coordinate values of each color in the first color space distribution image and the second color space distribution image in the HSV color space, and _hn , _sn , and _vn are respectively the coordinate values of the existing tile colors in the HSV color space.

Among them, Euclidean distance is a commonly used distance definition, which is the true distance between two points in n-dimensional space.

其中，d_jn表示第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色与已有瓷砖颜色之间的欧氏距离。Calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, d _jn represents the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color.

The multiple average distances are sorted from large to small, and corresponding colors are obtained according to the positions of the multiple average distances in the color space, and colors are selected therefrom to fill the blanks of the existing tile colors, so as to obtain the first part of tile colors that need to be added.

Step S30: Establish a cluster analysis model, divide the colors in the second color space distribution image into classes, calculate the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtain the cluster center.

Among them, before establishing the cluster analysis model, a fuzzy set will be established first. According to the RGB color matching principle, in addition to the three primary colors of red R, green G, and blue B, there are also yellow Y mixed from red R and green G, magenta M mixed from red R and blue B, cyan C mixed from green G and blue B, white W mixed from red R, green G, and blue B, and black without any of the three primary colors, as shown in Figure 4.

Fuzzy sets can be established based on the several types of colors in Figure 4. If there is a number U(k)∈[0,1] corresponding to any element k in the color domain Y, then U is called a fuzzy set on Y, and U _k is called the membership of k to Y. When k changes in Y, U(K) is a function, called the membership function of U. The closer the membership U(K) is to 1, the higher the degree to which k belongs to Y; the closer U(k) is to 0, the lower the degree to which k belongs to Y.

其中，目标函数J(U，C)表示所述第二色彩空间分布图像中的颜色所对应的坐标到每个聚类中心距离的加权平方和，隶属度矩阵U＝[u_jn]表示所述第二色彩空间分布图像中的颜色属于每个类的程度大小，M是所述第二色彩空间分布图像中的颜色的个数，N是聚类中心个数，f是加权指数，dist(c_n，k_j)是指所述第二色彩空间分布图像中的颜色与每个聚类中心的距离，c_n是聚类中心对应的坐标，k_j是所述第二色彩空间分布图像中的颜色对应的坐标。Specifically, a cluster analysis model is established to divide the colors in the second color space distribution image into classes, and the objective function of fuzzy clustering is obtained:

Among them, the objective function J(U, C) represents the weighted square sum of the distances from the coordinates corresponding to the colors in the second color space distribution image to each cluster center, the membership matrix U=[u _jn ] represents the degree to which the colors in the second color space distribution image belong to each class, M is the number of colors in the second color space distribution image, N is the number of cluster centers, f is the weighted index, dist(c _n , k _j ) refers to the distance between the colors in the second color space distribution image and each cluster center, c _n is the coordinate corresponding to the cluster center, and k _j is the coordinate corresponding to the color in the second color space distribution image.

Among them, the clustering analysis model is the FCM model. FCM is an excellent clustering analysis algorithm and a partition-based clustering algorithm. Its idea is to maximize the similarity between objects divided into the same cluster and minimize the similarity between different clusters.

上述问题可转变为求

建立的FCM模型会计算每个点对所有类的隶属度，结果的可靠度较高。In addition to calculating the cluster center, fuzzy clustering does not directly classify data points into a certain category, but calculates the membership matrix.

The above question can be transformed into

The established FCM model calculates the membership of each point to all classes, and the reliability of the result is high.

Then, the Lagrange method is used to obtain the membership matrix u _jn ,

其中，m是所述第二色彩空间分布图像中的颜色对应的个数，dist² _nj是指所述第二色彩空间分布图像中的颜色所对应的坐标与每个聚类中心的距离的平方。

Wherein, m is the number of colors in the second color space distribution image, and dist ² _nj refers to the square of the distance between the coordinates corresponding to the colors in the second color space distribution image and each cluster center.

其中，u_nj＝1/u_jn。Obtain the cluster center _En :

Among them, u _nj =1/u _jn .

Among them, it can be found that the membership matrix U and the cluster center C are interrelated and contain each other. The continuous iteration and update of U and C move in the direction of continuously decreasing the objective function J(U, C), and finally reach a stable state. The values of U and C in this state are the final membership matrix and cluster center.

Step S40, classify the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculate the center point of each category to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

Specifically, the Euclidean distance between the colors in the second color space distribution image and the cluster center is calculated, each color in the second color space distribution image obtains N distances, and the colors in the second color space distribution image with the closest Euclidean distance to the cluster center are classified into one category.

The center point of each class is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

The total color obtained by the first part of the tile color and the second part of the tile color is the color that needs to be added in the present invention.

In addition, based on the present invention, it can be known that each color has a certain coverage range. As long as the color of the original image is within this coverage range, tiles of that color can be selected, and with each additional color, the color coverage rate is higher. Therefore, an evaluation index system can be established to evaluate which colors have a higher utilization rate, and the image performance effect can be enhanced by improving the utilization rate.

Furthermore, the RGB color space in the present invention can also be converted into the LAB color space to calculate the Euclidean distance between two color points.

In addition, the set covering model used in the present invention can not only be used to solve the present invention, but also has many applications in real production problems such as logistics distribution, facility site selection, road orientation, etc.; a fuzzy clustering algorithm in the present invention is also widely used in data classification processing, image segmentation, pattern recognition and data mining.

Further, as shown in FIG5 , based on the above-mentioned mosaic tile color selection method, the present invention also provides a mosaic tile color selection system accordingly, wherein the mosaic tile color selection system comprises:

The color set module 51 is used to establish a set coverage model, which forms a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensures that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set.

The first color selection module 52 is used to calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors in the set coverage model, and sort them according to the average distance to obtain the first part of tile colors that need to be added.

The cluster analysis module 53 is used to classify the colors in the second color space distribution image into classes, calculate the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtain cluster centers.

The second color selection module 54 is used to classify the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculate the center point of each category to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

Further, as shown in Fig. 6, based on the above-mentioned mosaic tile color selection method and system, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Fig. 6 only shows some components of the terminal, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead.

In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a mosaic tile color selection program 40 is stored on the memory 20, and the mosaic tile color selection program 40 can be executed by the processor 10, thereby realizing a mosaic tile color selection method in the present invention.

In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the mosaic tile color selection method.

In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

In one embodiment, when the processor 10 executes the mosaic tile color selection program 40 in the memory 20, the following steps are implemented:

Establishing a set coverage model, forming a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set;

In the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting them according to the average distances;

Establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining cluster centers;

The colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one category, and the center point of each category is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

The establishing of the set coverage model comprises forming a set of the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, specifically including:

其中x_j为决策变量，T_j为集合T中的任一种颜色，C_n为集合C中的覆盖子集，otherwise代表不在集合C覆盖范围内；The colors in the first color space distribution image and the second color space distribution image form a set T, which has 416 colors in total. The colors of the existing tiles and the colors in set T form a set C, and the decision variables are introduced:

Where _xj is a decision variable, _Tj is any color in set T, _Cn is a covering subset in set C, and otherwise represents a color not in the coverage of set C;

x_j＝0，j＝1，2，...，416，其中约束条件

用于确保集合T中的每一元素T_j都被集合C的至少任一子集C_n覆盖住。Build a collection coverage model:

x _j = 0, j = 1, 2, ..., 416, where the constraints

Used to ensure that every element _Tj in the set T is covered by at least any subset _Cn of the set C.

Wherein, in the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting according to the average distance, specifically including:

其中，d_jn表示第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色与已有瓷砖颜色之间的欧氏距离；Calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, d _jn represents the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color;

The multiple average distances are sorted from large to small, and corresponding colors are obtained according to the positions of the multiple average distances in the color space, and colors are selected therefrom to fill the blanks of the existing tile colors, so as to obtain the first part of tile colors that need to be added.

The step of calculating the average distance between each color in the first color space distribution image and the second color space distribution image and the color of the existing tiles specifically includes:

其中，h_j，s_j，v_j分别为HSV色彩空间中所述第一色彩空间分布图像和第二色彩空间分布图像中每一种颜色的坐标值，h_n，s_n，v_n分别为HSV色彩空间中所述已有瓷砖颜色的坐标值；Get the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, _hj , _sj , _vj are respectively the coordinate values of each color in the first color space distribution image and the second color space distribution image in the HSV color space, and _hn , _sn , _vn are respectively the coordinate values of the existing tile colors in the HSV color space;

The average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color is obtained.

The step of establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining cluster centers specifically includes:

其中，目标函数J(U，C)表示所述第二色彩空间分布图像中的颜色所对应的坐标到每个聚类中心距离的加权平方和，隶属度矩阵U＝[u_jn]表示所述第二色彩空间分布图像中的颜色属于每个类的程度大小，M是所述第二色彩空间分布图像中的颜色的个数，N是聚类中心个数，f是加权指数，dist(c_n，k_j)是指所述第二色彩空间分布图像中的颜色与每个聚类中心的距离，c_n是聚类中心对应的坐标，k_j是所述第二色彩空间分布图像中的颜色对应的坐标；A cluster analysis model is established to divide the colors in the second color space distribution image into classes, and the objective function of fuzzy clustering is obtained:

Wherein, the objective function J(U, C) represents the weighted sum of squares of the distances from the coordinates corresponding to the colors in the second color space distribution image to each cluster center, the membership matrix U=[u _jn ] represents the degree to which the colors in the second color space distribution image belong to each class, M is the number of colors in the second color space distribution image, N is the number of cluster centers, f is a weighted index, dist(c _n , k _j ) refers to the distances from the colors in the second color space distribution image to each cluster center, c _n is the coordinates corresponding to the cluster center, and k _j is the coordinates corresponding to the colors in the second color space distribution image;

其中，m是所述第二色彩空间分布图像中的颜色对应的个数，dist² _nj是指所述第二色彩空间分布图像中的颜色所对应的坐标与每个聚类中心的距离的平方；After obtaining the objective function of fuzzy clustering, the Lagrange method is used to obtain the membership matrix u _jn ,

Wherein, m is the number of colors in the second color space distribution image, and dist ² _nj refers to the square of the distance between the coordinates corresponding to the colors in the second color space distribution image and each cluster center;

其中，u_nj＝1/u_jn。Obtain the cluster center _En :

Among them, u _nj =1/u _jn .

The method of classifying the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculating the center point of each category to obtain a new cluster center, wherein the color corresponding to the new cluster center is the second part of tile colors that need to be added, specifically includes:

Calculating the Euclidean distance between the colors in the second color space distribution image and the cluster center, obtaining N distances for each color in the second color space distribution image, and classifying the colors in the second color space distribution image that have the closest Euclidean distance to the cluster center into one category;

The center point of each class is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added.

The method of establishing a set coverage model comprises forming a set of colors of existing tiles and colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, and also comprises:

The RGB values of the colors in the first color space distribution image and the second color space distribution image and the colors of the existing tiles are converted into HSV values.

The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for selecting colors of mosaic tiles, and when the program for selecting colors of mosaic tiles is executed by a processor, the steps of the method for selecting colors of mosaic tiles as described above are implemented.

In summary, the present invention provides a mosaic tile color selection method and related equipment, the method comprising: establishing a set coverage model, forming a set of colors of existing tiles and colors in a first color space distribution image and a second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set; in the set coverage model, calculating the average distance between each color in the first color space distribution image and the second color space distribution image and the color of the existing tiles, sorting according to the average distance, and obtaining the first part of tile colors that need to be added; establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining the cluster center; classifying the colors in the second color space distribution image that are closest to the cluster center in the Euclidean distance, and calculating the center point of each class to obtain a new cluster center, and the color corresponding to the new cluster center is the second part of tile colors that need to be added. The present invention converts the RGB values of the colors in the first color space image, the second color space image and the existing tiles into HSV values. On the one hand, by calculating the distance between the corresponding positions of the colors of the first color space image and the second color space image in the color space and the corresponding positions of the colors of the existing tiles in the color space, a color close to the existing tile color is obtained. On the other hand, by finding the color corresponding to the cluster center position in the second color space image, the diversity of tile colors and the expressiveness of the spliced image are increased, while also meeting the customer's demand for color.

It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims (10)

1. A mosaic tile color selection method, characterized in that the mosaic tile color selection method comprises: Establishing a set coverage model, forming a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set; In the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting them according to the average distances; Establishing a cluster analysis model, dividing the colors in the second color space distribution image into classes, calculating the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtaining cluster centers; The colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one category, and the center point of each category is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added. 2. The mosaic tile color selection method according to claim 1 is characterized in that the establishment of the set coverage model, the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image constitute a set, and ensure that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, specifically includes: The colors in the first color space distribution image and the second color space distribution image form a set T, which has 416 colors in total. The colors of the existing tiles and the colors in set T form a set C, and the decision variables are introduced:

Where _xj is a decision variable, _Tj is any color in set T, _Cn is a covering subset in set C, and otherwise represents a color not in the coverage of set C; Build a collection coverage model:

x _j = 0, j = 1, 2, ..., 416, where the constraints

Used to ensure that every element _Tj in the set T is covered by at least any subset _Cn of the set C. 3. The mosaic tile color selection method according to claim 1, characterized in that, in the set coverage model, the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors is calculated, and the colors of the first part of tiles to be added are obtained by sorting according to the average distance, specifically comprising: Calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, d _jn represents the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color; The multiple average distances are sorted from large to small, and corresponding colors are obtained according to the positions of the multiple average distances in the color space, and colors are selected therefrom to fill the blanks of the existing tile colors, so as to obtain the first part of tile colors that need to be added. 4. The mosaic tile color selection method according to claim 3, characterized in that the step of calculating the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color specifically comprises: Get the Euclidean distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color:

Wherein, _hj , _sj , _vj are respectively the coordinate values of each color in the first color space distribution image and the second color space distribution image in the HSV color space, and _hn , _sn , _vn are respectively the coordinate values of the existing tile colors in the HSV color space; The average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile color is obtained. 5. The mosaic tile color selection method according to claim 1, characterized in that the cluster analysis model is established, the colors in the second color space distribution image are divided into classes, the membership matrix of the second color space distribution image is calculated by a fuzzy clustering method, and the cluster center is obtained, which specifically includes: A cluster analysis model is established to divide the colors in the second color space distribution image into classes, and the objective function of fuzzy clustering is obtained:

Wherein, the objective function J(U, C) represents the weighted sum of squares of the distances from the coordinates corresponding to the colors in the second color space distribution image to each cluster center, the membership matrix U=[u _jn ] represents the degree to which the colors in the second color space distribution image belong to each class, M is the number of colors in the second color space distribution image, N is the number of cluster centers, f is a weighted index, dist(c _n , k _j ) refers to the distances from the colors in the second color space distribution image to each cluster center, c _n is the coordinates corresponding to the cluster center, and k _j is the coordinates corresponding to the colors in the second color space distribution image; After obtaining the objective function of fuzzy clustering, the Lagrange method is used to obtain the membership matrix u _jn ,

Wherein, m is the number of colors in the second color space distribution image, and dist ² _nj refers to the square of the distance between the coordinates corresponding to the colors in the second color space distribution image and each cluster center; Obtain the cluster center _En :

Among them, u _nj =1/u _jn . 6. The mosaic tile color selection method according to claim 5, characterized in that the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance are classified into one category, and the center point of each category is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the second part of tile colors that need to be added, specifically comprising: Calculating the Euclidean distance between the colors in the second color space distribution image and the cluster center, obtaining N distances for each color in the second color space distribution image, and classifying the colors in the second color space distribution image that have the closest Euclidean distance to the cluster center into one category; The center point of each class is calculated to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added. 7. The mosaic tile color selection method according to claim 1, characterized in that the establishing of the set coverage model comprises forming a set of colors of existing tiles and colors in the first color space distribution image and the second color space distribution image, and ensuring that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set, and before that, it further comprises: The RGB values of the colors in the first color space distribution image and the second color space distribution image and the colors of the existing tiles are converted into HSV values. 8. A mosaic tile color selection system, characterized in that the mosaic tile color selection system comprises: A color set module, used to establish a set coverage model, to form a set with the colors of the existing tiles and the colors in the first color space distribution image and the second color space distribution image, and to ensure that each color in the first color space distribution image and the second color space distribution image is covered by at least any subset of the set; A first color selection module is used to calculate the average distance between each color in the first color space distribution image and the second color space distribution image and the existing tile colors in the set coverage model, and sort them according to the average distance to obtain the first part of tile colors that need to be added; A cluster analysis module, used to classify the colors in the second color space distribution image into classes, calculate the membership matrix of the second color space distribution image by a fuzzy clustering method, and obtain cluster centers; The second color selection module is used to classify the colors in the second color space distribution image that are closest to the cluster center in Euclidean distance into one category, and calculate the center point of each category to obtain a new cluster center, and the color corresponding to the new cluster center is the color of the second part of tiles that need to be added. 9. A terminal, characterized in that the terminal comprises: a memory, a processor, and a mosaic tile color selection program stored in the memory and executable on the processor, wherein the mosaic tile color selection program, when executed by the processor, implements the steps of a mosaic tile color selection method as described in any one of claims 1 to 7. 10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program for mosaic tile color selection, and when the program for mosaic tile color selection is executed by a processor, the steps of the mosaic tile color selection method according to any one of claims 1 to 7 are implemented.

Images