An automatic coloring method and system for mandala patterns

Abstract

The present invention provides a method and system for automatically coloring a mandala pattern. The method includes the following steps: obtaining a pattern to be colored, performing binarization processing on the pattern to be colored to obtain a black-and-white line drawing; extracting each closed region in the black-and-white line drawing and constructing a minimum bounding rectangle for each closed region; classifying the closed regions into multiple categories through a first classification based on the length and width of the minimum bounding rectangle of the closed region; obtaining the positions of all closed regions of the same category in the pattern to be colored and performing unified coloring. This solution constructs a minimum bounding rectangle for each closed region and classifies the closed regions based on specified rules. Staff can directly obtain the positions of closed regions of the same category and can uniformly color all closed regions of a category. This solution no longer requires manual determination of which small structures belong to the same shape, improving the coloring efficiency of the mandala pattern.

Description

Technical Field

[0001] The present invention relates to the technical field of pattern coloring, and in particular, to an automatic coloring method and system for mandala patterns. Background Art

[0002] Mandala patterns are widely used in the fields of art, design, advertising, and art. Designers often use mandala patterns to express special meanings. Generally, mandala patterns are usually symmetric or partially symmetric. Designers usually use software tools such as Photoshop or Illustrator to design mandala patterns. When the pattern structure is symmetric, usually a small part of the structure can be realized first, and then the rest of the structure can be completed by copying. However, coloring is relatively troublesome, and the same color needs to be assigned to each identical shape in the mandala pattern.

[0003] When the pattern is complex, the designer needs to manually determine which small structures belong to the same shape and color each small structure separately. Therefore, the designer often needs to spend a long time to complete the coloring of the mandala pattern. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide an automatic coloring method for mandala patterns to eliminate or improve one or more defects existing in the prior art.

[0005] One aspect of the present invention provides an automatic coloring method for mandala patterns, the method comprising the following steps:

[0006] Obtain a pattern to be colored, perform binarization processing on the pattern to be colored to obtain a black and white line drawing;

[0007] Extract each closed region in the black and white line drawing, and construct a minimum bounding rectangle for each closed region;

[0008] Based on the length and width of the minimum bounding rectangle of the closed region, classify the closed region into multiple categories through a first classification;

[0009] Obtain the positions of the closed regions of the same category in the pattern to be colored, and perform unified coloring.

[0010] Adopting the above solution, the present solution constructs a minimum bounding rectangle for each closed region and classifies the closed regions based on specified rules. The staff can directly obtain the positions of the closed regions of the same category and can uniformly color the closed regions of one category. This solution no longer requires manual determination of which small structures belong to the same shape, improving the coloring efficiency of mandala patterns.

[0011] In some embodiments of the present invention, after the step of obtaining the pattern to be colored, it further includes classifying the pattern to be colored based on a preset neural network model to determine whether the pattern to be colored is a centrosymmetric figure.

[0012] In some embodiments of the present invention, in the step of classifying the closed region into multiple categories by the first classification based on the length and width of the minimum circumscribed rectangle of the closed region, if the pattern to be colored is a centrosymmetric figure, obtain the classification result of the first classification, calculate the center points of the closed regions in the same category and the center point of the pattern to be colored, and classify them into multiple categories by the second classification based on the distance between the center point of each closed region in the same category and the center point of the pattern to be colored.

[0013] In some embodiments of the present invention, in the step of classifying them into multiple categories by the second classification based on the distance between the center point of each closed region in the same category and the center point of the pattern to be colored, calculate the average value of the distances between the center points of each closed region in the same category and the center point of the pattern to be colored, calculate the difference between the distance between the center point of each closed region and the center point of the pattern to be colored and the average value, compare the difference corresponding to each closed region with a preset second comparison threshold, and if the difference corresponding to the closed region is greater than the preset second comparison threshold, delete the closed region from the category to obtain the classification result of the second classification.

[0014] In the specific implementation process, if the difference corresponding to the closed region is less than or equal to the preset second comparison threshold, keep the closed region in the category to obtain the classification result of the second classification.

[0015] In some embodiments of the present invention, in the step of classifying the closed region into multiple categories by the first classification based on the length and width of the minimum circumscribed rectangle of the closed region, take the minimum circumscribed rectangles of any two closed regions as a comparison group, compare the length and width of the minimum circumscribed rectangles in the comparison group, and respectively compare the length and width of the two minimum circumscribed rectangles in the comparison group. If the differences between the length and width of the two minimum circumscribed rectangles in the comparison group are all less than or equal to a preset first comparison threshold, classify the closed regions corresponding to the two minimum circumscribed rectangles in the comparison group into the same category.

[0016] In some embodiments of the present invention, in the step of obtaining the positions of the closed regions in the same category in the pattern to be colored and performing unified coloring, obtain the coloring color corresponding to the closed region of each category, and uniformly color the closed regions of one category with the corresponding coloring color.

[0017] In some embodiments of the present invention, in the step of obtaining the coloring colors corresponding to the closed regions of each category and uniformly coloring the closed regions of one category with the corresponding coloring colors, the closed regions of each category are sorted to obtain a region sorting, the preselected colors are sorted in terms of color, and based on the serial numbers of the region sorting and the serial numbers of the color sorting, a match is made to obtain the coloring colors corresponding to the closed regions of each category.

[0018] In some embodiments of the present invention, in the step of sorting the preselected colors in terms of color, an ascending or descending order sorting is performed based on the brightness, hue or saturation of the preselected colors.

[0019] In some embodiments of the present invention, in the step of sorting the closed regions of each category to obtain a region sorting, if the pattern to be colored is not a centrosymmetric figure, the sorting is performed based on the area of the minimum circumscribed rectangle of the closed regions of the same category; if the pattern to be colored is a centrosymmetric figure, the sorting is performed based on the area of the minimum circumscribed rectangle of the closed regions of the same category or based on the distance between the center points of the minimum circumscribed rectangles of the closed regions of the same category and the center point of the pattern to be colored.

[0020] The second aspect of the present invention further provides a mandala pattern automatic coloring system, which includes a computer device. The computer device includes a processor and a memory. Computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0021] The third aspect of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps implemented by the aforementioned mandala pattern automatic coloring method are implemented.

[0022] The additional advantages, objectives, and features of the present invention will be partially elaborated in the following description, and will become partially obvious to those of ordinary skill in the art after studying the following text, or can be learned from the practice of the present invention. The objectives and other advantages of the present invention can be pointed out and obtained specifically in the description and the accompanying drawings.

[0023] Those skilled in the art will understand that the objectives and advantages that can be achieved by the present invention are not limited to the above specifically described, and it will be more clearly understood from the following detailed description that the above and other objectives that the present invention can achieve. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and do not constitute a limitation to the present invention.

[0025] Figure 1 Schematic diagram of an implementation manner of the method for automatically coloring the mandala pattern of the present invention;

[0026] Figure 2 System architecture diagram of the method for automatically coloring the mandala pattern of the present invention;

[0027] Figure 3 Comparison schematic diagram of the symmetric mandala line drawing and the asymmetric mandala line drawing;

[0028] Figure 4 Schematic diagram of an example mandala line drawing;

[0029] Figure 5 Gray scale diagram of the schematic diagram of the coloring result image of the corresponding example mandala line drawing. Detailed implementation manner

[0030] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in combination with the implementation manners and the accompanying drawings. Herein, the schematic implementation manners of the present invention and their descriptions are used to explain the present invention, but do not limit the present invention.

[0031] Herein, it also needs to be noted that in order to avoid obscuring the present invention due to unnecessary details, only the structures and / or processing steps closely related to the solution of the present invention are shown in the drawings, and other details less related to the present invention are omitted.

[0032] As Figure 1 and 2 shown, the present invention proposes a method for automatically coloring a mandala pattern, and the method includes the following steps:

[0033] Step S100, obtaining a pattern to be colored, and performing binarization processing on the pattern to be colored to obtain a black and white line drawing;

[0034] In the specific implementation process, the pattern to be colored is a mandala pattern to be colored, that is, a mandala line drawing, and different brightness information is included in the mandala line drawing.

[0035] In the specific implementation process, in the step of performing binarization processing on the pattern to be colored to obtain a black and white line drawing, the pattern to be colored is processed into a black and white line drawing with black and white colors. The binarization processing of the image is a process of setting the gray value of the pixel points of the image to 0 or 255. This process can greatly reduce the amount of data in the image, thereby highlighting the outline of the target.

[0036] In the specific implementation process, the OSTU algorithm can be used to binarize the mandala line drawing, generating a mandala line drawing that only contains two colors, black and white. After binarization, the mandala line drawing only contains two values, 0 and 255.

[0037] Step S200: Extract each closed region in the black-and-white line drawing and construct the minimum bounding rectangle for each closed region.

[0038] In the specific implementation process, the depth-first search method, breadth-first search method, or deep learning-based technology can be used to identify each closed region in the black-and-white line drawing.

[0039] In the specific implementation process, in the step of constructing the minimum bounding rectangle for each closed region, the minimum bounding rectangle for each closed region can be constructed by using the principal axis method and rotation method based on vertex chain codes and discrete Green, or the direct calculation method can be used to determine the boundaries of the rectangle by calculating the maximum and minimum values of the object distribution coordinates in the image.

[0040] Step S300: Based on the length and width of the minimum bounding rectangle of the closed region, classify the closed region into multiple categories through the first classification.

[0041] In the specific implementation process, each closed region corresponds to one of the categories, and each category includes at least one closed region.

[0042] In the specific implementation process, since the structures of the closed regions in the same category are the same, the shapes of the generated minimum bounding rectangles are also less different. By comparing the length and width of the minimum bounding rectangle of each closed region, the closed regions are classified.

[0043] As Figure 4 and 5 shown, step S400: Obtain the positions of the closed regions in the same category in the pattern to be colored and perform unified coloring.

[0044] In the specific implementation process, obtain the positions of the regions enclosed by the closed regions in the same category in the pattern to be colored and uniformly color them with the same color.

[0045] Adopting the above solution, this solution constructs the minimum bounding rectangle for each closed region and classifies the closed regions based on the closed regions. The staff can directly obtain the positions of the closed regions in the same category and can uniformly color the closed regions in one category. This solution no longer requires manual determination of which small structures belong to the same shape, improving the coloring efficiency of the mandala pattern.

[0046] In some embodiments of the present invention, after the step of obtaining the pattern to be colored, it further includes classifying the pattern to be colored based on a preset neural network model to determine whether the pattern to be colored is a centrosymmetric figure.

[0047] In the specific implementation process, the neural network model is provided with a classification layer, and the pattern to be colored is binary-classified through the classification layer to determine whether the pattern to be colored is a centrosymmetric figure.

[0048] In the specific implementation process, in the step of determining whether the pattern to be colored is a centrosymmetric figure, the input image of the neural network model can be a black-and-white line drawing after binarization processing, or the original pattern to be colored.

[0049] In some embodiments of the present invention, in the step of classifying the closed region into multiple categories by the first classification based on the length and width of the minimum circumscribed rectangle of the closed region, if the pattern to be colored is a centrosymmetric figure, the classification result of the first classification is obtained, the center points of the closed regions in the same category and the center point of the pattern to be colored are calculated, and the closed regions in the same category are classified into multiple categories by the second classification based on the distance between the center point of each closed region in the same category and the center point of the pattern to be colored.

[0050] In some embodiments of the present invention, in the classification result of the first classification, each category includes at least one closed region.

[0051] In some embodiments of the present invention, in the step of classifying the closed regions in the same category into multiple categories by the second classification based on the distance between the center point of each closed region in the same category and the center point of the pattern to be colored, the average value of the distances between the center points of each closed region in the same category and the center point of the pattern to be colored is calculated, the difference between the distance between the center point of each closed region and the center point of the pattern to be colored and the average value is calculated, the difference corresponding to each closed region is compared with a preset second comparison threshold, and if the difference corresponding to the closed region is greater than the preset second comparison threshold, the closed region is deleted from the category to obtain the classification result of the second classification.

[0052] In some embodiments of the present invention, in the step of comparing the difference corresponding to each closed region with the preset second comparison threshold, the absolute value of the difference corresponding to each closed region is compared with the preset second comparison threshold.

[0053] In the specific implementation process, if the difference corresponding to the closed region is less than or equal to the preset second comparison threshold, the closed region is kept in the category to obtain the classification result of the second classification.

[0054] With the above solution, for regions with the same shape, the dimensions of their circumscribed rectangles are the same. For any mandala pattern, it can be judged based on the similarity of the length and width of the circumscribed rectangle. If the differences between the length and width of the circumscribed rectangles of two regions are both lower than the specified threshold, the regions are considered to have the same shape. For symmetric mandalas, such as Figure 3 as shown, the distances from the centers of the circumscribed rectangles with the same shape to the center of the circle are also the same. The judgment condition also requires that the difference in the distances from the circumscribed rectangles of the two regions to the center point of the original image is also lower than the specified threshold.

[0055] In some embodiments of the present invention, in the step of classifying the closed regions into multiple categories by the first classification based on the length and width of the minimum circumscribed rectangle of the closed region, any two minimum circumscribed rectangles of the closed regions are taken as a comparison group, and the length and width of the minimum circumscribed rectangles in the comparison group are compared. The length and width of the two minimum circumscribed rectangles in the comparison group are respectively compared. If the differences between the length and width of the two minimum circumscribed rectangles in the comparison group are both less than or equal to the preset first comparison threshold, the closed regions corresponding to the two minimum circumscribed rectangles in the comparison group are classified into the same category.

[0056] In some embodiments of the present invention, in the step of respectively comparing the length and width of the two minimum circumscribed rectangles in the comparison group, the difference between the lengths of the two minimum circumscribed rectangles is calculated, and the difference between the widths of the two minimum circumscribed rectangles is also calculated.

[0057] In the specific implementation process, in the step of if the differences between the length and width of the two minimum circumscribed rectangles in the comparison group are both less than or equal to the preset first comparison threshold, the closed regions corresponding to the two minimum circumscribed rectangles in the comparison group are classified into the same category., the absolute value of the corresponding difference in length and the absolute value of the corresponding difference in width are respectively compared with the first comparison threshold.

[0058] In the specific implementation process, if any one of the differences between the length and width of the two minimum circumscribed rectangles in the comparison group is greater than the preset first comparison threshold, the closed regions corresponding to the two minimum circumscribed rectangles in the comparison group are not classified into the same category.

[0059] In some embodiments of the present invention, in the step of obtaining the positions of the closed regions of the same category in the pattern to be colored and performing unified coloring, the coloring colors corresponding to the closed regions of each category are obtained, and the closed regions of one category are uniformly colored with the corresponding coloring colors.

[0060] In some embodiments of the present invention, in the step of obtaining the coloring colors corresponding to the closed regions of each category and uniformly coloring the closed regions of one category with the corresponding coloring colors, the closed regions of each category are sorted to obtain a region sorting, the preselected colors are sorted in terms of color, and based on the serial numbers of the region sorting and the color sorting, a match is made to obtain the coloring colors corresponding to the closed regions of each category.

[0061] In the specific implementation process, the preselected colors can be obtained from a preselected color source map.

[0062] In the specific implementation process, in the specific implementation process, K colors are extracted from the color source map. Using the K-means algorithm, K colors specified by the user are extracted from the color source map. In particular, the K-means clustering is performed in the Lab color space. The final set of K colors is stored in the RGB format.

[0063] If the number N of the categories of the closed regions is less than the number T of the color set, then coloring can be performed according to the normal process. On the contrary, if N>T, then the colors need to be recycled.

[0064] In some embodiments of the present invention, in the step of sorting the preselected colors in terms of color, the sorting is based on the brightness, hue or saturation of the preselected colors.

[0065] In some embodiments of the present invention, in the step of sorting the closed regions of each category to obtain a region sorting, if the pattern to be colored is not a centrosymmetric figure, then the sorting is based on the area of the minimum circumscribed rectangle of the closed regions of the same category; if the pattern to be colored is a centrosymmetric figure, then the sorting is based on the area of the minimum circumscribed rectangle of the closed regions of the same category or based on the distance between the center point of the minimum circumscribed rectangle of the closed regions of the same category and the center point of the pattern to be colored.

[0066] In the specific implementation process, the steps of sorting the closed regions of each category to obtain a region sorting and sorting the preselected colors in terms of color can both be in ascending order or descending order.

[0067] In the specific implementation process, the schemes for sorting the preselected colors in terms of color include: converting the RGB color space to the HSV space and sorting in ascending order or descending order according to the brightness of the color; converting the RGB color space to the HSV space and sorting in ascending order or descending order according to the hue of the color; converting the RGB color space to the HSV space and sorting in ascending order or descending order according to the saturation of the color; taking the above three different sorting rules as examples, and each rule has two sorting methods of ascending order and descending order, so there are a total of six color sorting schemes.

[0068] An embodiment of the present invention also provides a mandala pattern automatic coloring system, which includes a computer device. The computer device includes a processor and a memory. Computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps achieved by the method described above.

[0069] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps achieved by the aforementioned mandala pattern automatic coloring method. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disks, removable storage disks, CD-ROMs, or any other form of storage medium known in the art.

[0070] Those of ordinary skill in the art should understand that the various exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Specifically, whether to implement it in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link.

[0071] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0072] In the present invention, the features described and / or illustrated for one embodiment can be used in the same way or in a similar way in one or more other embodiments, and / or combined with the features of other embodiments or replace the features of other embodiments.

[0073] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An automatic coloring method for mandala patterns, characterized in that, The method comprises the following steps: Obtaining a pattern to be colored, and performing binarization processing on the pattern to be colored to obtain a black and white line drawing; Extracting each closed area in the black and white line drawing and constructing a minimum circumscribed rectangle of each closed area; Based on the length and width of the minimum circumscribed rectangle of the closed area, the closed area is classified into multiple categories through a first classification. If the pattern to be colored is a centrally symmetrical figure, the classification result of the first classification is obtained, and the minimum circumscribed rectangles of any two closed areas are taken as a comparison group, and the two minimum circumscribed rectangles in the comparison group are compared respectively. If the difference between the two lengths and the difference between the two widths of the two minimum circumscribed rectangles in the comparison group are both less than the first comparison threshold, the closed areas corresponding to the two minimum circumscribed rectangles in the comparison group are classified into the same category, and the center point of the closed area of the same category and the center point of the pattern to be colored are calculated. Based on the distance between the center point of each closed area of the same category and the center point of the pattern to be colored, the closed areas are classified into multiple categories through a second classification; Get the positions of closed areas of the same category in the pattern to be colored and color them uniformly.

2. The method for automatically coloring a mandala pattern according to claim 1, wherein After the step of acquiring the pattern to be colored, the method further includes classifying the pattern to be colored based on a preset neural network model to determine whether the pattern to be colored is a centrally symmetrical figure.

3. The method for automatically coloring the mandala pattern according to claim 1, wherein In the step of classifying into multiple categories through the second classification based on the distance between the center point of each closed area of the same category and the center point of the pattern to be colored, the average value of the distance between the center point of each closed area of the same category and the center point of the pattern to be colored is calculated, the difference between the distance between the center point of each closed area and the center point of the pattern to be colored and the average value is calculated, the difference corresponding to each closed area is compared with a preset second comparison threshold, and if the difference corresponding to the closed area is greater than the preset second comparison threshold, the closed area is deleted from the category to obtain the classification result of the second classification.

4. The method for automatically coloring the mandala pattern according to any one of claims 1 to 3, characterized in that, In the step of obtaining the positions of closed areas of the same category in the pattern to be colored and performing unified coloring, the coloring color corresponding to the closed areas of each category is obtained, and the closed areas of one category are uniformly colored with the corresponding coloring color.

5. The method for automatically coloring the mandala pattern according to claim 4, characterized in that, In the step of obtaining the coloring color corresponding to the closed area of each category and uniformly coloring the closed areas of a category with the corresponding coloring color, the closed areas of each category are sorted to obtain the area sorting, the pre-selected colors are sorted, and the serial numbers of the area sorting and the color sorting are matched to obtain the coloring color corresponding to the closed areas of each category.

6. The automatic coloring method of the mandala pattern according to claim 5, wherein In the step of sorting the pre-selected colors, the pre-selected colors are sorted in ascending or descending order based on brightness, hue or saturation.

7. The automatic coloring method of the mandala pattern according to claim 5, characterized in that In the step of sorting the closed areas of each category to obtain the area sorting, if the pattern to be colored is not a centrally symmetrical figure, the sorting is performed based on the area of the minimum circumscribed rectangle of the closed areas of the same category; If the pattern to be colored is a centrally symmetric figure, sorting is performed based on the area of the minimum circumscribed rectangle of the closed regions of the same category or based on the distance between the center points of the minimum circumscribed rectangles of the closed regions of the same category and the center point of the pattern to be colored.

8. An automatic coloring system for mandala patterns, characterized in that, The system includes a computer device, the computer device includes a processor and a memory, computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method according to any one of claims 1 to 7.

Images