Nail painting method and system based on artificial intelligence and storage medium

Abstract

The invention relates to the technical field of image processing, and discloses a manicure inkjet method and system based on artificial intelligence, and a storage medium. The method comprises the following steps: performing pattern analysis through a pattern processing system to obtain a pattern parameter matrix; performing spectrum scanning and feature extraction on the fingernails to generate an adaptive parameter packet; performing isolated spraying according to the boundary data and the morphology data to form a protective film; carrying out bottom color spraying according to the pattern parameters and the adaptive parameters; performing 3D spraying based on the pattern data and the ground color layer to obtain a pattern layer; and finally, performing quality evaluation to generate evaluation data. According to the invention, through a data driving and intelligent control mode, the accuracy and the restoration degree of manicure inkjet are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to an artificial intelligence-based nail art spray painting method, system and storage medium. Background Art

[0002] At present, the nail industry has widely adopted digital equipment for pattern spraying. Traditional nail spraying equipment mainly includes pattern selection module, spraying execution module and quality inspection module. In the pattern selection stage, users can select the required pattern from the preset pattern library or upload the pattern by themselves; in the spraying execution stage, the equipment completes the pattern drawing by controlling the position of the nozzle and the spraying parameters; in the quality inspection stage, the spraying effect is evaluated through manual observation or simple image acquisition. At the same time, some equipment is also equipped with an isolation protection function, which protects the skin around the nails by spraying an isolation layer to prevent dye penetration.

[0003] However, the existing technology has the following shortcomings: the traditional spray painting method lacks the ability to resolve the pattern in space and cannot accurately restore the three-dimensional texture effect; during the spraying process, due to the irregularity of the nail surface, problems such as uneven color and blurred layers are prone to occur; quality inspection mainly relies on manual experience and judgment, and lacks objective and quantitative evaluation standards. Especially when dealing with complex gradient patterns, the existing technology is difficult to achieve accurate color transitions and three-dimensional effects, affecting the overall quality of nail art works. Summary of the invention

[0004] The present application provides an artificial intelligence-based nail spray painting method, system and storage medium, which are used to significantly improve the accuracy and restoration of nail spray painting through data-driven and intelligent control.

[0005] In the first aspect, the present application provides an artificial intelligence-based nail painting method, which includes: performing spatial stratification and visual parameter conversion on the nail pattern selected by the user through a pattern processing system to obtain a pattern processing matrix containing color gradient data, spatial gradient data and three-dimensional texture data; performing multi-band spectral scanning and surface feature extraction on the nails to be sprayed to obtain microscopic morphology data and precise boundary mapping data of the nails, and generating a nail adaptation parameter package based on the pattern processing matrix; performing spraying trajectory planning and flow dynamic compensation on the isolation protection system according to the precise boundary mapping data and the microscopic morphology data to obtain to a protective film layer with an adaptive thickness, and generate a film distribution map at the same time; according to the color gradient data and the nail adaptation parameter package, combined with the film distribution map, the base color spraying system is subjected to multi-dimensional environmental compensation and flow intelligent adjustment to obtain a base color bearing layer; based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, the 3D three-dimensional spraying system is subjected to multi-level staggered spraying control to obtain a micro-nano pattern layer, and the pattern layer structure data is generated; according to the pattern layer structure data, the finished product is subjected to multi-dimensional stereo scanning and real-time dynamic monitoring to obtain a quality assessment data packet including micro texture distribution, color level transition and spatial effect restoration status.

[0006] In a second aspect, the present application provides an artificial intelligence-based nail painting system, the artificial intelligence-based nail painting system comprising:

[0007] A conversion module, used to perform spatial stratification and visual parameter conversion on the nail art pattern selected by the user through the pattern processing system, and obtain a pattern processing matrix containing color gradient data, spatial gradient data and three-dimensional texture data;

[0008] An extraction module is used to perform multi-band spectral scanning and surface feature extraction on the nails to be sprayed, obtain microscopic morphology data and precise boundary mapping data of the nails, and generate a nail adaptation parameter package based on the pattern processing matrix;

[0009] A compensation module, for performing spraying trajectory planning and flow rate dynamic compensation for the isolation protection system according to the precise boundary mapping data and the microscopic morphology data, obtaining a protective film layer with adaptive thickness, and generating a film distribution map at the same time;

[0010] An adjustment module, for performing multi-dimensional environmental compensation and flow intelligent adjustment on the base color spraying system according to the color gradient data and the nail adaptation parameter package in combination with the film distribution map, to obtain a base color bearing layer;

[0011] A control module, for controlling the 3D printing system to perform multi-layer staggered spraying based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, to obtain a micro-nano pattern layer, and to generate pattern layer structure data;

[0012] The monitoring module is used to perform multi-dimensional stereoscopic scanning and real-time dynamic monitoring of the finished product according to the pattern layer structure data, and obtain a quality evaluation data package including micro-texture distribution, color level transition and spatial effect restoration status.

[0013] The third aspect of the present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned artificial intelligence-based nail painting method.

[0014] In the technical solution provided by the present application, by spatially stratifying and converting the visual parameters of the nail art pattern, the color gradient data, spatial gradient data and three-dimensional texture data of the pattern are effectively extracted, and the accurate quantification of the pattern features is achieved, laying a data foundation for subsequent processing. At the same time, based on multi-band spectral scanning and surface feature extraction technology, the microscopic morphology data and precise boundary mapping data of the nails are accurately obtained, and the recognition accuracy of the surface features of the nails is improved. By planning the spraying trajectory and dynamically compensating the flow rate of the isolation protection system, the adaptive thickness control of the protective film layer is achieved, which effectively solves the uniformity problem of the isolation protection. According to the color gradient data and the nail adaptation parameter package, combined with the film The distribution map performs multi-dimensional environmental compensation and intelligent flow adjustment on the base color spraying system, ensuring the uniform transition effect of the base color bearing layer. Then, through multi-level staggered spraying control of the 3D stereoscopic spraying system, the construction of a micro-nano pattern layer with a spatial three-dimensional effect is successfully achieved with the cooperation of spatial gradient data, three-dimensional texture data and the base color bearing layer. Finally, multi-dimensional stereo scanning and real-time dynamic monitoring technology are used to conduct a comprehensive quality assessment of the finished product, and a quality assessment data package including micro-texture distribution, color level transition and spatial effect restoration is obtained. A complete quality control system is established, which significantly improves the accuracy and restoration of nail spraying through data-driven and intelligent control. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 This is a schematic diagram of an embodiment of a nail spray painting method based on artificial intelligence in an embodiment of the present application;

[0017] Figure 2 This is a schematic diagram of an embodiment of an artificial intelligence-based nail painting system in the embodiment of the present application. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a method, system and storage medium for nail painting based on artificial intelligence. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of the nail painting method based on artificial intelligence includes:

[0020] Step S101: spatially layering and visual parameter conversion are performed on the nail art pattern selected by the user through a pattern processing system to obtain a pattern processing matrix including color gradient data, spatial gradient data and three-dimensional texture data;

[0021] Step S102, performing multi-band spectral scanning and surface feature extraction on the nail to be sprayed, obtaining microscopic morphology data and precise boundary mapping data of the nail, and generating a nail adaptation parameter package based on the pattern processing matrix;

[0022] Step S103: According to the precise boundary mapping data and microscopic morphology data, the spraying trajectory planning and flow rate dynamic compensation are performed on the isolation protection system to obtain a protective film layer with adaptive thickness, and a film distribution map is generated at the same time;

[0023] Step S104: Based on the color gradient data and the nail adaptation parameter package, combined with the film distribution map, multi-dimensional environmental compensation and flow intelligent adjustment are performed on the base color spraying system to obtain a base color bearing layer;

[0024] Step S105: Based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, the 3D three-dimensional inkjet printing system is controlled to spray in multiple layers to obtain a micro-nano pattern layer, and generate pattern layer structure data;

[0025] Step S106: Perform multi-dimensional stereoscopic scanning and real-time dynamic monitoring on the finished product according to the pattern layer structure data to obtain a quality evaluation data package including micro texture distribution, color level transition and spatial effect restoration status.

[0026] It is understandable that the execution subject of the present application can be an artificial intelligence-based nail painting system, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0027] Specifically, the nail art pattern is processed by relying on the pattern processing system. After receiving the input of the nail art pattern selected by the user, the system performs the initial digital conversion. The spatial stratification process divides the input pattern into three dimensions: color data layer, gradient data layer and texture data layer for processing. The color data layer is processed by channel separation, and the pattern is separated in the RGB color space. The data of each channel is quantized to form independent color component data. The color gradient data is extracted by analyzing the color change relationship between adjacent pixels. Specifically, for each pixel (x, y), its gradient value on the three RGB channels is calculated to construct a color gradient vector. The gradient data layer focuses on the light and dark change characteristics in the pattern. By calculating and analyzing the grayscale value of the image, the spatial gradient data is extracted. The texture data layer uses the frequency domain analysis method to extract the three-dimensional texture data based on the microscopic structural characteristics of the pattern surface. These three types of data are constructed into a pattern processing matrix containing complete pattern information after parameter calibration and correlation analysis. In the nail data acquisition stage, multiple light sources with different wavelengths are used to scan the nail surface. The wavelength range covers the visible spectrum, and each wavelength of the light source can provide specific reflection information on the nail surface. During the scanning process, light interacts with the nail surface to generate reflection signals. By collecting these reflection signals and analyzing and processing them, the microscopic morphological features of the nail surface are extracted. At the same time, the system uses a high-precision edge detection method to locate the nail contour and generate accurate boundary mapping data. The microscopic morphological data and boundary mapping data are matched and analyzed with the aforementioned pattern processing matrix to calculate and generate a parameter package suitable for the current nail features.

[0028] After entering the isolation protection stage, the system determines the precise spraying range based on the boundary mapping data. Combined with the microscopic morphology data, the optimal spraying path is determined by numerical calculation. In the actual spraying process, the thickness distribution of the thin film layer is monitored in real time, and the spray flow parameters are dynamically adjusted according to the monitoring data to ensure the uniformity and integrity of the protective film. The parameter data of the entire spraying process is recorded and processed, and converted into a detailed film distribution map as an important reference for subsequent processes. The base color spraying stage comprehensively processes the color gradient data and the nail adaptation parameter package. Under the guidance of the film distribution map, the working parameters of the spraying system are optimized and adjusted in multiple dimensions. The influence of environmental factors (including temperature, humidity, airflow, etc.) is collected in real time by sensors and compensated for. The spray flow parameters are intelligently adjusted according to the real-time feedback data to ensure the uniformity and transition effect of the base color layer.

[0029] The pattern printing stage uses 3D stereoscopic printing technology to convert spatial gradient data and stereoscopic texture data into specific printing control instructions through numerical processing. A multi-level staggered spraying strategy is adopted to gradually build a three-dimensional effect on the base color bearing layer. The printing parameters of each layer are precisely numerically calculated and optimized to ensure that the actual effect is consistent with the expected design. The structural features of the entire printing process are recorded in real time and converted into pattern layer structure data. In the quality inspection stage, high-precision multi-dimensional stereo scanning technology is used to conduct all-round inspection of the finished product. After processing, the scanning data generates a micro-texture distribution map for evaluating the uniformity of the surface structure. The color level transition effect is evaluated by analyzing the numerical changes in the color transition area. The degree of restoration of the spatial three-dimensional effect is quantitatively analyzed to generate a quality evaluation data package containing multiple dimensional evaluation indicators. Calculation and optimization are performed through the mathematical model of the system. For example, when extracting color gradient data, the original RGB data is first separated by channels, and the data of each channel is subjected to independent gradient analysis to calculate the difference between adjacent pixels, and finally the color gradient information is obtained. When generating spray control instructions, the system converts spatial gradient data and three-dimensional texture data into specific nozzle position, pressure and flow parameters to ensure the accuracy of each layer of spraying.

[0030] In the embodiment of the present application, by spatially stratifying and converting the visual parameters of the nail art pattern, the color gradient data, spatial gradient data and three-dimensional texture data of the pattern are effectively extracted, and the accurate quantification of the pattern features is achieved, which lays a data foundation for subsequent processing. At the same time, based on multi-band spectral scanning and surface feature extraction technology, the microscopic morphology data and precise boundary mapping data of the nails are accurately obtained, which improves the recognition accuracy of the surface features of the nails. By planning the spraying trajectory and dynamically compensating the flow rate of the isolation protection system, the adaptive thickness control of the protective film layer is achieved, which effectively solves the uniformity problem of the isolation protection. According to the color gradient data and the nail adaptation parameter package, combined with the film distribution The atlas performs multi-dimensional environmental compensation and intelligent flow adjustment on the base color spraying system to ensure the uniform transition effect of the base color bearing layer. Then, through multi-level staggered spraying control of the 3D stereoscopic spraying system, with the cooperation of spatial gradient data, three-dimensional texture data and the base color bearing layer, the construction of a micro-nano pattern layer with a spatial three-dimensional effect is successfully realized. Finally, multi-dimensional stereo scanning and real-time dynamic monitoring technology are used to conduct a comprehensive quality assessment of the finished product, and a quality assessment data package including micro-texture distribution, color level transition and spatial effect restoration is obtained. A complete quality control system is established, which significantly improves the accuracy and restoration of nail spraying through data-driven and intelligent control.

[0031] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0032] (1) Processing the nail art pattern through color conversion to generate a digital matrix, performing RGB channel quantization segmentation and signal intensity calibration on the digital matrix, and outputting RGB three-channel data after discrete Fourier transform processing;

[0033] (2) Perform nonlinear color mapping and cross correction based on RGB three-channel data, perform multi-dimensional quantitative analysis and gradient interpolation calculation on color parameters, and generate color gradient data through color gamut conversion and gradient reconstruction;

[0034] (3) Extracting the depth information sequence from the digital matrix, performing hierarchical mapping and dynamic range expansion according to the brightness level, and outputting spatial gradient data through contrast enhancement and spatial compensation operations;

[0035] (4) Separating high-frequency texture and filtering low-frequency background from the digital matrix, and then subjecting it to wavelet transform and frequency domain decomposition, extracting texture features and recombining and synthesizing to generate three-dimensional texture data;

[0036] (5) Normalizing the spatial coordinates of the color gradient data, spatial gradient data, and three-dimensional texture data, converting them to a unified coordinate system according to the principles of geometric transformation and projection mapping, and generating a three-dimensional data association table through data alignment and calibration;

[0037] (6) Perform principal component analysis and parameter dimensionality reduction on the three-dimensional data association table, calculate the inter-layer eigenvectors and association strength, and generate a pattern processing matrix through data optimization and redundancy elimination.

[0038] Specifically, color conversion is first performed to convert the input nail art pattern into a digital matrix through digital sampling. The digital sampling process uses high-precision image acquisition equipment to scan and quantize the pattern point by point. The digital matrix contains the position and color information of the pattern, and each matrix element corresponds to the value of a pixel. RGB channel quantization segmentation decomposes the color information of each pixel into three basic channels: red, green, and blue, and the value range of each channel is 0-255. Signal intensity calibration ensures the accuracy of the data by normalizing the values ​​of each channel. The calibrated data is subjected to a discrete Fourier transform to convert the spatial domain information into the frequency domain for subsequent feature extraction. After obtaining the RGB three-channel data, nonlinear color mapping and cross correction are performed. Nonlinear mapping takes into account the perception characteristics of the human eye to different colors, and uses methods such as Gamma correction to optimize color performance. Cross correction handles the crosstalk between different channels to improve the accuracy of color reproduction. The multi-dimensional quantitative analysis of color parameters is expressed as:

[0039]

[0040] Where: Q(p,q) is the color quantization value of the pixel (p,q); λ k is the weight factor of the kth dimension; W k (p,q) is the characteristic function of the kth dimension; γ is the color space conversion factor; H(r,s,t) is the color space mapping function; m is the total number of characteristic dimensions; r, s, t are the color space coordinate parameters.

[0041] Gradient interpolation calculation builds continuous color transition based on the color difference of adjacent pixels. Through color gamut conversion, color data is mapped to a color space suitable for printing, and gradient reconstruction is performed to generate color gradient data.

[0042] When extracting the depth information sequence from the digital matrix, the image is converted to grayscale and a brightness level distribution map is established. Layered mapping is performed according to the brightness values, and the image is divided into multiple brightness levels. The dynamic range extension technology is used to increase the distinction between levels and enhance the three-dimensional sense of the pattern. Contrast enhancement processing improves the transition effect between different levels, and spatial compensation calculation corrects the deformation caused by projection, and finally outputs accurate spatial gradient data.

[0043] Texture analysis of digital matrices extracts high-frequency texture information through high-pass filtering, while using low-pass filtering to remove low-frequency background. Wavelet transform decomposes the image into detail layers and approximation layers of different scales, and frequency domain decomposition further separates the directional characteristics of the texture. Texture feature extraction includes multiple dimensions such as directionality, roughness, and regularity. These features are recombined and synthesized to form three-dimensional texture data. Spatial coordinate normalization processing unifies color gradient data, spatial gradient data, and three-dimensional texture data into a standard coordinate system. Geometric transformation and projection mapping ensure the spatial correspondence between different data. The data alignment and calibration process eliminates the deviation between various types of data and generates an accurate three-dimensional data association table.

[0044] The principal component analysis of the three-dimensional data association table is performed to extract the main feature directions, and the data redundancy is reduced by parameter dimension reduction. The calculation of inter-layer feature vectors reflects the association relationship between different data layers, and the quantification of association strength reflects the degree of mutual influence of each layer of data. The data optimization process removes redundant information, retains key features, and generates an efficient pattern processing matrix.

[0045] For example, the pattern contains petal textures that transition from dark red to light pink. After digital sampling, RGB channel separation shows that the red channel value varies in the range of 255-180, reflecting the gradient characteristics of the color. Through Fourier transform, it is found that the texture features are mainly concentrated in the medium and high frequency bands, indicating that the pattern has rich details. After multi-dimensional quantitative analysis, an accurate color gradient model is established. The spatial gradient data reflects the three-dimensional sense of the petals, while the texture data retains the subtle features of the pattern. The three-dimensional data association table organically combines these features, and the pattern processing matrix accurately guides the subsequent printing process.

[0046] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0047] (1) irradiating the nail to be sprayed with a multi-band light source, collecting reflected light signals of different wavelengths, performing wavelength decomposition and intensity calculation on the reflected light signals, and obtaining a spectral data set;

[0048] (2) Perform multi-dimensional cross-analysis and data reconstruction on the spectral data set, and generate initial morphological feature points through spectral parameter correction and signal noise reduction processing;

[0049] (3) Construct a spatial coordinate sequence based on the initial morphological feature points, and calculate the microscopic morphological data through point cloud data reconstruction and error elimination;

[0050] (4) Detect edge features of the surface of the painted nails, calculate grayscale gradients and extract contours, combine curvature analysis and boundary tracking, and output accurate boundary mapping data;

[0051] (5) Matching and transforming the color gradient data, spatial gradient data, and three-dimensional texture data in the pattern processing matrix with the microscopic morphology data, and generating initial adaptation parameters through geometric deformation compensation and data mapping;

[0052] (6) Perform spatial dimension correction and numerical optimization on the initial adaptation parameters, perform boundary constraint processing based on precise boundary mapping data, and output the nail adaptation parameter package.

[0053] Specifically, a multi-band light source technology is used to illuminate the nails to be sprayed. The multi-band light source includes light of different wavelengths, and the wavelength range covers the visible spectrum (380-780nm). The integrity of the collected data is ensured by controlling the intensity and irradiation angle of the light source of different wavelengths. When the light is irradiated to the surface of the nail, reflected light signals of different wavelengths are generated. These reflected light signals are decomposed by wavelength through a spectrometer, and the reflected light intensity of each wavelength is recorded and converted into a digital signal to form an initial spectral data set. The spectral data set contains the reflection characteristics of the nail surface at different wavelengths, and these data are processed by multidimensional cross analysis. Multidimensional cross analysis performs correlation analysis on data of different wavelengths to find out the correlation between wavelengths. In the process of data reconstruction, spectral parameter correction technology is used to eliminate ambient light interference, and signal noise reduction processing removes random noise in the acquisition process. These processed data are converted into feature points in three-dimensional space, each of which carries position and reflection intensity information.

[0054] The process of establishing the spatial coordinates of the morphological feature points can be expressed as:

[0055]

[0056] Where: S(u, v, w) represents the three-dimensional coordinate value of the space point; ξ j is the weight coefficient of the j-th dimension feature; M j (u, v, w) is the mapping function of the jth dimension; η is the spatial transformation coefficient; N(e, f, g) is the coordinate compensation function; d is the number of feature dimensions; e, f, g are compensation parameters.

[0057] Point cloud data reconstruction connects discrete feature points into a continuous surface and fills the blank areas between feature points through interpolation algorithms. The error elimination process identifies and removes outliers to ensure that the microscopic topography data accurately reflects the real structure of the nail surface.

[0058] Edge feature detection uses a multi-level grayscale gradient analysis method to calculate the grayscale change rate of each pixel in the image and find areas with significant grayscale value changes as potential boundary points. Contour extraction connects these boundary points into contour lines. Curvature analysis calculates the curvature value of each point on the contour line and identifies key shape features. Boundary tracking verifies point by point along the initially determined boundary to ensure the continuity and accuracy of the boundary, and finally outputs accurate boundary mapping data. In the data matching transformation stage, the pattern processing matrix (including color gradient data, spatial gradient data, and three-dimensional texture data) obtained in the previous step is spatially matched with the microscopic morphology data. The geometric deformation compensation processing takes into account the curvature change of the nail surface and makes corresponding deformation adjustments to the pattern data. Data mapping establishes a corresponding relationship between the two and generates preliminary adaptation parameters.

[0059] In the parameter optimization phase, the initial adaptation parameters are corrected in spatial dimension to ensure the accuracy of the parameters in three-dimensional space. The numerical optimization process removes unreasonable parameter values ​​to make the parameter distribution more reasonable. Constraint processing is performed in combination with precise boundary mapping data to ensure that all parameters are within the valid boundary range, and finally the nail adaptation parameter package is output.

[0060] For example, when scanning a piece of nail, the multi-band light source emits light of different wavelengths in a preset sequence. The reflection signal of each wavelength is recorded, and after wavelength decomposition, it is found that the reflection characteristics in the 500-600nm band are the most significant, indicating that the nail surface has unique optical properties in this band. Multi-dimensional cross-analysis found that the data of adjacent wavelengths have a strong correlation, and the initial morphological feature points were obtained through data reconstruction. These feature points are transformed through spatial coordinates and reconstructed through point clouds to form a microscopic morphological model of the nail surface. During the edge detection process, the contour line of the nail is identified by grayscale gradient calculation, and the curvature analysis shows the curvature change law of the nail edge, thereby obtaining accurate boundary data. The nail art pattern is matched with the nail morphology, and the adaptation scheme is obtained through parameter optimization to ensure the perfect presentation of the pattern on the nail surface.

[0061] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0062] (1) Extract boundary point sets from precise boundary mapping data, and generate a spraying area boundary map through spatial coordinate transformation and region segmentation processing;

[0063] (2) Calculate the surface curvature change based on the microscopic morphology data, and output the spray height compensation value through numerical processing and parameter analysis;

[0064] (3) The spraying area boundary map is superimposed with the spraying height compensation value, and the spraying trajectory data of the isolation protection system is calculated through trajectory interpolation and path optimization processing;

[0065] (4) Calculate the flow distribution of the spray trajectory data, and output a dynamic flow control sequence through pressure parameter adjustment and flow rate compensation;

[0066] (5) spraying the protective film layer according to a dynamic flow control sequence, and generating the protective film layer through thickness sensing and feedback regulation;

[0067] (6) Perform spatial scanning and density distribution analysis on the protective film layer, and output the film distribution map through data integration and parameter mapping.

[0068] Specifically, a boundary point set is extracted from the precise boundary mapping data. The boundary point set refers to the set of key point coordinates of the edge of the nail, which is obtained by sampling the precise boundary mapping data. Each boundary point contains its position information in three-dimensional space. The spatial coordinates of these boundary points are transformed and converted into a unified spraying coordinate system. The region segmentation process divides the entire spraying area into multiple sub-areas, and the boundary features of each sub-area are recorded and marked separately to generate a spraying area boundary map. The boundary map clearly identifies the area range that needs to be isolated and protected. Then, the surface curvature change is calculated based on the microscopic morphology data. The microscopic morphology data records the microstructural features of the nail surface, including height changes and surface undulation information. These data are numerically processed to calculate the curvature values ​​of each point on the surface, and the law of curvature change is determined by parameter analysis. These analysis results are converted into specific spraying height compensation values, which are used to adjust the height position of the nozzle during the spraying process.

[0069] The spraying area boundary map and the spraying height compensation value are fused to obtain comprehensive data containing boundary information and height information. Through trajectory interpolation technology, a continuous spraying path is generated between boundary points. Path optimization processing takes into account spraying efficiency and uniformity to plan the best spraying trajectory. These processed data form spraying trajectory data to guide the movement of the isolation protection system. Flow distribution calculation is performed based on the spraying trajectory data. According to the spraying requirements of different positions, the corresponding flow parameters are calculated. Pressure parameter adjustment ensures that the spraying material can evenly cover the specified area, and flow rate compensation handles the dynamic change factors during the spraying process. These calculation results are combined to form a dynamic flow control sequence to achieve precise control of the spraying process.

[0070] The protective film layer spraying process is carried out according to the dynamic flow control sequence. During the spraying process, the film formation status is monitored in real time by the thickness sensor. The feedback regulation mechanism adjusts the spraying parameters in time according to the monitoring data to ensure the uniformity and integrity of the protective film layer. The formed protective film layer can effectively protect the skin around the nails. The completed protective film layer is spatially scanned to obtain the three-dimensional distribution data of the film. The density distribution analysis evaluates the coverage and thickness uniformity of the film. Through data integration, various parameters are processed uniformly, and parameter mapping establishes the correspondence between film characteristics and spatial positions. These processed data form a film distribution map, which provides an important reference for the subsequent spraying process.

[0071] For example: when processing a piece of nail, 356 boundary feature points are extracted from the boundary mapping data, and these points form a closed area boundary after coordinate transformation. Microscopic morphology analysis shows that there are different degrees of undulations on the surface of the nail, based on which the height compensation value of each point in the area is calculated. On this basis, the spraying path is planned, and a spiral trajectory mode from inside to outside is adopted, and the spacing between each trajectory is kept at a uniform interval of 0.2mm. In flow control, the spraying amount near the edge is appropriately reduced to avoid overflow, while the center area maintains a stable flow to ensure coverage. Real-time monitoring data shows that the film thickness fluctuates within the range of 15-20 microns, and a uniform coverage effect is finally achieved through dynamic adjustment. The spatial scanning results show that the film density is evenly distributed, the edge transition is natural, and the thickness changes smoothly, which fully meets the requirements of isolation protection.

[0072] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0073] (1) Performing color space conversion and gradient distribution analysis on color gradient data, and generating background color distribution data through numerical calculation and parameter calibration;

[0074] (2) Calculate the surface curvature and divide the area according to the nail adaptation parameter package, and output the spraying compensation parameters through coordinate transformation and data reconstruction;

[0075] (3) Extract thickness variation data from the film distribution map and calculate the spray pressure adjustment value through numerical analysis and parameter correction;

[0076] (4) Fusing the background color distribution data with the spraying compensation parameters, and generating a spraying control sequence through parameter optimization and data reconstruction;

[0077] (5) spraying the base color according to the spraying pressure adjustment value and the spraying control sequence, and outputting the base color layer through data feedback and dynamic adjustment;

[0078] (6) Surface features and uniformity analysis of the base color layer are performed, and the base color bearing layer is generated through data verification and parameter updating.

[0079] Specifically, the color gradient data is converted to a color space. The color space conversion converts the initial RGB color data to a CMYK color space that is more suitable for inkjet printing to ensure the accuracy of color reproduction. The gradient distribution analysis focuses on the gradual characteristics of the color, and determines the gradient transition method by analyzing the color differences in adjacent areas. Numerical calculation quantifies the color data into specific spraying parameters, and parameter calibration ensures that these parameters meet the working characteristics of the spraying equipment and generates accurate background color distribution data.

[0080] The nail adaptation parameter package contains the shape feature information of the nail surface. The surface curvature calculation is based on the three-dimensional shape data of the nail, and its calculation formula is:

[0081]

[0082] Where: K(i, j, k) represents the curvature value at the spatial point (i, j, k); is the weight coefficient of the mth curvature component; B m (i, j, k) is the mth basic curvature function; ψ is the surface deformation coefficient; D(o, p, q) is the deformation compensation function; t is the number of curvature components; o, p, q are deformation parameters.

[0083] Regional division divides the nail surface into multiple sub-regions, which facilitates precise control of spraying parameters. Coordinate transformation converts the parameters of each region into a unified spraying coordinate system, and data reconstruction integrates the scattered parameters into coherent spraying compensation parameters. The thickness variation data extracted from the film distribution map reflects the spatial distribution characteristics of the isolation layer. Numerical analysis performs statistical processing on these data to find out the law of thickness distribution. Parameter correction adjusts the spraying pressure parameters according to the analysis results and calculates the optimal spraying pressure adjustment value.

[0084] The fusion process of the background color distribution data and the spray compensation parameters focuses on the spatial correspondence between the two sets of data. The parameter optimization process removes unreasonable parameter combinations, and the data reconstruction generates control sequences that meet the actual spraying requirements. These control sequences contain parameters in multiple dimensions such as position, pressure, and flow.

[0085] During the base color spraying stage, precise spraying is performed according to the spraying control sequence and pressure adjustment value. The data feedback mechanism monitors the spraying effect in real time and dynamically adjusts to ensure the uniformity of the base color layer. During the spraying process, the pressure and flow parameters are dynamically adjusted as the spraying position changes to ensure uniform coverage of the base color.

[0086] The surface characteristics of the formed base color layer are collected, including data in multiple dimensions such as thickness distribution and color uniformity. The uniformity analysis evaluates the quality of the base color layer, and confirms whether various parameters meet the standards through data verification. The parameter update optimizes and adjusts the problems found to form a stable base color bearing layer.

[0087] For example, the color gradient data shows a gradual change of pink from the center to the edge. After converting this data into the spray color space, the specific color material ratio parameters are obtained. The curvature analysis of the nail surface shows that the center area is relatively flat while the edge has a larger curvature, and five spray sub-areas are divided accordingly. The film distribution map shows that the isolation layer at the edge is slightly thicker, and the dynamic adjustment of the pressure parameters ensures that the base color does not penetrate into the isolation layer. The spray control sequence generated after data fusion specifies the spiral spray path from the center to the outside. In the actual spraying process, a larger flow rate is used in the center area to ensure color saturation, and the edge area achieves a natural gradient effect through precise pressure control. The inspection after the base color layer is completed shows that the color transition is smooth and the thickness distribution is uniform, which fully meets the requirements of subsequent pattern spraying.

[0088] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0089] (1) Perform multi-level decomposition and numerical reconstruction of spatial gradient data, and output a spatial rendering parameter sequence through stereo gradient analysis and parameter extraction;

[0090] (2) Extracting depth information and surface features from the three-dimensional texture data, and generating a texture control matrix through data conversion and feature mapping;

[0091] (3) Scanning the surface profile of the base color bearing layer and collecting data, and calculating the height compensation value through surface parameter analysis and numerical reconstruction;

[0092] (4) Data fusion of the spatial rendering parameter sequence and the texture control matrix is ​​performed, and the spraying path sequence is output through hierarchical processing and parameter optimization;

[0093] (5) According to the height compensation value and the spraying path sequence, the spraying parameters are adjusted in detail and numerically corrected to generate a micro-nano pattern layer;

[0094] (6) Structural feature collection and three-dimensional effect analysis of the micro-nano pattern layer are performed, and pattern layer structural data is generated through data integration and feature extraction.

[0095] Specifically, the spatial gradient data is decomposed at multiple levels. Multi-level decomposition divides the gradient data according to different spatial scales, decomposing it layer by layer from the overall effect to the local details. The larger scale level reflects the overall gradient trend, while the smaller scale level contains the detail change information. Numerical reconstruction recombines the decomposed data at each level, retaining the key features while removing noise. Stereo gradient analysis focuses on the variation law of gradient in three-dimensional space, thereby determining the spatial distribution characteristics of the gradient effect. Parameter extraction converts these analysis results into specific numerical parameters to form a sequence of spatial rendering parameters. Stereo texture data contains the depth information and surface features of the pattern. In the process of depth information extraction, the three-dimensional depth value of the texture is obtained by analyzing the intensity distribution of the texture data. Surface features include information in multiple dimensions such as texture directionality, roughness, and regularity. Data conversion converts these features into parameters that can be used to control printing, and feature mapping establishes the corresponding relationship between texture features and printing parameters to form a texture control matrix.

[0096] When scanning the surface of the base color bearing layer, a high-precision optical scanning device is used to collect surface profile information. The data acquisition process records the height changes and shape characteristics of the surface. The surface parameter analysis processes these raw data and extracts the key shape feature parameters. The numerical reconstruction converts these parameters into specific height compensation values ​​for height adjustment in the subsequent printing process. In the data fusion process of the spatial rendering parameter sequence and the texture control matrix, the spatial correspondence is first established. The hierarchical processing organizes the fused data in layers according to the printing requirements. The lower level determines the basic spraying path, and the higher level controls the formation of details. The parameter optimization process removes unreasonable parameter combinations to ensure that the spraying path sequence meets the technical requirements and is easy to implement in practice.

[0097] When performing actual spraying according to the height compensation value and spray path sequence, the first step is to make detail adjustments. The detail adjustment process adjusts the nozzle parameters according to the requirements of different positions, including spray angle, pressure, flow rate, etc. The numerical correction monitors and adjusts these parameters in real time to ensure the accuracy of the spraying effect. The formed micro-nano pattern layer has a precise three-dimensional effect and clear texture details. The structural feature collection of the micro-nano pattern layer adopts a multi-angle scanning method to comprehensively record the three-dimensional effect of the pattern. The three-dimensional effect analysis evaluates the spatial performance of the pattern, including depth restoration, detail clarity and other aspects. Data integration systematically processes these analysis results, and feature extraction extracts key structural features to generate pattern layer structure data.

[0098] For example, the spatial gradient data is processed: the whole is divided into three levels. The first level processes the gradient of the main outline of the pattern, the second level focuses on the transition effect between the petals, and the third level accurately controls the internal gradient of each petal. Texture data processing extracts the concave and convex texture information of the pattern and establishes the corresponding relationship between the depth of the texture and the spraying parameters. The base color layer scan shows slight surface undulations, and compensation parameters are generated based on this. After data fusion, a spiral spraying path from the center of the flower to the outside is planned, and combined with height compensation to ensure the accurate presentation of the pattern on the curved surface. The formed three-dimensional pattern has a natural sense of layering, the edge transition of the petals is smooth, and the overall effect is three-dimensional and realistic.

[0099] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0100] (1) Perform multi-angle scanning and depth analysis on the pattern layer structure data, and generate a detection data set through parameter extraction and data reconstruction;

[0101] (2) Extract surface features from the detection data set and output the micro-texture distribution through data processing and morphological analysis;

[0102] (3) The color data in the detection data set is decomposed hierarchically, and the color level transition is calculated through gradient processing and contrast analysis;

[0103] (4) Perform spatial mapping of micro texture distribution and color level transition, and generate spatial effect restoration state through data integration and parameter extraction;

[0104] (5) Perform numerical analysis on micro texture distribution, color level transition and spatial effect restoration status, and generate a quality assessment matrix through data verification and parameter optimization;

[0105] (6) Perform data synthesis and feature extraction based on the quality assessment matrix, and output quality assessment data packets through parameter matching and data fusion.

[0106] Specifically, the pattern layer structure data is scanned at multiple angles. Multi-angle scanning uses light sources at different angles to illuminate the pattern surface, collect reflected light signals, and record the three-dimensional structural features of the pattern. The depth analysis process processes these raw scan data to extract the depth information of the pattern surface. Parameter extraction converts the analysis results into quantifiable feature parameters, and data reconstruction organizes these parameters into an ordered data set to form a detection data set. When extracting surface features from the detection data set, attention is paid to the microscopic structural features of the pattern surface. Data processing includes basic processing such as denoising and smoothing, and morphological analysis focuses on extracting the shape features of the pattern, including edge sharpness, surface flatness, etc. After being sorted, these features are output as micro-texture distribution data, which reflects the spatial distribution characteristics of the pattern surface structure.

[0107] The color data in the detection data set contains the color information of the pattern. Hierarchical decomposition decomposes the color data according to different spatial scales, from overall hue to local details. Gradient processing analyzes the color change rules between adjacent areas, and contrast analysis evaluates the color differences between different areas, and finally calculates the color level transition data. The spatial mapping of micro-texture distribution and color level transition establishes the spatial correspondence between structural features and color features. Data integration aligns the two types of data in spatial position, and parameter extraction extracts the key parameters that reflect the spatial effect, generating accurate spatial effect restoration state data.

[0108] When performing numerical analysis on three types of data (micro texture distribution, color level transition and spatial effect restoration status), the distribution of their characteristic parameters is evaluated respectively. Data verification ensures that all parameters are within a reasonable range, and parameter optimization adjusts the weight relationship between parameters to generate a comprehensive quality assessment matrix.

[0109] The data synthesis process of the quality assessment matrix takes all the assessment indicators into consideration, and feature extraction finds the most representative quality features. Parameter matching ensures that the correlation between the indicators is reasonable, and data fusion integrates all information into a quality assessment data package.

[0110] For example, multi-angle scanning collects pattern data at different angles such as 0 degrees, 45 degrees, and 90 degrees, and extracts three-dimensional structural features through analysis of these data. Surface feature analysis shows that the three-dimensional transition of the pattern edge is clear and the micro-texture is uniform. Color level decomposition finds that the gradual transition from the center of the flower to the edge of the petals is natural, and the colors of different areas are coordinated. Spatial mapping shows that the texture features and color changes work together to create a three-dimensional effect. Numerical analysis confirms that all parameters have met the expected standards, and the quality assessment data package fully records the quality characteristics of the work. In the quality assessment process, multi-angle scanning first uses a visible light source with a wavelength of 380-780nm, from 0 degrees to 360 degrees, and scans and collects every 15 degrees. The scanning data at each angle contains surface reflection intensity and spatial position information. In the depth analysis stage, these raw data are converted into a three-dimensional coordinate point set through the principle of triangulation, and each point contains XYZ spatial coordinates and reflection intensity values. The parameter extraction process calculates feature parameters such as surface normal vectors and curvature values, and the data reconstruction connects these discrete feature points into a continuous surface model to form a detection data set.

[0111] The surface feature extraction in the detection data set adopts a multi-scale analysis method. First, Gaussian filtering is performed to remove random noise, and then the surface features are decomposed into detail layers of different scales through wavelet transform. The morphological features at each scale are calculated in the morphological analysis stage, including parameters such as roughness, waviness, and contour. These features are combined to form a micro-texture distribution, reflecting the micro-structural characteristics of the pattern surface.

[0112] The hierarchical decomposition of color data adopts a pyramid structure to divide the pattern into 4-5 levels with different resolutions. Each level performs color space conversion from RGB space to HSV space to better describe the gradient characteristics of color. Gradient processing calculates the color gradient of adjacent pixels and determines the direction and intensity of color change through vector field analysis. Contrast analysis calculates the color difference between different areas, and all these analysis results are combined into color level transition data. The spatial mapping process establishes a three-dimensional grid model and maps the micro-texture distribution and color level transition data to this model. Each grid node contains position, texture and color information. The data integration process calculates the spatial correlation of texture features and color features, obtains the feature vector reflecting the overall spatial effect through parameter extraction, and generates the spatial effect restoration state.

[0113] The three types of data are comprehensively evaluated in the numerical analysis phase. First, the statistical characteristics of each type of data are calculated, including mean, variance, kurtosis, etc. Multiple thresholds are set in the data verification process to check whether each parameter is within a reasonable range. Parameter optimization uses an iterative method to adjust the weight coefficients of different features, and finally obtain an evaluation matrix that reflects the overall quality.

[0114] The evaluation matrix is ​​processed using principal component analysis to extract the most representative feature vectors. The feature extraction process calculates the contribution of each feature, focusing on retaining the features that have a greater impact on quality assessment. Parameter matching ensures the balance between different types of features, and data fusion uses a weighted average method to integrate all features into the quality assessment data package.

[0115] For example: To evaluate a nail art with a three-dimensional pattern, multi-angle scanning collected data from 24 different angles. Each scanning angle records about 1 million data points to form the initial point cloud data. Surface feature analysis shows that the transition width of the pattern edge is in the range of 20-30 microns, which meets the clarity requirements. Color analysis found that in the gradual change from the center of the flower to the petals, the change in hue angle presents a smooth S-shaped curve, indicating that the gradient effect is natural. After mapping these data to the three-dimensional model, it was found that the spatial distribution of the texture is highly consistent with the color change, which together creates a three-dimensional effect. Data analysis shows that key indicators such as edge clarity, color uniformity, and three-dimensional restoration have met the expected standards, and the evaluation data package objectively records the quality characteristics of the product.

[0116] In a specific embodiment, the process of performing the numerical analysis step on the micro texture distribution, color level transition and spatial effect restoration state may specifically include the following steps:

[0117] (1) Perform regional statistics and frequency analysis on micro-texture distribution, and generate texture scoring data by calculating texture density and evaluating distribution uniformity;

[0118] (2) Calculate color difference and detect gradient according to color level transition, and output color scoring data through transition smoothness analysis and level distinction evaluation;

[0119] (3) The spatial effect restoration state is measured in stereoscopic degree and morphological comparison, and the spatial score data is calculated through spatial consistency analysis and restoration accuracy evaluation;

[0120] (4) Cross-validating the texture scoring data with the color scoring data, and generating initial evaluation parameters through data association and parameter correction;

[0121] (5) Perform multi-dimensional fusion of the initial evaluation parameters and spatial scoring data, and output a comprehensive scoring vector through weight allocation and parameter calibration;

[0122] (6) Data reconstruction and parameter mapping are performed based on the comprehensive score vector, and a quality assessment matrix is ​​generated through matrix transformation and numerical optimization.

[0123] Specifically, the micro texture distribution is partitioned. The partitioning process divides the entire pattern area into multiple sub-areas, each of which is 500×500 microns in size, to facilitate local feature analysis. Regional statistics calculate the texture feature parameters in each sub-area, including the directionality, continuity and regularity of the texture. Frequency analysis uses Fourier transform to convert texture features into frequency domain space and analyze the periodic characteristics of the texture. Texture density calculation counts the number of texture feature points per unit area, and combines comparative analysis of adjacent areas to evaluate the uniformity of texture distribution, generating texture scoring data containing multiple dimensions.

[0124] The analysis of color level transition first calculates the color difference in the Lab color space. The amplitude of color change is quantified by calculating the Euclidean distance between adjacent regions. The gradient detection uses the Sobel operator to calculate the direction and intensity of color change. The transition smoothness analysis focuses on the continuity of color change and evaluates the naturalness of the transition effect by calculating the gradient change rate. The level distinction evaluation analyzes the contrast between different color levels to ensure a clear sense of hierarchy. All these analysis results are combined to form color scoring data.

[0125] The evaluation of the restoration status of spatial effects uses three-dimensional measurement technology. Stereoscopic measurement evaluates the degree of stereoscopic effect by calculating the distribution characteristics of surface normal vectors. Morphological comparison analysis compares the actual printing effect with the original design and calculates the deviation of morphological characteristics. Spatial consistency analysis evaluates the coordination of the overall effect, and restoration accuracy evaluation quantifies the degree of match between the actual effect and the expected effect. These data together constitute the spatial scoring data.

[0126] The cross-validation phase of texture scoring data and color scoring data focuses on the coordination between the two. Data association analysis calculates the correlation between texture features and color features to find out the key parameters that influence each other. Parameter correction adjusts the parameters based on the results of association analysis to ensure the balance between the parameters and generate initial evaluation parameters.

[0127] Multi-dimensional fusion processing integrates the initial evaluation parameters with the spatial scoring data. Weight allocation considers the impact of different parameters on the overall quality, and important parameters are given higher weights. Parameter calibration ensures that all parameters are compared under a unified scoring standard, and a comprehensive scoring vector is output through weighted calculation.

[0128] The final data reconstruction converts the comprehensive score vector into a two-dimensional matrix form. Parameter mapping establishes the correspondence between the score results and the actual quality characteristics. Matrix transformation adjusts the expression of data to facilitate subsequent analysis and application. Numerical optimization removes outliers, smoothes data distribution, and forms a standardized quality assessment matrix.

[0129] For example, this work contains a gradient pattern. Zoning analysis shows that within a 1 square millimeter area, the distribution density of texture feature points remains at 200-250 / mm. 2 The color difference of the gradient process is within the range of 3-5 color difference units per 100 microns, which ensures the naturalness of the transition. The three-dimensional effect analysis shows that the range of the surface normal vector is between 15-20 degrees, reflecting a moderate three-dimensional sense. Cross-validation found that the spatial distribution of texture features is highly consistent with the color gradient, and the correlation coefficient is above 0.85. In the quality assessment matrix, all indicators meet the expected standards, and the overall score reflects the quality level of the product.

[0130] The parameter analysis in the quality assessment system also involves a deeper data processing process. In the micro-texture distribution analysis, each 500×500 micron sub-area is further subdivided into 25 100×100 micron micro-blocks. After Fourier transforming each micro-block, the spectrum distribution map is obtained. By analyzing the main frequency components and energy distribution of the spectrum, the periodic characteristics of the texture are extracted. At the same time, the gray level co-occurrence matrix is ​​used to calculate the statistical characteristics of the texture, such as contrast, entropy, energy and correlation. After these characteristic parameters are normalized, the texture feature vector of the area is formed.

[0131] In the color hierarchy analysis, CIE Lab color space is used for color difference calculation. The color difference value △E between adjacent pixels is calculated by Euclidean distance, while considering the combined influence of brightness difference △L and chromaticity difference △ab. For the gradient area, a dynamic threshold is set to judge the continuity of color transition. If the color difference change rate of the local area exceeds the threshold, it is marked as an unqualified area. The histogram analysis is used to evaluate the hierarchy distinction, and the peak-to-valley ratio of the color distribution is calculated to ensure the clarity of the color hierarchy. The restoration of the spatial effect is evaluated by three-dimensional reconstruction technology. The point cloud data obtained by multi-angle scanning is used to reconstruct the surface model using the Delaunay triangulation algorithm. The Hausdorff distance between the reconstructed surface and the design model is calculated to evaluate the accuracy of shape restoration. At the same time, the geometric characteristics of the surface, including the degree of concavity and convexity and the continuity of the surface, are evaluated by principal curvature analysis.

[0132] The analytic hierarchy process is used to determine the weights of various parameters in the data fusion stage. First, a judgment matrix is ​​established, and the weight coefficients of various indicators are obtained by eigenvalue calculation. During the parameter correction process, an adaptive compensation mechanism is set up to dynamically adjust the influence of different parameters according to their importance. In the process of generating the quality assessment matrix, principal component analysis is used to reduce the data dimension and retain the principal components with the largest contribution rate. At the same time, the correlation between various indicators is evaluated through covariance analysis to ensure the comprehensiveness and accuracy of the evaluation results.

[0133] The above describes the nail spray painting method based on artificial intelligence in the embodiment of the present application. The following describes the nail spray painting system based on artificial intelligence in the embodiment of the present application. Figure 2 In the embodiments of the present application, an embodiment of the nail painting system based on artificial intelligence includes:

[0134] The conversion module 201 is used to perform spatial stratification and visual parameter conversion on the nail art pattern selected by the user through the pattern processing system to obtain a pattern processing matrix including color gradient data, spatial gradient data and three-dimensional texture data;

[0135] The extraction module 202 is used to perform multi-band spectral scanning and surface feature extraction on the nail to be sprayed, obtain the microscopic morphology data and precise boundary mapping data of the nail, and generate a nail adaptation parameter package based on the pattern processing matrix;

[0136] The compensation module 203 is used to plan the spraying trajectory and dynamically compensate the flow rate of the isolation protection system according to the precise boundary mapping data and the microscopic morphology data, obtain a protective film layer with an adaptive thickness, and generate a film distribution map at the same time;

[0137] The adjustment module 204 is used to perform multi-dimensional environmental compensation and flow intelligent adjustment on the base color spraying system according to the color gradient data and the nail adaptation parameter package in combination with the film distribution map to obtain the base color bearing layer;

[0138] The control module 205 is used to control the 3D printing system to perform multi-layer staggered spraying based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, obtain a micro-nano pattern layer, and generate pattern layer structure data;

[0139] The monitoring module 206 is used to perform multi-dimensional stereoscopic scanning and real-time dynamic monitoring of the finished product according to the pattern layer structure data, and obtain a quality evaluation data package including micro-texture distribution, color level transition and spatial effect restoration status.

[0140] Through the coordinated cooperation of the above-mentioned components, by spatially stratifying and converting the visual parameters of the nail art pattern, the color gradient data, spatial gradient data and three-dimensional texture data of the pattern are effectively extracted, and the accurate quantification of the pattern features is achieved, laying a data foundation for subsequent processing. At the same time, based on multi-band spectral scanning and surface feature extraction technology, the microscopic morphology data and precise boundary mapping data of the nails are accurately obtained, which improves the recognition accuracy of the surface features of the nails. By planning the spraying trajectory and dynamically compensating the flow rate of the isolation protection system, the adaptive thickness control of the protective film layer is achieved, which effectively solves the uniformity problem of the isolation protection. Based on the color gradient data and the nail adaptation parameter package, combined with The thin film distribution map performs multi-dimensional environmental compensation and intelligent flow adjustment on the base color spraying system, ensuring the uniform transition effect of the base color bearing layer. Then, through multi-level staggered spraying control of the 3D stereoscopic spraying system, with the cooperation of spatial gradient data, three-dimensional texture data and the base color bearing layer, the construction of a micro-nano pattern layer with a spatial three-dimensional effect is successfully realized. Finally, multi-dimensional stereo scanning and real-time dynamic monitoring technology are used to conduct a comprehensive quality assessment of the finished product, and a quality assessment data package including micro-texture distribution, color level transition and spatial effect restoration is obtained. A complete quality control system has been established, which has significantly improved the accuracy and restoration of nail spraying through data-driven and intelligent control.

[0141] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein instructions are stored in the computer, and when the instructions are executed on a computer, the computer executes the steps of the artificial intelligence-based nail painting method.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0143] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0144] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A nail art spray painting method based on artificial intelligence, characterized in that: The artificial intelligence-based nail art spray painting method comprises: The pattern processing system performs spatial stratification and visual parameter conversion on the nail art pattern selected by the user to obtain a pattern processing matrix including color gradient data, spatial gradient data and three-dimensional texture data; Performing multi-band spectral scanning and surface feature extraction on the nails to be sprayed, obtaining microscopic morphology data and precise boundary mapping data of the nails, and generating a nail adaptation parameter package based on the pattern processing matrix; According to the precise boundary mapping data and the microscopic morphology data, spraying trajectory planning and flow rate dynamic compensation are performed on the isolation protection system to obtain a protective film layer with adaptive thickness, and a film distribution map is generated at the same time; According to the color gradient data and the nail adaptation parameter package, combined with the film distribution map, multi-dimensional environmental compensation and flow intelligent adjustment are performed on the base color spraying system to obtain a base color bearing layer; Based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, a 3D three-dimensional inkjet printing system is controlled to spray in multiple layers to obtain a micro-nano pattern layer, and pattern layer structure data is generated; The finished product is subjected to multi-dimensional stereoscopic scanning and real-time dynamic monitoring according to the pattern layer structure data to obtain a quality evaluation data package including micro texture distribution, color level transition and spatial effect restoration status.

2. The artificial intelligence-based nail painting method according to claim 1, characterized in that: The pattern processing system performs spatial stratification and visual parameter conversion on the nail art pattern selected by the user to obtain a pattern processing matrix containing color gradient data, spatial gradient data and three-dimensional texture data, including: The nail art pattern is processed by color conversion to generate a digital matrix, and the digital matrix is ​​quantized and segmented into RGB channels and the signal intensity is calibrated. After discrete Fourier transform processing, the RGB three-channel data is output; Nonlinear color mapping and cross correction are performed according to the RGB three-channel data, multi-dimensional quantitative analysis and gradient interpolation calculation are performed on the color parameters, and the color gradient data is generated through color gamut conversion and gradient reconstruction; Extracting a depth information sequence from the digital matrix, performing hierarchical mapping and dynamic range expansion according to brightness levels, and outputting the spatial gradient data through contrast enhancement and spatial compensation operations; The digital matrix is ​​subjected to high-frequency texture separation and low-frequency background filtering, and subjected to wavelet transformation and frequency domain decomposition processing, and the three-dimensional texture data is generated by texture feature extraction and recombinant synthesis; Normalizing the color gradient data, the spatial gradient data and the three-dimensional texture data in spatial coordinates, converting them into a unified coordinate system according to the principles of geometric transformation and projection mapping, and generating a three-dimensional data association table through data alignment and calibration; The three-dimensional data association table is subjected to principal component analysis and parameter dimension reduction, the inter-layer feature vector and association strength are calculated, and the pattern processing matrix is ​​generated through data optimization and redundancy elimination.

3. The artificial intelligence-based nail painting method according to claim 1, characterized in that: The method performs multi-band spectral scanning and surface feature extraction on the nail to be sprayed, obtains microscopic morphology data and precise boundary mapping data of the nail, and generates a nail adaptation parameter package based on the pattern processing matrix, including: The nail to be sprayed is illuminated by a multi-band light source, reflected light signals of different wavelengths are collected, and the reflected light signals are decomposed by wavelength and the intensity is calculated to obtain a spectrum data set; Perform multi-dimensional cross analysis and data reconstruction on the spectral data set, generate initial morphological feature points through spectral parameter correction and signal noise reduction processing; Construct a spatial coordinate sequence based on the initial morphological feature points, and calculate the microscopic morphological data through point cloud data reconstruction and error elimination; Detect edge features of the surface of the painted nails, calculate grayscale gradients and extract contours, combine curvature analysis and boundary tracking, and output accurate boundary mapping data; Matching and transforming the color gradient data, spatial gradient data and three-dimensional texture data in the pattern processing matrix with the microscopic morphology data, and generating initial adaptation parameters through geometric deformation compensation and data mapping; The initial adaptation parameters are spatially dimensional corrected and numerically optimized, and boundary constraint processing is performed in combination with the precise boundary mapping data to output a nail adaptation parameter package.

4. The artificial intelligence-based nail painting method according to claim 1, characterized in that: According to the precise boundary mapping data and the microscopic morphology data, the isolation protection system is subjected to spraying trajectory planning and flow rate dynamic compensation to obtain a protective film layer with adaptive thickness, and a film distribution map is generated at the same time, including: Extract boundary point sets from precise boundary mapping data, and generate spraying area boundary maps through spatial coordinate transformation and area segmentation processing; Calculate the surface curvature change according to the microscopic topography data, and output the spray height compensation value through numerical processing and parameter analysis; The spraying area boundary map is superimposed with the spraying height compensation value, and the spraying trajectory data of the isolation protection system is calculated through trajectory interpolation and path optimization processing; Calculate the flow distribution of the spray trajectory data, and output a dynamic flow control sequence through pressure parameter adjustment and flow rate compensation; Spraying of the protective film layer is performed according to a dynamic flow control sequence, and the protective film layer is generated through thickness sensing and feedback regulation; The protective film layer is spatially scanned and density distribution analyzed, and a film distribution map is output through data integration and parameter mapping.

5. The artificial intelligence-based nail painting method according to claim 1, characterized in that: The method of performing multi-dimensional environmental compensation and flow intelligent adjustment on the base color spraying system based on the color gradient data and the nail adaptation parameter package in combination with the film distribution map to obtain a base color bearing layer includes: Perform color space conversion and gradient distribution analysis on color gradient data, and generate background color distribution data through numerical calculation and parameter calibration; Calculate the surface curvature and divide the area according to the nail adaptation parameter package, and output the spraying compensation parameters through coordinate transformation and data reconstruction; Extract thickness variation data from the film distribution map, and calculate the spray pressure adjustment value through numerical analysis and parameter correction; The base color distribution data and the spraying compensation parameters are fused, and the spraying control sequence is generated through parameter optimization and data reconstruction; The base color is sprayed according to the spray pressure adjustment value and the spray control sequence, and the base color layer is output through data feedback and dynamic adjustment; The surface characteristics and uniformity of the base color layer are collected and analyzed, and the base color bearing layer is generated through data verification and parameter update.

6. The artificial intelligence-based nail painting method according to claim 1, characterized in that: The method of controlling the 3D printing system to spray in multiple layers based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer to obtain a micro-nano pattern layer and generate pattern layer structure data includes: Perform multi-level decomposition and numerical reconstruction on spatial gradient data, and output spatial rendering parameter sequence through stereo gradient analysis and parameter extraction; Extract depth information and surface features from stereo texture data, and generate texture control matrix through data conversion and feature mapping; Scan the surface profile and collect data of the base color bearing layer, and calculate the height compensation value through surface parameter analysis and numerical reconstruction; The spatial rendering parameter sequence is fused with the texture control matrix, and the spraying path sequence is output through hierarchical processing and parameter optimization. According to the height compensation value and the spraying path sequence, the spraying parameters are adjusted in detail and numerically corrected to generate a micro-nano pattern layer; The structural features of the micro-nano pattern layer are collected and the three-dimensional effect is analyzed. Through data integration and feature extraction, the pattern layer structural data is generated.

7. The artificial intelligence-based nail painting method according to claim 1, characterized in that: The method of performing multi-dimensional stereoscopic scanning and real-time dynamic monitoring on the finished product according to the pattern layer structure data to obtain a quality assessment data package including micro texture distribution, color level transition and spatial effect restoration status includes: Perform multi-angle scanning and in-depth analysis on the pattern layer structure data, and generate a test data set through parameter extraction and data reconstruction; Extract surface features from the detection data set, and output micro-texture distribution through data processing and morphological analysis; The color data in the detection data set is decomposed hierarchically, and the color level transition is calculated through gradient processing and contrast analysis; The micro texture distribution and color level transition are spatially mapped, and the spatial effect restoration state is generated through data integration and parameter extraction; Numerical analysis is performed on micro texture distribution, color level transition and spatial effect restoration status, and a quality assessment matrix is ​​generated through data verification and parameter optimization; Data synthesis and feature extraction are performed according to the quality assessment matrix, and quality assessment data packets are output through parameter matching and data fusion.

8. The artificial intelligence-based nail painting method according to claim 7, characterized in that: The numerical analysis of micro texture distribution, color level transition and spatial effect restoration state is performed, and a quality evaluation matrix is ​​generated through data verification and parameter optimization, including: Perform regional statistics and frequency analysis on micro texture distribution, and generate texture scoring data through texture density calculation and distribution uniformity evaluation; Calculate color difference and detect gradient according to color level transition, and output color scoring data through transition smoothness analysis and level distinction evaluation; The spatial effect restoration state is measured in stereoscopic degree and morphological comparison, and the spatial scoring data is calculated through spatial consistency analysis and restoration accuracy evaluation; The texture scoring data and the color scoring data are cross-validated, and initial evaluation parameters are generated through data association and parameter correction; Perform multi-dimensional fusion of initial evaluation parameters and spatial scoring data, and output a comprehensive scoring vector through weight allocation and parameter calibration; Data reconstruction and parameter mapping are performed according to the comprehensive score vector, and the quality assessment matrix is ​​generated through matrix transformation and numerical optimization.

9. An artificial intelligence-based nail painting system, used to implement the artificial intelligence-based nail painting method according to any one of claims 1 to 8, characterized in that: The artificial intelligence-based nail painting system includes: A conversion module, used to perform spatial stratification and visual parameter conversion on the nail art pattern selected by the user through the pattern processing system, and obtain a pattern processing matrix containing color gradient data, spatial gradient data and three-dimensional texture data; An extraction module is used to perform multi-band spectral scanning and surface feature extraction on the nails to be sprayed, obtain microscopic morphology data and precise boundary mapping data of the nails, and generate a nail adaptation parameter package based on the pattern processing matrix; A compensation module, for performing spraying trajectory planning and flow rate dynamic compensation for the isolation protection system according to the precise boundary mapping data and the microscopic morphology data, obtaining a protective film layer with adaptive thickness, and generating a film distribution map at the same time; An adjustment module, for performing multi-dimensional environmental compensation and flow intelligent adjustment on the base color spraying system according to the color gradient data and the nail adaptation parameter package in combination with the film distribution map, to obtain a base color bearing layer; A control module, for controlling the 3D printing system to perform multi-layer staggered spraying based on the spatial gradient data, the three-dimensional texture data and the base color bearing layer, to obtain a micro-nano pattern layer, and to generate pattern layer structure data; The monitoring module is used to perform multi-dimensional stereoscopic scanning and real-time dynamic monitoring of the finished product according to the pattern layer structure data, and obtain a quality evaluation data package including micro-texture distribution, color level transition and spatial effect restoration status.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the artificial intelligence-based nail painting method as described in any one of claims 1-8 is implemented.

Images