An automatic power adjustment method for a nail lamp, a nail lamp and a system

Abstract

This application relates to the technical field of energy-saving power consumption, and specifically relates to a method for automatically adjusting the power of a nail lamp, a nail lamp and a system. The method includes: obtaining the ultraviolet dose of each nail area on the palm during the irradiation of the nail lamp; collecting an image of the palm area during the irradiation of the nail lamp; using a target detection algorithm to obtain each nail area in the palm area image; determining the shape similarity measure between the palm currently irradiated by the nail lamp and the palm irradiated historically; obtaining the feature similarity coefficient between the palm currently irradiated by the nail lamp and the palm irradiated historically; determining an objective function based on the ultraviolet dose of all nail areas on the palm during the irradiation of the nail lamp, and combining with a particle swarm optimization algorithm to obtain the optimal ultraviolet dose of each nail area, so as to determine the power of the nail lamp; wherein, the inertia weight in the particle swarm optimization algorithm is determined based on the feature similarity coefficient. This application improves the accuracy of power adjustment of the nail lamp.

Description

Technical Field

[0001] This application relates to the technical field of energy-saving electricity use, and particularly relates to a method for automatically adjusting the power of a nail lamp, a nail lamp and a system. Background Art

[0002] During the nail art process, a nail lamp is needed to cure the nail phototherapy gel to improve the quality and durability of the nail art. When it is necessary to cure the nail phototherapy gel, the entire back of the hand is placed within the illumination range of the nail lamp. Since the commonly used nail lamp is an ultraviolet lamp, long-term irradiation will cause certain damage to the skin. Therefore, reasonably controlling the illumination intensity and time has become the key point to note when using a nail lamp. However, the commonly used nail lamps currently are usually of fixed power and cannot achieve relatively precise control of ultraviolet rays.

[0003] Due to the differences in the shapes and sizes of the fingers of different customers, and the nail art styles selected by the customers are also different, the ultraviolet intensities received by the nail phototherapy gels in different nail areas are inconsistent, resulting in certain differences in the curing conditions of the nail art in different nail areas, thus affecting the uniformity of the nail art effect. In order to automatically adjust the power of the nail lamp, an optimization algorithm is often used to iteratively obtain the optimal solution. However, in traditional optimization algorithms, all parameters are fixed values and cannot be adaptively adjusted according to the changes of particle conditions and objective functions, thus affecting the accuracy of the optimal solution and the iteration efficiency, resulting in errors in the power adjustment of the nail lamp. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a method for automatically adjusting the power of a nail lamp, a nail lamp and a system.

[0005] In a first aspect, an embodiment of this application provides a method for automatically adjusting the power of a nail lamp, and the method includes the following steps:

[0006] Obtain the ultraviolet dose of each nail area on the palm during the irradiation of the nail lamp; collect the palm area image during the irradiation of the nail lamp;

[0007] Use an object detection algorithm to obtain each nail area in the palm area image; respectively analyze the similarity of the area and aspect ratio of each nail area in the current irradiated palm image and the historical irradiated palm image of the nail lamp, and determine the shape similarity measure between the current irradiated palm and the historical irradiated palm of the nail lamp;

[0008] Obtain the measured distance between adjacent nail areas in the palm area image. Based on the difference in the measured distance between the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp, as well as the difference in the change amount of the area between adjacent nail areas and the difference in the change amount of the aspect ratio between adjacent nail areas, combine the shape similarity measure to determine the feature similarity coefficient between the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp;

[0009] Based on the ultraviolet dose of all nail areas of the palm during the irradiation of the nail lamp, determine the objective function, and combine the particle swarm optimization algorithm to obtain the optimal ultraviolet dose for each nail area, so as to determine the power of the nail lamp; wherein, determine the inertia weight in the particle swarm optimization algorithm based on the feature similarity coefficient.

[0010] In one embodiment, the determination process of the shape similarity measure is as follows:

[0011] Arrange the areas and aspect ratios of all nail areas in the palm in sequence to form an area sequence and an aspect ratio sequence respectively. Calculate the similarity of the area sequence between the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp, denoted as the first similarity. Calculate the similarity of the aspect ratio sequence between the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp, denoted as the second similarity. Combine the first similarity and the second similarity to obtain the shape similarity measure.

[0012] In one embodiment, the aspect ratio is the aspect ratio of the minimum circumscribed rectangle of each nail area in the palm area image.

[0013] In one embodiment, the determination of the feature similarity coefficient includes:

[0014] Calculate the measured distance between the centers of adjacent nail areas in the palm area image, arrange them in sequence to form a distance sequence, calculate the difference between the distance sequences of the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp, denoted as the first difference. Denote the difference in the change amount of the area between adjacent nail areas as the second difference, and denote the difference in the change amount of the aspect ratio between adjacent nail areas as the third difference;

[0015] Calculate the fusion result of the first difference, the second difference, and the third difference. The feature similarity coefficient is positively correlated with the shape similarity measure and negatively correlated with the fusion result.

[0016] In one embodiment, the acquisition process of the second difference is as follows:

[0017] Calculate the first-order difference sequence of the area sequence, obtain the integral area of the fitting curve of the first-order difference sequence, denoted as the first integral area, and denote the difference between the first integral areas of the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp as the second difference.

[0018] In one of the embodiments, the process of determining the third difference is as follows:

[0019] Calculate the first-order difference sequence of the aspect ratio sequence, obtain the integral area of the fitting curve of the first-order difference sequence, denoted as the second integral area, and denote the difference between the second integral area of the current palm irradiated by the nail lamp and the historical palm irradiated by the nail lamp as the third difference.

[0020] In one of the embodiments, the objective function is:

[0021] f(x) = ω1 × f1(x) + ω2 × f2(x); where f(x) is the objective function, ω1 is the preset first weight, ω2 is the preset second weight, f1(x) is the degree of dispersion of the ultraviolet dose of all nail areas of the palm during the irradiation of the nail lamp, and f2(x) is the sum of the ultraviolet doses of all nail areas of a single palm during the irradiation of the nail lamp. Among them, the optimization process of the particle swarm optimization algorithm is to minimize the objective function, and the constraint condition is that the sum is greater than or equal to the minimum ultraviolet dose required for the curing of the nail light-curing glue.

[0022] In one of the embodiments, the process of determining the inertia weight is as follows:

[0023] Calculate the mean value of the feature similarity coefficients between the current palm irradiated by the nail lamp and a preset number of historical palms irradiated by the nail lamp, and the inertia weight is the ratio of the preset initial inertia weight to the mean value.

[0024] Second, the embodiments of the present application also provide a nail lamp, and the power adjustment of the nail lamp is realized by the automatic power adjustment method of the nail lamp described in any one of the above.

[0025] Third, the embodiments of the present application also provide an automatic power adjustment system for a nail lamp, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are realized.

[0026] The present application has at least the following beneficial effects:

[0027] This application obtains the ultraviolet dose of each nail area on the palm during the irradiation of the nail lamp; collects the palm area image during the irradiation of the nail lamp; uses the target detection algorithm to obtain each nail area in the palm area image; analyzes the similarity of the area and aspect ratio of each nail area in the current irradiated palm and the historically irradiated palm of the nail lamp respectively, and determines the shape similarity measure between the current irradiated palm and the historically irradiated palm of the nail lamp; the shape similarity measure reflects the similarity degree of the nail areas between the two palms in shape, improving the reliability of the reference of the historically irradiated palm to the current irradiated palm; further, obtains the measurement distance between adjacent nail areas in the palm area image, and based on the difference in the measurement distance between the current irradiated palm and the historically irradiated palm of the nail lamp, as well as the difference in the change amount of the area between adjacent nail areas and the difference in the change amount of the aspect ratio between adjacent nail areas, combines the shape similarity measure to determine the feature similarity coefficient between the current irradiated palm and the historically irradiated palm of the nail lamp; the feature similarity coefficient reflects the similarity of the nail areas between the two palms under multiple features, improving the sensitivity and quantification accuracy of the difference recognition of the nail areas; finally, based on the ultraviolet dose of all nail areas on the palm during the irradiation of the nail lamp, determines the objective function, combines the particle swarm optimization algorithm, and obtains the optimal ultraviolet dose of each nail area, thereby determining the power of the nail lamp; ensuring the uniformity of the curing of the nail area nail phototherapy gel and reducing unnecessary ultraviolet irradiation; wherein, determines the inertia weight in the particle swarm optimization algorithm based on the feature similarity coefficient, improving the accuracy of the global and local adaptive adjustment of the optimization algorithm, while taking into account the accuracy of the optimal solution and the iteration efficiency of the optimization algorithm, improving the accuracy of the power adjustment of the nail lamp. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0029] Figure 1 It is a flowchart of the steps of a method for automatically adjusting the power of a nail lamp provided by the present application;

[0030] Figure 2 It is a flowchart for determining the inertia weight. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] To further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a method for automatically adjusting the power of a nail lamp, a nail lamp, and a system according to this application, including their specific implementation manners, structures, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0033] The following specifically describes the specific solutions of a method for automatically adjusting the power of a nail lamp, a nail lamp, and a system provided by this application in conjunction with the accompanying drawings.

[0034] Please refer to Figure 1 , which shows a flowchart of the steps of a method for automatically adjusting the power of a nail lamp provided by an embodiment of this application. The method includes the following steps:

[0035] Step S001, obtaining the ultraviolet dose of each nail area on the palm during the irradiation of the nail lamp; collecting the palm area image during the irradiation of the nail lamp.

[0036] In this embodiment, a camera is placed at a fixed position directly above the nail operation area to capture the palm area image at the initial moment of the nail lamp irradiation, so that the palm area can completely appear in the captured palm area image. The Gaussian filtering algorithm is used to denoise the palm area image. In this embodiment, the HOG (Histogram of Oriented Gradients) + SVM (Support Vector Machines) object detection algorithm is used to obtain each nail area in the palm area image. The Gaussian filtering algorithm and the HOG + SVM object detection algorithm are both well-known existing technologies. Implementers can select other feasible filtering algorithms and object detection algorithms according to the actual situation. This embodiment does not limit them here.

[0037] The nail lamp is placed directly above the center position of the nail area to obtain the ultraviolet dose of each nail area during the irradiation of the nail lamp. Among them, the method for obtaining the ultraviolet dose of each nail area is as follows: First, according to the positional relationship between the nail lamp and the nail area, obtain the ultraviolet intensity of the nail area, and based on the ultraviolet intensity and irradiation time of the nail area, obtain the ultraviolet dose of the nail area.

[0038] It should be noted that the acquisition of the ultraviolet intensity of the nail area and the ultraviolet dose of the nail area are both well-known existing technologies, and this embodiment does not elaborate on them in detail here.

[0039] Step S002, respectively analyzing the similarities of the area and aspect ratio of each nail region in the palm region image of the palm currently illuminated by the nail lamp and the palm illuminated in the past, and determining the shape similarity measure between the palm currently illuminated by the nail lamp and the palm illuminated in the past.

[0040] During manicure, because the shapes and sizes of customers' fingers are not exactly the same, and the nail styles they choose are not exactly the same, it is necessary to choose different powers to cure the nail phototherapy glue in a targeted manner. However, existing nail lamps often use fixed power to irradiate until the nail phototherapy glue is completely cured, and a large amount of unnecessary ultraviolet damage may be generated in this process. However, existing nail lamps cannot perform adaptive power adjustment, making this damage unavoidable. In order to adaptively adjust the power of the nail lamp, it is necessary to select the optimal power according to the shape of the customer's nails and the intensity of ultraviolet rays received by the nails.

[0041] During the manicure process, the length, size, and shape of the nails corresponding to different nail styles are not exactly the same, which results in certain differences in the identified nail areas. When the nail styles of two different palms are closer, the features of the nail areas are more similar, which results in the corresponding nail lamp powers being closer. Secondly, when using a nail lamp, each nail area will be irradiated with a certain power for a period of time. Therefore, when adjusting the power of the nail lamp, in addition to the differences in nail styles between different palms, the differences between different nail areas in the same palm are also factors that affect the power adjustment of the nail lamp. In addition, the placement of the palm under the nail lamp and the distance between different fingers are not exactly the same, which will also affect the ultraviolet intensity of different nail areas and the curing effect of the nail phototherapy glue. Therefore, these differences are also factors that need to be considered when adjusting the power of the nail lamp.

[0042] The main reason why different nail art styles cause changes in the power adjustment of the nail lamp is the difference in appearance shape, and the difference in appearance shape can be obtained through the area and aspect ratio of the nail area. Based on the above analysis, the boundary pixel point set of each nail area and the minimum circumscribed rectangle of each nail area are used as input, and the Monte Carlo method is used to obtain the area of ​​each nail area, and the areas of all nail areas in the palm area image are arranged in clockwise order to form an area sequence, and the ratio of the length to the width of the minimum circumscribed rectangle of each nail area is calculated, which is recorded as the aspect ratio, and the aspect ratios of all nail areas in the palm area image are arranged in clockwise order to form an aspect ratio sequence. Among them, the Monte Carlo method is an existing well-known technology, and this embodiment will not be described in detail here.

[0043] Calculate the similarity between the area sequences of the current palm irradiated by the manicure lamp and the historical palm irradiated, denoted as the first similarity. Calculate the similarity between the aspect ratio sequences of the current palm irradiated by the manicure lamp and the historical palm irradiated, denoted as the second similarity. Take the sum of the first similarity and the second similarity as the shape similarity measure between the current palm irradiated by the manicure lamp and the historical palm irradiated.

[0044] It should be noted that in this embodiment, the calculation method of similarity is cosine similarity. Implementers can choose other existing feasible similarity calculation methods according to actual situations, such as Pearson correlation coefficient, etc. The calculation of cosine similarity is a well-known existing technology, and this embodiment will not elaborate on it in detail here.

[0045] Step S003: Obtain the measurement distance between adjacent nail areas in the palm area image. Based on the difference in the measurement distance between the current palm irradiated by the manicure lamp and the historical palm irradiated, as well as the difference in the change amount of the area between adjacent nail areas and the difference in the change amount of the aspect ratio between adjacent nail areas, and combine the shape similarity measure to determine the feature similarity coefficient between the current palm irradiated by the manicure lamp and the historical palm irradiated.

[0046] In addition, in the palm area image, calculate the measurement distance between the center of each nail area and the center of its adjacent nail area, and arrange them in clockwise order to form a distance sequence. Calculate the difference between the distance sequences of the current palm irradiated by the manicure lamp and the historical palm irradiated, denoted as the first difference. Calculate the difference in the change amount of the area between the adjacent nail areas of the current palm irradiated by the manicure lamp and the historical palm irradiated, denoted as the second difference. Calculate the difference in the change amount of the aspect ratio between the adjacent nail areas of the current palm irradiated by the manicure lamp and the historical palm irradiated, denoted as the third difference.

[0047] It should be noted that in this embodiment, the calculation method of the measurement distance is Euclidean distance. Implementers can choose other existing feasible distance calculation methods according to actual situations, such as Manhattan distance, DTW distance, etc. This embodiment does not limit it here; the difference represents the degree of difference between two variables, and specifically, the absolute value of the difference, the square of the difference, or the measurement distance can be used for calculation. In this embodiment, the Manhattan distance between the distance sequences of the current palm irradiated by the manicure lamp and the historical palm irradiated is determined as the first difference.

[0048] In this embodiment, the calculation method of the second difference is as follows: calculate the first-order difference sequence of the area sequence corresponding to each palm area image, use the least squares method to obtain the fitting curve of the first-order difference sequence, calculate the integral area of the fitting curve, denoted as the first integral area, and take the absolute value of the difference between the first integral areas of the current irradiated palm and the historical irradiated palm of the nail lamp as the second difference. The least squares method and the acquisition of the integral area are both well-known prior arts, and will not be elaborated in detail in this embodiment.

[0049] In this embodiment, the calculation method of the third difference is as follows: calculate the first-order difference sequence of the aspect ratio sequence corresponding to each palm area image, use the least squares method to obtain the fitting curve of the first-order difference sequence of the aspect ratio sequence, and calculate the integral area of the fitting curve, denoted as the second integral area, and take the absolute value of the difference between the second integral areas of the current irradiated palm and the historical irradiated palm of the nail lamp as the third difference.

[0050] Calculate the fusion result of the first difference, the second difference, and the third difference. The feature similarity coefficient between the current irradiated palm and the historical irradiated palm of the nail lamp is positively correlated with the shape similarity measure and negatively correlated with the fusion result.

[0051] It should be understood that fusion means combining multiple variables, and specific calculation methods such as multiplication, addition, and a combination of addition and multiplication can be used. In this embodiment, the sum of the second difference and the third difference is calculated, and the product of the sum and the first difference is used as the fusion result; positive correlation means that the dependent variable increases as the independent variable increases and decreases as the independent variable decreases, and negative correlation means that the dependent variable decreases as the independent variable increases and increases as the independent variable decreases.

[0052] In this embodiment, the calculation method of the feature similarity coefficient between the current irradiated palm and the historical irradiated palm of the nail lamp is as follows:

[0053] In the formula, A is the feature similarity coefficient between the current irradiated palm and the historical irradiated palm of the nail lamp, T is the shape similarity measure between the current irradiated palm and the historical irradiated palm of the nail lamp, m is the first difference, ΔE is the sum of the second difference and the third difference, m×ΔE is the fusion result, and ε is a preset value greater than 0 to avoid the denominator being 0. In this embodiment, ε = 0.01, and the implementer can set it according to the actual situation without limitation in this embodiment.

[0054] It can be understood that when doing manicures, the greater the similarity between the nail areas of the two palms, that is, the higher the similarity of the area and aspect ratio of the nail areas, the greater the shape similarity measure, and thus the greater the feature similarity coefficient between the two palms. At the same time, when the difference in the change amount of the area of the adjacent nail areas between the two palms is smaller, that is, the second difference is smaller, and the difference in the change amount of the aspect ratio of the adjacent nail areas between the two palms is smaller, that is, the third difference is smaller, and the difference in the nail placement position is also smaller, that is, the first difference is smaller, it reflects a higher similarity degree between the nail areas of the two palms, and the greater the feature similarity coefficient between the two palms is obtained.

[0055] Step S004: Based on the ultraviolet dose of all nail areas of the palm during the irradiation of the manicure lamp, determine the objective function, and combine it with the particle swarm optimization algorithm to obtain the optimal ultraviolet dose for each nail area, so as to determine the power of the manicure lamp; wherein, the inertia weight in the particle swarm optimization algorithm is determined based on the feature similarity coefficient.

[0056] In order to adaptively adjust the power of the manicure lamp, it is necessary to use an intelligent optimization algorithm to iteratively find the optimal power of the manicure lamp. In this embodiment, the particle swarm optimization algorithm is used to obtain the optimal power of the manicure lamp. First, determine the objective function of the particle swarm optimization algorithm. When using the manicure lamp to cure the manicure phototherapy gel, the closer the ultraviolet doses received by each nail area are, the more consistent the curing effects of each nail will be, so that the manicure effects and qualities of each nail will be closer; secondly, since the manicure lamp is an ultraviolet lamp, it will cause certain damage to the skin when irradiating the palm, so when the ultraviolet dose received by the entire palm area is smaller, the power control of the manicure lamp is better. Based on the above analysis, the objective function can be determined as:

[0057] f(x) = ω1×f1(x) + ω2×f2(x); where f(x) is the objective function, ω1 is the preset first weight, ω2 is the preset second weight, f1(x) is the dispersion degree of the ultraviolet doses of all nail areas of a single palm during the irradiation of the manicure lamp, and f2(x) is the sum of the ultraviolet doses of all nail areas of the palm during the irradiation of the manicure lamp. Among them, the optimization process of the particle swarm optimization algorithm is to minimize the objective function, and the constraint condition is that the sum is greater than or equal to the minimum ultraviolet dose required for curing the manicure phototherapy gel.

[0058] It should be understood that the dispersion degree can be specifically obtained by means of variance, standard deviation, coefficient of variation, etc. In this embodiment, variance is used as the calculation method for the dispersion degree.

[0059] In this embodiment, ω1 = 0.7 and ω2 = 0.3. To ensure the consistency of the nail art curing effect in each nail area, a larger weight is given to f1(x). The implementer can determine the values of ω1 and ω2 according to the actual situation, and this embodiment does not limit them here.

[0060] In addition, to ensure the quality of the nail art, this embodiment constructs a constraint condition, specifically that the cumulative sum of the ultraviolet doses of all nail areas of the palm during the irradiation of the nail lamp needs to be greater than or equal to the minimum ultraviolet dose required for the curing of the nail gel polish. Among them, the minimum ultraviolet dose is a known parameter when the nail gel polish leaves the factory.

[0061] However, when using the particle swarm optimization algorithm to iterate the optimal power, since the parameters of the traditional particle swarm optimization algorithm are fixed and the ability of adaptive adjustment is poor, it cannot be adaptively adjusted according to the particle situation to balance the globality and locality of the algorithm, and improve the iteration efficiency of the optimal solution while ensuring the accuracy of the optimal solution. The particle situation can be measured according to the characteristics of the palm nail area. Therefore, in order to improve the sensitivity of identifying the differences between particles, this embodiment determines the inertia weight in the particle swarm optimization algorithm based on the feature similarity coefficient between the current palm irradiated by the nail lamp and the historical irradiated palm, specifically:

[0062] During the optimization process of the particle swarm optimization algorithm, in this embodiment, when the nail lamp irradiates during the historical nail art process, the ultraviolet doses of all nail areas of each palm are arranged in clockwise order of the nail area to form the initial particles, which can avoid the randomness of the generation of the initial particles, thereby improving the efficiency of the optimization algorithm to a certain extent. In this embodiment, the number of initial particles z = 50, which means that the ultraviolet doses corresponding to z palms in the historical nail art process are selected as the initial particles. The particle dimension I = 5, corresponding to the ultraviolet doses of each nail area in turn during the irradiation process of the nail lamp. The maximum number of iterations d = 100, and both the individual learning factor and the social learning factor are 1.5. The implementer can set the number of initial particles, the maximum number of iterations, the individual learning factor, and the social learning factor according to the actual situation, and this embodiment does not limit them here. The process of using the particle swarm optimization algorithm for optimization is to minimize the objective function. The particle swarm optimization algorithm is a well-known prior art, and this embodiment does not elaborate on it in detail here.

[0063] Using the particle swarm optimization algorithm, iteratively obtain the optimal power of the nail lamp for each nail area when curing the nail polish on the current palm with light therapy glue. In the original particle swarm optimization algorithm, the inertia weight is fixed and cannot be adaptively adjusted, thus affecting the efficiency and accuracy of the algorithm. In fact, when the difference between the historical palm corresponding to the initial particle and the current palm is large, it is necessary to improve the global search ability, thereby improving the optimization efficiency of the optimization algorithm; when the difference between the historical palm corresponding to the initial particle and the current palm is smaller, it is necessary to improve the local search ability, thereby improving the accuracy of the optimal solution; therefore, it is necessary to adaptively adjust the inertia weight according to the difference between the palm corresponding to the initial particle and the current palm. The difference between the palm corresponding to the initial particle and the current palm can be measured by the feature similarity coefficient, and the specific calculation method of the inertia weight is as follows:

[0064] In the formula, ω is the inertia weight after adaptive adjustment, ω0 is the initial inertia weight, in this embodiment, ω0 = 0.5, and the implementer can adjust it according to the actual situation, and this embodiment does not limit it here. M is the mean value of the feature similarity coefficients between the palms corresponding to all initial particles and the current palm. In this embodiment, it is the mean value of the feature similarity coefficients between the palms corresponding to z initial particles and the current palm. The flowchart for determining the inertia weight is as Figure 2 shown.

[0065] It can be understood that when the similarity between the palm corresponding to the initial particle and the current palm is higher, the difference between the corresponding nail areas is smaller, so the feature similarity coefficient is larger, that is, M is larger, and the inertia weight ω is smaller, which helps to enhance the local search ability and improve the accuracy of the optimal solution. On the contrary, when the similarity between the palm corresponding to the initial particle and the current palm is smaller, the feature similarity coefficient is smaller, that is, M is smaller, so the inertia weight ω is larger, and the global search ability is stronger, which helps to improve the optimization efficiency of the algorithm.

[0066] Based on the inertia weight after adaptive adjustment, use the particle swarm optimization algorithm to optimize the objective function, and the optimal ultraviolet dose for each nail area when the current palm is irradiated by the nail lamp can be obtained. Based on the optimal ultraviolet dose, the optimal power of the nail lamp for each nail area during irradiation can be deduced inversely, and the automatic adjustment of the nail lamp power is completed.

[0067] It should be noted that when the optimal power of the nail lamp for each nail area during irradiation can be deduced inversely based on the optimal ultraviolet dose, in this embodiment, the irradiation time of the nail lamp is fixed at 10s to minimize the damage to the skin caused by ultraviolet irradiation. The implementer can adjust it according to the actual situation, and this embodiment does not limit it here.

[0068] The embodiment of the present application also provides a nail lamp, and the power adjustment of the nail lamp is realized by the automatic power adjustment method of the nail lamp described in any one of the above.

[0069] Based on the same inventive concept as the above method, an embodiment of the present application further provides a nail lamp automatic power adjustment system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for automatically adjusting the power of a nail lamp are implemented.

[0070] It should be noted that: the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0072] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; modifying the technical solutions recorded in the foregoing embodiments, or equivalently replacing some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of each embodiment of the present application, and should all be included within the protection scope of the present application.

Claims

1. A method for automatic power adjustment of a nail lamp, characterized in that: The method comprises the following steps: Obtaining the ultraviolet dose of each nail area of ​​the palm during the irradiation of the nail lamp; collecting the palm area image during the irradiation of the nail lamp; Using a target detection algorithm to obtain each nail region in the palm region image; analyzing the similarity of the area and aspect ratio of each nail region in the image of the palm currently illuminated by the nail lamp and the palm historically illuminated by the nail lamp, respectively, to determine the shape similarity measure between the palm currently illuminated by the nail lamp and the palm historically illuminated by the nail lamp; Obtaining the metric distance between adjacent nail regions in the palm region image, and determining the feature similarity coefficient between the palm currently illuminated by the nail lamp and the palm historically illuminated based on the difference in the metric distance between the palm currently illuminated by the nail lamp and the palm historically illuminated, as well as the difference in the amount of change in the area between adjacent nail regions and the difference in the amount of change in the aspect ratio between adjacent nail regions, combined with the shape similarity metric; Based on the ultraviolet dose of all nail areas of the palm during irradiation by the nail lamp, the objective function is determined, and the optimal ultraviolet dose of each nail area is obtained in combination with the particle swarm optimization algorithm, thereby determining the power of the nail lamp; wherein, the inertia weight in the particle swarm optimization algorithm is determined based on the feature similarity coefficient.

2. The method for automatic power adjustment of a nail lamp as claimed in claim 1, characterized in that: The process of determining the shape similarity measure is: The areas and aspect ratios of all nail regions in the palm are arranged in sequence to form an area sequence and an aspect ratio sequence, and the similarity of the area sequence between the palm currently irradiated by the nail lamp and the palm historically irradiated is calculated, which is recorded as the first similarity. The similarity of the aspect ratio sequence between the palm currently irradiated by the nail lamp and the palm historically irradiated is calculated, which is recorded as the second similarity. The first similarity and the second similarity are combined to obtain the shape similarity measure.

3. The method for automatic power adjustment of a nail lamp as claimed in claim 2, characterized in that: The aspect ratio is the aspect ratio of the minimum circumscribed rectangle of each nail area in the palm area image.

4. The method for automatic power adjustment of a nail lamp as claimed in claim 2, characterized in that: The determination of the feature similarity coefficient includes: Calculate the metric distances between the centers of adjacent nail regions in the palm region image, arrange them in sequence to form a distance sequence, calculate the difference between the distance sequences of the palm currently irradiated by the nail lamp and the palm irradiated in the past, record it as the first difference, record the difference in the amount of change of the area between adjacent nail regions as the second difference, and record the difference in the amount of change of the aspect ratio between adjacent nail regions as the third difference; A fusion result of the first difference, the second difference, and the third difference is calculated, and the feature similarity coefficient is positively correlated with the shape similarity measure and negatively correlated with the fusion result.

5. The method for automatic power adjustment of a nail lamp as claimed in claim 4, characterized in that: The process of obtaining the second difference is: The first-order difference sequence of the area sequence is calculated, and the integral area of ​​the fitting curve of the first-order difference sequence is obtained, which is recorded as the first integral area. The difference between the first integral area of ​​the palm currently irradiated by the nail lamp and the palm irradiated historically is recorded as the second difference.

6. The method for automatic power adjustment of a nail lamp as claimed in claim 4, characterized in that: The process of determining the third difference is: Calculate the first-order difference sequence of the aspect ratio sequence, obtain the integral area of ​​the fitting curve of the first-order difference sequence, record it as the second integral area, and record the difference between the second integral area of ​​the palm currently irradiated by the nail lamp and the palm irradiated historically as the third difference.

7. The method for automatic power adjustment of a nail lamp as claimed in claim 1, characterized in that: The objective function is: f(x)=ω1×f1(x)+ω2×f2(x); wherein f(x) is the objective function, ω1 is the preset first weight, ω2 is the preset second weight, f1(x) is the discrete degree of the ultraviolet dose of all nail areas of a single palm during the irradiation of the nail lamp, and f2(x) is the cumulative sum of the ultraviolet doses of all nail areas of the palm during the irradiation of the nail lamp. The optimization process of the particle swarm optimization algorithm is to minimize the objective function, and there is a constraint condition that the cumulative sum is greater than or equal to the minimum ultraviolet dose required for the curing of the nail phototherapy glue.

8. The method for automatic power adjustment of a nail lamp as claimed in claim 1, characterized in that: The process of determining the inertia weight is: The mean of the feature similarity coefficients between the palm currently illuminated by the nail lamp and a preset number of palms illuminated in history is calculated, and the inertia weight is the ratio of the preset initial inertia weight to the mean.

9. A nail lamp, using the method for automatic power adjustment of a nail lamp as claimed in claim 1, characterized in that: The power regulation of the nail lamp is achieved by using an automatic power regulation method for a nail lamp as described in any one of claims 1-8.

10. A nail lamp automatic power adjustment system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images