Sunscreen smearing detection method and device and storage medium

Abstract

The invention discloses a sunscreen smearing detection method and device and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: collecting UV images of the face of a user at at least two preset angles through an ultraviolet imaging device, inputting each UV image into a pre-training image segmentation model, and obtaining a pre-training image segmentation model; the method comprises the steps of generating a target image containing a reflective interference mark and a sunscreen substance mark, then determining an effective sunscreen area according to the reflective interference mark and the sunscreen substance mark in the target image, and then mapping the effective sunscreen area to a face reference coordinate system. Calculating the area proportion of the effective sunscreen area relative to the total area of the face, and finally generating a sunscreen smearing detection result based on the area proportion. According to the method, the target image is generated through the UV image and the pre-trained image segmentation model, the effective sunscreen area is determined in combination with the reflective interference mark and the sunscreen substance mark, and the sunscreen smearing effect is evaluated, so that the sunscreen smearing detection effect is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a method, device, and storage medium for detecting sunscreen application. Background Art

[0002] Currently, traditional sunscreen application detection generally uses the Sun Protection Factor (SPF) test method to detect the application effect. The SPF test method uses an ultraviolet spectrometer to irradiate the skin when using a sunscreen product and the skin when not using a sunscreen product, and calculates the SPF value by the ratio of the doses of erythema generated under ultraviolet irradiation at specific wavelengths, and then judges the sunscreen effect according to the SPF value. The higher the SPF value, the better the application effect of the sunscreen product. However, in actual applications, the above method will affect the final detection result of sunscreen application due to individual skin differences, resulting in poor detection effect of traditional solutions for sunscreen application.

[0003] The above content is only used to assist in understanding the technical solution of this application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] This application provides a method, device, and storage medium for detecting sunscreen application, aiming to solve the problem of poor detection effect of traditional solutions for sunscreen application.

[0005] To achieve the above object, a method for detecting sunscreen application provided by this application includes the following steps:

[0006] Collect UV images of the user's face at at least two preset angles through an ultraviolet imaging device;

[0007] Input each of the UV images into a pre-trained image segmentation model to generate a target image including a specular interference marker and a sunscreen substance marker;

[0008] Determine an effective sunscreen area according to the specular interference marker and the sunscreen substance marker in the target image;

[0009] Map the effective sunscreen area to a facial reference coordinate system, and calculate the area ratio of the effective sunscreen area to the total facial area;

[0010] Generate a detection result of sunscreen application based on the area ratio.

[0011] In one embodiment, the step of determining an effective sunscreen area according to the specular interference marker and the sunscreen substance marker in the target image includes:

[0012] Determine a matching weight value according to the reflective intensity and area information of the reflective interference mark, and associate the corresponding weight value with the reflective interference mark in the target image;

[0013] In the target images at different angles, determine the weighted sum of the weight values corresponding to the reflective interference marks in the same physical area;

[0014] When the weighted sum is less than a preset threshold, determine the physical area as the effective sunscreen area.

[0015] In one embodiment, after the step of generating a detection result of sunscreen application based on the area ratio, the method further includes:

[0016] Determine the user's application effect according to the comparison result between the detection result and historical detection data;

[0017] When the application effect is that the area ratio of the effective sunscreen area decreases, generate application improvement information according to the historical detection data;

[0018] Determine a matching sunscreen product and corresponding sunscreen product usage suggestions based on the user's skin type information;

[0019] Feedback the application improvement information and the sunscreen product usage suggestions to the corresponding user interface.

[0020] In one embodiment, after the step of generating a detection result of sunscreen application based on the area ratio, the method further includes:

[0021] Obtain a sunscreen coverage distribution map including the detection result;

[0022] In the sunscreen coverage distribution map, render the effective sunscreen coverage area and the uncovered area as a first visualization color and a second visualization color respectively;

[0023] Render the updated sunscreen coverage distribution map to the corresponding interface for display.

[0024] In one embodiment, after the step of obtaining a sunscreen coverage distribution map including the detection result, the method further includes:

[0025] Determine the coverage rate of the key parts according to the area size of the uncovered area, where the coverage rate is the ratio of the area of the uncovered area to the total area of the face;

[0026] When it is detected that the uncovered rate of the area corresponding to the key part is lower than a critical value, trigger a key re-application reminder;

[0027] Feedback the key re-application reminder to the user interface.

[0028] In one embodiment, after the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device, the method further includes:

[0029] Real-time detecting the current facial pose information;

[0030] Determining the deviation value between the user's face and the ultraviolet imaging device according to the facial pose information;

[0031] Adjusting the acquisition parameters of the ultraviolet imaging device according to the deviation value;

[0032] Executing the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device according to the adjusted ultraviolet acquisition device.

[0033] In one embodiment, after the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device, the method further includes:

[0034] Synchronously collecting color images of the user's face at at least two preset angles by a color camera;

[0035] Performing spatial registration on the UV image and the color image based on a feature point matching algorithm to generate corrected UV images and color images;

[0036] Mapping the purple spectrum of the corrected UV image to the color spectrum interval to generate a color-adjusted UV image;

[0037] Performing pixel superposition and fusion on the color-adjusted UV image and the corrected color image to generate a composite image and outputting the composite image through a display interface.

[0038] In one embodiment, the step of performing spatial registration on the UV image and the color image based on a feature point matching algorithm to generate corrected UV images and color images includes:

[0039] Extracting the feature point sets in the UV image and the color image and generating feature descriptors of the feature point sets;

[0040] Determining the target feature points that match in the feature point sets according to the feature descriptors;

[0041] Aligning the spatial coordinate systems of the UV image and the color image according to the target feature points to generate corrected UV images and color images.

[0042] In addition, to achieve the above object, the present application further provides a sunscreen application detection device, where the sunscreen application detection device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the sunscreen application detection method as described above.

[0043] In addition, to achieve the above object, the present application further provides a storage medium, where the storage medium is a computer-readable storage medium, and a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the sunscreen application detection method as described above are implemented.

[0044] The present application provides a sunscreen application detection method, a sunscreen application detection device, and a storage medium. By using an ultraviolet imaging device to collect UV images of the user's face at at least two preset angles, and then inputting each of the UV images into a pre-trained image segmentation model to generate a target image including a specular interference marker and a sunscreen substance marker, then determining an effective sunscreen area according to the specular interference marker and the sunscreen substance marker in the target image, then mapping the effective sunscreen area to a facial reference coordinate system, and calculating the area ratio of the effective sunscreen area to the total facial area, and finally generating a detection result of the sunscreen application based on the area ratio. In this embodiment, UV images are collected by an ultraviolet imaging device, and a pre-trained image segmentation model is used to generate a target image. By combining the specular interference marker and the sunscreen substance marker, an effective sunscreen area is determined. Finally, the sunscreen application effect is evaluated by the area ratio. This method can accurately and quickly detect the coverage rate of the user's sunscreen application, thereby improving the detection effect of the sunscreen application. Description of the Drawings

[0045] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0046] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a flowchart of the first embodiment of the sunscreen application detection method of the present application;

[0048] Figure 2 It is a flowchart of the second embodiment of the sunscreen application detection method of the present application;

[0049] Figure 3It is a schematic flowchart of the third embodiment of the sunscreen application detection method of this application;

[0050] Figure 4 It is a schematic architecture diagram of the hardware operating environment of the sunscreen application detection device involved in the embodiment of this application.

[0051] The implementation, functional features and advantages of the purpose of this application will be further described with reference to the embodiments and the accompanying drawings. Specific Embodiments

[0052] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0053] To better understand the above technical solutions, the exemplary embodiments of this application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0054] To better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners.

[0055] The main solution of this application is: collecting UV images of the user's face at at least two preset angles through an ultraviolet imaging device; inputting each of the UV images into a pre-trained image segmentation model to generate a target image including a specular interference marker and a sunscreen substance marker; determining an effective sunscreen area according to the specular interference marker and the sunscreen substance marker in the target image; mapping the effective sunscreen area to a facial reference coordinate system, and calculating the area ratio of the effective sunscreen area to the total facial area; generating a detection result of the sunscreen application based on the area ratio.

[0056] Currently, most of the existing sunscreen application detection methods on the market rely on simple color comparison techniques. In the above method, the user applies the sunscreen product by themselves, and then observes the skin color change under a specific light source to judge whether the sunscreen is evenly applied. However, in actual applications, the above depends on the subjective feedback of the user and cannot comprehensively reflect the sunscreen situation of the user's face, which results in poor detection effects of traditional solutions for sunscreen application.

[0057] Collect UV images of the user's face at at least two preset angles through an ultraviolet imaging device, then input each of the UV images into a pre-trained image segmentation model to generate a target image including a specular interference marker and a sunscreen marker, and then determine an effective sunscreen area according to the specular interference marker and the sunscreen marker in the target image. Next, map the effective sunscreen area to a facial reference coordinate system, calculate the area ratio of the effective sunscreen area to the total facial area, and finally generate a detection result of sunscreen application based on the area ratio. In this embodiment, UV images are collected through an ultraviolet imaging device, and a pre-trained image segmentation model is used to generate a target image. By combining the specular interference marker and the sunscreen marker, the effective sunscreen area is determined. Finally, the sunscreen application effect is evaluated through the area ratio. This method can accurately and quickly detect the coverage rate of the user's sunscreen application, thereby improving the detection effect of sunscreen application.

[0058] It should be noted that the execution subject of this embodiment can be a smear detection system, or a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a sunscreen smear detection device capable of implementing the above functions. This embodiment does not make specific limitations in this regard. Hereinafter, taking the smear detection system as the execution subject as an example, this embodiment and the following embodiments will be described.

[0059] Embodiment 1

[0060] Based on this, an embodiment of the present application provides a method for detecting sunscreen application. Refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the sunscreen application detection method of the present application. The sunscreen application detection method includes steps S10 to S50:

[0061] Step S10: Collect UV images of the user's face at at least two preset angles through an ultraviolet imaging device.

[0062] In this embodiment, the smear detection system performs the processing action. The ultraviolet imaging device is communicatively connected to the smear detection system. The smear detection system can be set in a smart dressing mirror or in other smart terminals. The ultraviolet imaging device is a device that can capture the reflection and absorption of ultraviolet rays, and can convert invisible ultraviolet information into a visual image. It can also be a dedicated imaging device equipped with a UV filter and a high-sensitivity sensor, and the working wavelength range is 315 - 400 nm (UVA band). The UV image reflects the reflection characteristics of the object surface under ultraviolet irradiation and can be used to distinguish sunscreen substances from other substances.

[0063] Specifically, the ultraviolet imaging device is placed at two or more preset angles, and the preset angles can also include a combination of the front position and the 30° side position, which are used to cover the three-dimensional curved surface features of the face to ensure that the user's face can be comprehensively covered. For example, one angle can be the front, and the other angle can be the side, and the ultraviolet imaging device captures the UV images of the user's face at these angles respectively.

[0064] Optionally, in this embodiment, after step S10, steps S11 to S13 are further included:

[0065] Step S11: Real-time detect the current facial pose information.

[0066] Step S12: Determine the deviation value between the user's face and the ultraviolet imaging device according to the facial pose information.

[0067] Step S13: Adjust the acquisition parameters of the ultraviolet imaging device according to the deviation value.

[0068] Step S14: According to the adjusted ultraviolet acquisition device, execute the step of acquiring the UV images of the user's face at at least two preset angles by the ultraviolet imaging device.

[0069] Specifically, the facial pose information refers to various parameters describing the current pose of the user's face, such as pitch angle, yaw angle, and roll angle, etc. These parameters can reflect the change of the user's head pose relative to the ultraviolet imaging device. The preset pose angle range refers to the ideal range of the user's facial pose when the ultraviolet imaging device captures the UV images, which is set in advance. When the actual facial pose information deviates from this range, the acquisition parameters of the imaging device need to be adjusted. The acquisition parameters include exposure time and focal length, which are key parameters affecting the image quality. By changing these parameters, the UV image acquisition effect under different facial poses can be optimized.

[0070] In this embodiment, the pose information of the user's face is obtained in real time through a camera connected to the smear detection system. For example, the continuous change of the facial image can be captured by the camera, and the displacement of the facial feature points in the image can be analyzed to infer the pose change, or the inertial sensor in the smart device can be used to detect the head movement pose. Then, the smear detection system determines the deviation degree between the user's face and the ultraviolet imaging device according to the facial pose information through a preset adjustment rule to calculate the new acquisition parameter value. For example, if the pitch angle of the user deviates from the preset range of the ultraviolet imaging device, the system will adjust the length of the exposure time accordingly according to the magnitude of the deviation value to adapt to the current lighting and human body pose conditions.

[0071] Meanwhile, according to the distance and pose changes, the focal length is dynamically adjusted to ensure the clarity of the facial image. Using the ultraviolet imaging device with adjusted parameters, the UV image of the user's face is collected again according to the preset angle setting. Through this collection, a high-quality UV image that better conforms to the current facial pose conditions can be obtained, laying a better data foundation for subsequent image processing and analysis. By real-time detecting the facial pose information and adjusting the acquisition parameters of the ultraviolet imaging device accordingly, the collected UV images can still have good quality and accuracy under different user poses, thus further improving the overall effect of sunscreen application detection.

[0072] Step S20: Input each of the UV images into a pre-trained image segmentation model to generate a target image containing a specular interference marker and a sunscreen marker.

[0073] In this embodiment, the image segmentation model is a deep learning-based algorithm that can segment an image into multiple regions and label each region. The pre-trained image segmentation model refers to a model that has been trained with a large amount of data and can identify and label the specular interference region and the sunscreen region in the UV image.

[0074] Specifically, the UV images collected in step S10 are input into the pre-trained image segmentation model. The model analyzes the pixel features in the image, identifies the region covered by the sunscreen and labels it as "sunscreen marker", and at the same time identifies the specular region caused by skin oil or other factors and labels it as "specular interference marker".

[0075] Optionally, in this embodiment, the step of determining the effective sunscreen region according to the specular interference marker and the sunscreen marker in the target image includes steps S21 - S22:

[0076] Step S21: Determine a matching weight value according to the specular intensity and area information of the specular interference marker, and associate the corresponding weight value with the specular interference marker in the target image.

[0077] Step S22: In the target images at different angles, determine the weighted sum of the weight values corresponding to the specular interference markers in the same physical region.

[0078] Step S23: When the weighted sum is less than a preset threshold, determine the physical region as the effective sunscreen region.

[0079] Specifically, a reflective interference mark refers to a mark recognized as a reflective area in the target image. The weight value refers to a value assigned to the reflective interference mark according to its influence degree at different angles, which is used to quantify the influence of reflective interference. The weighted sum refers to the weighted summation of the weight values of the reflective interference marks at different angles in the same physical area to comprehensively evaluate the degree of reflective interference in this area. The preset threshold refers to a value preset according to the actual application scenario and sunscreen detection requirements, which is used to determine whether a physical area is affected by reflective interference. The effective sunscreen area refers to an area in the target image where the influence of reflective interference is small and can accurately reflect the coverage of sunscreen substances.

[0080] In this embodiment, the smear detection system first assigns weight values to the reflective interference marks in the target image. The assignment of weight values can be determined according to factors such as the reflective intensity and area size. For example, a larger weight value can be assigned to an area with higher reflective intensity. Then, the smear detection system determines the same physical area in the target images at different angles and calculates the weighted sum of the reflective interference marks in this area. The specific calculation method can be to add up the weight values of the reflective interference marks in this area at each angle. Then, compare the calculated weighted sum with the preset threshold. If the weighted sum is less than the preset threshold, it means that the influence of reflective interference in this physical area is small and can be determined as an effective sunscreen area. The setting of the preset threshold can be adjusted according to experimental data and actual requirements. For example, if the preset threshold is 1.5 and the weighted sum of a certain physical area is 1.0, then this area is determined as an effective sunscreen area. By adding weight values to the reflective interference marks and calculating the weighted sum of the same physical area at different angles, the effective sunscreen area can be determined more accurately, thereby improving the accuracy and reliability of sunscreen smear detection.

[0081] Step S30: Determine the effective sunscreen area according to the reflective interference marks and the sunscreen substance marks in the target image.

[0082] In this embodiment, the effective sunscreen area refers to the actual sunscreen area in the target image that is marked as covered by sunscreen substances and not affected by reflective interference.

[0083] Specifically, the smear detection system determines the effective sunscreen area by analyzing the mark information in the target image, excluding the areas corresponding to the reflective interference marks, and only retaining the areas corresponding to the sunscreen substance marks.

[0084] Step S40: Map the effective sunscreen area to the facial reference coordinate system and calculate the area ratio of the effective sunscreen area to the total facial area.

[0085] In this embodiment, the facial reference coordinate system is a preset coordinate system used to locate and quantify the positions and areas of various regions of the face. The area ratio refers to the ratio of the area of the effective sunscreen application region to the total area of the facial region, and is used to quantify the coverage rate of sunscreen application.

[0086] Specifically, the application detection system maps the determined effective sunscreen application region into the facial reference coordinate system, calculates the area of the effective sunscreen application region through coordinate positioning and area calculation algorithms, and compares it with the total area of the facial region to obtain the area ratio.

[0087] As an alternative implementation, first call the pre-stored standard facial model, which contains detailed facial structure data such as the length, width, depth of the face, and the position information of each key feature point. Then, through computer vision algorithms, register the standard facial model with the user's current facial image so that the standard facial coordinate system can be accurately mapped onto the user's facial image. Next, use the mapping algorithm in computer vision to match the determined effective sunscreen application region with the obtained facial reference coordinate system.

[0088] After the matching, extract the contour of the effective sunscreen application region, and then convert each pixel point or feature point of this region into the corresponding three-dimensional coordinate values in the facial reference coordinate system according to the facial structure characteristics and the coordinate system direction. Specifically, it can be achieved by constructing a transformation matrix from the image space to the coordinate system space. Then, project the coordinate information of the effective sunscreen application region in the facial reference coordinate system to obtain its projection contour on the two-dimensional plane. Use the polygon area calculation formula or integral method to calculate the area enclosed by this projection contour, so as to obtain the total area of the entire effective sunscreen application region. The area of the total facial region can be obtained through the standard facial model or pre-stored facial area data. Finally, divide the area of the effective sunscreen application region calculated in the previous step by the obtained total area of the facial region to obtain the area ratio.

[0089] Step S50: Generate a detection result of sunscreen application based on the area ratio.

[0090] In this embodiment, the detection result of sunscreen application refers to the final evaluation report generated according to the area ratio, which is used to inform the user whether the effect of sunscreen application meets the standard. Among them, the detection result is not limited to forms such as scores, stars, comments, the percentage of application completeness, and the presentation of the applied area on the face.

[0091] Specifically, the application detection system generates a detection result according to the area ratio. If the area ratio reaches a preset threshold (for example, 80%), it is determined that the effect of sunscreen application is good; if it is lower than the threshold, the user is prompted to supplement sunscreen.

[0092] Optionally, in this embodiment, after the step of generating a detection result of sunscreen application based on the area ratio, steps S51 to S52 are further included:

[0093] Step S51: Determine the application effect of the user according to the comparison result between the detection result and the historical detection data.

[0094] Step S52: When the application effect is that the area ratio of the effective sunscreen area decreases, generate application improvement information according to the historical detection data.

[0095] Step S53: Feedback the application improvement information and the sunscreen product usage suggestion to the corresponding user interface.

[0096] Specifically, the detection result refers to the evaluation information about the user's sunscreen application situation generated based on the area ratio, and the historical detection data refers to the relevant data records obtained from the user's previous sunscreen application detections. The application improvement information refers to the suggestions provided to the user on how to improve the sunscreen application method according to the difference between the current detection result and the historical data. The sunscreen product usage suggestion refers to combining the user's sunscreen needs and detection situation, and recommending suitable sunscreen products and their usage methods to the user. The user interface refers to the interface through which the user interacts with the application detection system, and is used to display the detection result and relevant information to the user. By comparing the detection result with the historical data, generating application improvement information and sunscreen product usage suggestions, and feeding them back to the user interface, personalized sunscreen guidance can be provided to the user, helping the user better perform sunscreen and improving the sunscreen effect.

[0097] The application detection system first compares and analyzes the current detection result with the user's historical detection data. By comparing the area ratio changes at different time points, it is judged whether the user's sunscreen application effect has improved or decreased. If the detection result shows that the current sunscreen application effect is not good, the application detection system will generate targeted application improvement information according to the user's skin type, environmental factors (such as ultraviolet intensity, outdoor activity time, etc.) and the distribution of the effective sunscreen area in the historical data. For example, it prompts the user which parts need to strengthen sunscreen application, or suggests adjusting the thickness and evenness of the application. At the same time, the application detection system will associate and recommend sunscreen product usage suggestions, and screen out suitable sunscreen products for the user from the database according to the user's skin type (such as dry, oily, sensitive, etc.) and sunscreen needs, and provide detailed usage methods, such as the application amount, application time interval, etc.

[0098] The application detection system integrates the updated sunscreen distribution map and application improvement information onto the user interface for display. The sunscreen distribution map can visually show the effective sunscreen areas and the areas without sunscreen application through different colors or markings, enabling users to clearly understand their sunscreen application status at a glance. The application improvement information is presented in the form of text or graphics on the user interface, clearly communicating to users how to improve their sunscreen application methods. For example, on the sunscreen distribution map, the effective sunscreen areas can be represented by green, and the areas without sunscreen application by red. At the same time, application improvement information such as "It is recommended that you strengthen sunscreen application on the forehead and nose bridge to enhance the sunscreen effect" is displayed below the interface. Users can view the detailed information through interactive devices such as touchscreens and operate according to the recommended sunscreen product usage suggestions of the system.

[0099] Exemplarily, assume that the user is facing the ultraviolet imaging device during detection. The device first captures a UV image from the front, and then rotates to the side to capture another UV image. These two images respectively record the ultraviolet reflection conditions of the user's face at different angles. In the UV image, some areas show a lower ultraviolet reflectance due to the user applying sunscreen, and the model marks these areas as sunscreen substance areas; some other areas reflect ultraviolet light due to skin oil, and the model marks these areas as reflective interference areas. In the finally generated target image, the sunscreen substance areas and the reflective interference areas are clearly distinguished. In the target image, some areas are marked as sunscreen substances, but a small part of these areas is also marked as reflective interference. The application detection system uses logical operations to exclude the reflective interference areas from the sunscreen substance areas, and the finally determined effective sunscreen area is the sunscreen substance coverage area after excluding the interference. Assume that the total area of the face is 100 square centimeters, and the area of the effective sunscreen area is 70 square centimeters, then the area ratio is 70%. This ratio reflects the coverage rate of sunscreen application on the user's face. The preset threshold is 80%, and the calculated area ratio is 70%, so the detection result shows that the user needs to apply sunscreen to the areas without sunscreen application.

[0100] In the technical solution provided in this embodiment, UV images of the user's face are collected at at least two preset angles by an ultraviolet imaging device, and then each of the UV images is input into a pre-trained image segmentation model to generate a target image including a reflective interference mark and a sunscreen substance mark. Then, according to the reflective interference mark and the sunscreen substance mark in the target image, an effective sunscreen area is determined. Next, the effective sunscreen area is mapped to a facial reference coordinate system, and the area ratio of the effective sunscreen area to the total facial area is calculated. Finally, a detection result of sunscreen application is generated based on the area ratio. In this embodiment, UV images are collected by an ultraviolet imaging device, and a target image is generated by using a pre-trained image segmentation model. The effective sunscreen area is determined by combining the reflective interference mark and the sunscreen substance mark. Finally, the sunscreen application effect is evaluated by the area ratio. This method can accurately and quickly detect the coverage rate of the user's sunscreen application, thereby improving the detection effect of sunscreen application.

[0101] Embodiment Two

[0102] Based on the same inventive concept, the present application also provides a second embodiment. Refer to Figure 2 , Figure 2 , which is a schematic flowchart of the second embodiment of the sunscreen application detection method of the present application. In this embodiment, after the step of generating the detection result of sunscreen application based on the area ratio, steps S60 to S70 are further included:

[0103] Step S60: Obtain a sunscreen coverage distribution map including the detection result.

[0104] Step S70: In the sunscreen coverage distribution map, render the effective sunscreen coverage area and the uncovered area as a first visualization color and a second visualization color, respectively.

[0105] Step S80: Render the updated sunscreen coverage distribution map to the corresponding interface for display.

[0106] In this embodiment, the sunscreen distribution map refers to an image showing the distribution of sunscreen substances on the user's face. The updated sunscreen distribution map refers to an image in which the distribution area of sunscreen substances is re-annotated and displayed after the current detection and analysis. It is a diagram showing the coverage of sunscreen substances on the user's face in the form of an image, which includes the detection result of sunscreen application generated based on the area ratio and can intuitively reflect the distribution of the effective sunscreen area and the uncovered area. The first visualization color and the second visualization color refer to two different colors used to distinguish the effective sunscreen coverage area and the uncovered area in the sunscreen coverage distribution map. Through the distinction of colors, the user can more intuitively understand the coverage of sunscreen substances on his / her face.

[0107] Specifically, the application detection system can convert the coordinate information of the effective sunscreen area in the facial reference coordinate system into image pixel points through computer vision algorithms to generate a sunscreen coverage distribution map. Then, according to the area ratio data in the detection results, the sunscreen coverage distribution map is optimized using the first visualization color and the second visualization color. Finally, the sunscreen coverage distribution map marked with the first visualization color and the second visualization color is rendered into the application detection system for display on the corresponding interface, so that users can more intuitively view the sunscreen application effect.

[0108] As an alternative implementation, the application detection system uses graphics processing software to draw a sunscreen coverage distribution map based on the coordinates and area information of the effective sunscreen area. During the drawing process, different colors (i.e., the first visualization color and the second visualization color) can be used to distinguish the effective sunscreen area and the uncovered area, so that users can clearly identify them.

[0109] Finally, the application detection system renders the effective sunscreen coverage area and the uncovered area in the sunscreen coverage distribution map as the first visualization color and the second visualization color respectively according to the pre-set color rules.

[0110] Optionally, in this embodiment, after the step of obtaining the sunscreen coverage distribution map including the detection results, steps S61 to S63 are further included:

[0111] Step S61: Determine the coverage rate of the key parts according to the area size of the uncovered area, where the coverage rate is the ratio of the area of the uncovered area to the total area of the face.

[0112] Step S62: When it is detected that the coverage rate of the area corresponding to the key part is lower than the critical value, trigger a key re-application reminder.

[0113] Step S63: Feed back the key re-application reminder to the user interface.

[0114] Specifically, the uncovered area refers to the facial area where no sunscreen substance is applied in the sunscreen coverage distribution map. The key parts refer to the areas on the face with higher sunscreen requirements, such as the forehead, nose bridge, cheekbones, etc. These parts are usually more easily directly irradiated by ultraviolet rays. The coverage rate refers to the proportion of the area of the uncovered area in the total area of the key part, which is used to evaluate the sunscreen situation of the key part. The critical value is a threshold set according to sunscreen standards or experience, which is used to judge whether the coverage rate of the key part has reached the level that requires reminding users to re-apply. The key re-application reminder refers to the reminder information sent by the system to the user when the coverage rate of the key part is lower than the critical value, prompting the user to re-apply sunscreen to these parts.

[0115] In this embodiment, the application detection system first extracts the area information of the uncovered area from the sunscreen coverage distribution map through an image processing algorithm. Then, in combination with the key part information in the facial reference coordinate system, the uncovered area of each key part is determined. Next, based on the uncovered area and the total area of the key part, the coverage rate of the key part is calculated. The specific calculation formula is: coverage rate = (uncovered area ÷ total area of the key part) × 100%.

[0116] Then, the calculated coverage rates of each key part are compared with a preset critical value. If the coverage rate of a certain key part is lower than the critical value, the system triggers a key re-application reminder. The critical value can be set according to different sunscreen requirements and standards. For example, for daily sunscreen, the critical value can be set to 10%, while for sunscreen during long-term outdoor activities, the critical value can be set to 5%. Finally, the triggered key re-application reminder information is displayed through the user interface. The reminder information can be presented in various forms such as text, sound, and images to ensure that the user can clearly receive the reminder. For example, a text reminder such as "You have not applied sunscreen to your forehead and nose bridge. Please re-apply in time" can be displayed on the screen of the user interface, and at the same time, a sound prompt can be accompanied to attract the user's attention. The above solution determines the coverage rate of the key part according to the area of the uncovered area, triggers a key re-application reminder when the coverage rate is lower than the critical value, and feeds back the reminder to the user interface, which can timely remind the user to re-apply sunscreen to the key part, improve the sunscreen effect, and effectively protect the skin from the harm of ultraviolet rays.

[0117] In the technical solution provided in this embodiment, by generating a sunscreen coverage distribution map and rendering the effective sunscreen coverage area and the uncovered area as different visual colors respectively, the coverage of the sunscreen substance on the user's face can be intuitively displayed, helping the user better understand their sunscreen effect, so as to make up the application in time and improve the sunscreen effect.

[0118] Embodiment Three

[0119] Based on the same inventive concept, the present application also provides a third embodiment. Refer to Figure 3 , Figure 3 which is a schematic flowchart of the third embodiment of the sunscreen application detection method of the present application. In this embodiment, after the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device, the following steps S90 to S120 are further included:

[0120] Step S90: Synchronously collect color images of the user's face at at least two preset angles through a color camera.

[0121] In this embodiment, the color images of the user's face captured by a color camera (such as a common RGB camera) reflect the detailed information such as color and texture at different angles, and can present the natural appearance of the user's face, including information different from the UV image such as skin color and feature points.

[0122] Specifically, while collecting the UV image through the ultraviolet imaging device, the color camera is used to synchronously collect the color images of the user's face from multiple angles. Ensure that the acquisition time, position and other parameters of the two groups of images (i.e., the UV image and the color image) are consistent, so as to perform effective registration and fusion subsequently. For example, the ultraviolet imaging device and the color camera are integrated on the same device, and through precise timing control and synchronous triggering, it is ensured that the two cameras take pictures simultaneously at the moment when the user makes the same facial gesture.

[0123] Step S100: Perform spatial registration on the UV image and the color image based on the feature point matching algorithm to generate the corrected UV image and color image.

[0124] In this embodiment, the feature point matching algorithm is a computer vision technology that establishes the corresponding relationship between images by identifying and matching the feature points (such as key points, corner points, etc.) in the images. Spatial registration refers to the process of aligning images with different imaging methods or different perspectives to the same coordinate system, so that the objects in the images correspond to each other in terms of spatial position.

[0125] Specifically, first extract the feature points from the UV image and the color image respectively. For example, for the UV image, algorithms such as SURF (Speeded-Up Robust Features) or SIFT (Scale-Invariant Feature Transform) can be used to detect and describe the feature points; for the color image, these algorithms or other feature extraction algorithms suitable for color images (such as the ORB algorithm, etc.) can also be used. After extracting the feature points, calculate their matching relationship between the two images to find the corresponding point pairs. Then, based on these matching feature point pairs, estimate the transformation matrix, and on this basis, perform geometric correction on the UV image and the color image, such as rotation, scaling, and translation operations, so that the spatial coordinate systems of the two images are aligned, generating the corrected UV image and color image.

[0126] As an optional implementation manner, the step of performing spatial registration on the UV image and the color image based on the feature point matching algorithm to generate the corrected UV image and color image includes:

[0127] Extract the set of feature points in the UV image and the color image, and generate the feature descriptors of the set of feature points; determine the matching target feature points in the set of feature points according to the feature descriptors; align the spatial coordinate systems of the UV image and the color image according to the target feature points, and generate the corrected UV image and color image.

[0128] Specifically, a feature point refers to a point with obvious features in an image that is easy to identify and distinguish, such as a corner point, an edge point, a texture point, etc. The set of feature points refers to the set of all feature points detected from an image. A feature descriptor is a vector that quantitatively describes the local image information around a feature point and is used to characterize the unique properties of the feature point. Feature point matching refers to finding the corresponding feature point pairs, that is, the target feature points, in the sets of feature points of two images according to the similarity of the feature descriptors. A target feature point refers to a feature point that represents the same physical position in different images, and the corresponding relationship between images can be established through matching. Spatial coordinate system alignment refers to making the pixel points of two images correspond in spatial position through geometric transformation, that is, establishing the pixel coordinate mapping relationship of the same physical scene in different images. The corrected image refers to an image that has eliminated the influence of factors such as imaging device differences and shooting angle deviations after geometric transformation.

[0129] The smear detection system performs feature point detection on the UV image and the color image respectively. A variety of feature point detection algorithms can be used, such as the Harris corner detection algorithm, the FAST feature point detection algorithm, etc., to extract the set of feature points in the image. Then, for each feature point, its feature descriptor is calculated. According to the image gray level, texture and other information around the feature point, a feature descriptor vector with uniqueness and distinctiveness is generated.

[0130] Next, the feature descriptors of the UV image and the color image are compared to calculate the similarity between them. A variety of similarity measurement methods can be used, such as Euclidean distance, Hamming distance, cosine similarity, etc. Generally, the smaller the distance or the higher the similarity, the more matching the feature points are. According to the set matching threshold, the feature point pairs with similarity higher than the threshold are selected and determined as the matching target feature points. For example, the nearest neighbor distance ratio method can be used, that is, for each feature point, calculate the distance ratio between it and the nearest neighbor feature point and the second nearest neighbor feature point. If the ratio is less than a certain threshold (such as 0.7), it is considered that the feature point is successfully matched.

[0131] Finally, according to the matched target feature points, determine the geometric transformation parameters between the UV image and the color image. Multiple methods can be used, such as homography matrix estimation, affine transformation matrix estimation, etc. Taking the homography matrix as an example, through at least 4 pairs of target feature points, use a preset algorithm to solve the 3×3 homography matrix. Then, according to the obtained homography matrix, perform a perspective transformation on the UV image to align its spatial coordinate system with that of the color image. The transformed UV image and color image are the corrected images.

[0132] By extracting the feature point sets and feature descriptors in the UV image and the color image, accurately determine the matched target feature points, and align the spatial coordinate systems of the UV image and the color image according to the target feature points to generate the corrected image, which can effectively correct the image and further improve the reliability and accuracy of the sunscreen application detection method.

[0133] Step S110: Map the purple spectrum of the corrected UV image to the color spectrum range to generate a color-adjusted UV image.

[0134] In this embodiment, the mapping of the purple spectrum in the UV image means converting the image information originally in the ultraviolet spectrum range (usually invisible) into the color spectrum range in the visible spectrum through color conversion technology. This can make the information in the UV image that was originally invisible or difficult to identify (such as details of sunscreen substances, skin texture, etc.) appear in the form of color tones.

[0135] Specifically, the application detection system performs color processing on the corrected UV image. First, analyze the corresponding spectral response in the UV image to determine the pixel values related to the purple spectrum. Then, through a gamut mapping algorithm, convert the pixel values of these purple spectra into pixel values within the color spectrum range. For example, convert purple (RGB value approximately 128, 0, 128) to red (RGB value 255, 0, 0) or a warm-toned red series. This process can be achieved by using the color space conversion function in image processing software or through a dedicated spectral mapping algorithm library.

[0136] Step S120: Perform pixel superposition and fusion on the color-adjusted UV image and the corrected color image to generate a composite image and output the composite image through the display interface.

[0137] In this embodiment, pixel superposition and fusion means superimposing and merging two images with the same spatial dimensions and coordinates at the pixel level to generate a new composite image. The pixel superposition and fusion of the color-adjusted UV image and the color image can achieve an organic combination of two different types of information images, enabling users to simultaneously observe the distribution of sunscreen substances and the natural color structure of the face.

[0138] Specifically, first ensure that the color-corrected UV image and the corrected color image have been spatially registered and have the same resolution and size. Then, process each pair of corresponding pixels according to certain fusion rules. For example, the pixel values of the two images can be weighted and averaged. In terms of weight setting, appropriate weights may be set for the color image (such as the normal color of the skin, the appearance parts like hair, etc.), while higher weights may be set for the color-corrected UV image (such as the red prominent area of the sunscreen substance) so that the information that needs to be concerned can be prominently displayed in the synthesized image. Or a region-based fusion method can be adopted. By using a segmentation algorithm to determine different regions in the image (such as the skin region, the eyeball region, etc.), different fusion strategies can be set respectively in each region. After calculating the superimposed value of each pair of pixels, a synthesized image can be obtained. When the two images are effectively fused, the synthesized image can be transmitted to the corresponding display interface, such as a computer screen, a mobile phone display screen, etc., for the user to view.

[0139] In the technical solution provided in this embodiment, through a series of steps such as synchronous acquisition, spatial registration, spectral mapping, and pixel superposition fusion of the color image, an intuitive and accurate detection and display of the sunscreen application situation on the user's face are realized, providing a more convenient and efficient way for the user to evaluate the sunscreen effect, and helping the user better manage sunscreen and protect the skin.

[0140] Since the system introduced in the embodiments of the present application is the system adopted for implementing the methods in the embodiments of the present application, based on the methods introduced in the embodiments of the present application, those skilled in the art can understand the specific structure and variations of the system, so it will not be elaborated here. Any system adopted by the methods in the embodiments of the present application falls within the scope of protection of the present application.

[0141] The present application provides a sunscreen application detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sunscreen application detection method in the first embodiment above.

[0142] Next, refer to Figure 4, which shows a schematic structural diagram of a sunscreen application detection device suitable for implementing the embodiments of the present application. The sunscreen application detection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as smart makeup mirrors, mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description, tablet computers), PMPs (Portable Media Player, portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The shown sunscreen application detection device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0143] As Figure 4 shown, the sunscreen application detection device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM, Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM, Random Access Memory) 1004. In the random access memory 1004, various programs and data required for the operation of the sunscreen application detection device are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD, Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the sunscreen application detection device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a sunscreen application detection device with various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0144] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0145] The sunscreen application detection device provided by the present application adopts the sunscreen application detection method in the above-mentioned embodiment, and can solve the technical problem that the detection effect of the traditional solution for sunscreen application is poor. Compared with the prior art, the beneficial effects of the sunscreen application detection device provided by the present application are the same as those of the sunscreen application detection method provided by the above-mentioned embodiment, and other technical features in the sunscreen application detection device are the same as the features disclosed in the method of the previous embodiment, which will not be elaborated here.

[0146] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0147] As mentioned above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0148] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the sunscreen application detection method in the above-mentioned embodiment.

[0149] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination of the above.

[0150] The above computer-readable storage medium can be included in the sunscreen application detection device; it can also exist separately without being assembled into the sunscreen application detection device.

[0151] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the sunscreen application detection device, the sunscreen application detection device is caused to: collect UV images of the user's face at at least two preset angles through an ultraviolet imaging device; input each of the UV images into a pre-trained image segmentation model to generate a target image containing glare interference marks and sunscreen substance marks; determine an effective sunscreen area based on the glare interference marks and the sunscreen substance marks in the target image; map the effective sunscreen area to a facial reference coordinate system and calculate the area ratio of the effective sunscreen area to the total facial area; and generate a detection result of the sunscreen application based on the area ratio.

[0152] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0153] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0154] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0155] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned sunscreen application detection method, and can solve the technical problem that the detection effect of the traditional solution for sunscreen application is poor. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the sunscreen application detection method provided in the above embodiments, and will not be elaborated here.

[0156] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the sunscreen application detection method as described above when executed by a processor.

[0157] The computer program product provided by the present application can solve the technical problem that the detection effect of the traditional solution for sunscreen application is poor. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the sunscreen application detection method provided by the above embodiment, and will not be elaborated here.

[0158] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent scope of the present application by the same token.

Claims

1. A sunscreen smear detection method, characterized in that: The sunscreen smear detection method comprises the following steps: Collecting UV images of the user's face at at least two preset angles through an ultraviolet imaging device; Input each of the UV images into a pre-trained image segmentation model to generate a target image containing a reflective interference mark and a sunscreen material mark; Determining an effective sunscreen area according to the reflective interference mark and the sunscreen material mark in the target image; Mapping the effective sun protection area to a facial reference coordinate system, and calculating the area ratio of the effective sun protection area relative to the total facial area; A sunscreen application detection result is generated based on the area ratio.

2. The method according to claim 1, characterized in that The step of determining an effective sunscreen area according to the reflective interference mark and the sunscreen material mark in the target image comprises: Determining a matching weight value according to the reflective intensity and area information of the reflective interference mark, and associating the reflective interference mark in the target image with the corresponding weight value; Determine, in the target images at different angles, a weighted sum of the corresponding weight values ​​of the reflective interference marks in the same physical area; When the weighted sum is less than a preset threshold, the physical area is determined as the effective sun protection area.

3. The method according to claim 1, characterized in that After the step of generating the detection result of sunscreen application based on the area proportion, the method further includes: Determine the user's smearing effect according to the comparison result of the detection result and the historical detection data; When the coating effect is that the area ratio of the effective sunscreen area is reduced, coating improvement information is generated according to the historical detection data; Determining matching sunscreen products and corresponding sunscreen product usage suggestions based on the user's skin quality information; The application improvement information and the sunscreen product usage suggestion are fed back to a corresponding user interface.

4. The method according to claim 1, characterized in that After the step of generating the detection result of sunscreen application based on the area proportion, the method further includes: Obtaining a sunscreen coverage distribution map including the detection results; In the sunscreen coverage distribution map, the effective sunscreen coverage area and the uncovered area are rendered as a first visual color and a second visual color respectively; The updated sunscreen coverage distribution map is rendered to a corresponding interface display.

5. The method according to claim 4, characterized in that After the step of obtaining the sunscreen coverage distribution map including the detection result, the method further includes: Determining the coverage rate of the key parts according to the size of the uncovered area, wherein the coverage rate is the ratio of the area of ​​the uncovered area to the total area of ​​the face; When it is detected that the coverage rate of the area corresponding to the key part is lower than a critical value, a reminder for key part repainting is triggered; The reminder for repainting the key points is fed back to the user interface.

6. The method according to claim 1, characterized in that After the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device, the method further includes: Detect current facial posture information in real time; Determining a deviation value between the user's face and the ultraviolet imaging device according to the facial posture information; adjusting the acquisition parameters of the ultraviolet imaging device according to the deviation value; According to the adjusted ultraviolet collecting device, the step of collecting UV images of the user's face at at least two preset angles by using the ultraviolet imaging device is performed.

7. The method according to claim 1, characterized in that After the step of collecting UV images of the user's face at at least two preset angles by the ultraviolet imaging device, the method further includes: Synchronously collecting color images of the user's face at at least two preset angles through a color camera; Performing spatial registration on the UV image and the color image based on a feature point matching algorithm to generate a corrected UV image and a color image; Mapping the purple spectrum of the corrected UV image to a color spectrum interval to generate a toned UV image; The toned UV image and the corrected color image are pixel-overlaid and fused to generate a composite image, and the composite image is output through a display interface.

8. The method according to claim 7, characterized in that The step of spatially registering the UV image and the color image based on a feature point matching algorithm to generate a corrected UV image and a color image comprises: Extracting a set of feature points from the UV image and the color image, and generating a feature descriptor of the set of feature points; Determine a matched target feature point in the feature point set according to the feature descriptor; The spatial coordinate systems of the UV image and the color image are aligned according to the target feature points to generate a corrected UV image and a color image.

9. A sunscreen smear detection device, characterized in that: The sunscreen smear detection device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the sunscreen smear detection method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the sunscreen smear detection method according to any one of claims 1 to 8 are implemented.

Images