CN116473520B - Electronic equipment and skin analysis method and device thereof - Google Patents

Abstract

The application provides electronic equipment and a skin analysis method and device thereof. The skin analysis method comprises the following steps: controlling a camera device to acquire a video stream at the target skin, wherein the video stream comprises a plurality of frames of images in a preset time period; selecting at least one frame of image meeting the image quality requirement from a plurality of frames of images of the video stream as at least one frame of target image; performing skin analysis according to at least one frame of target image to obtain a skin analysis result; and outputting the skin analysis result. Therefore, in an open environment, video streams are collected in real time, rather than pictures are collected by standing, so that efficient and noninductive collection is achieved, and user experience is improved; moreover, all the images for skin analysis can be controlled above the same quality level, so that the stability and comparability of skin analysis results are improved, the noise problem caused by the quality problem of the images is removed, and the accuracy of skin analysis is improved.

Description

Electronic device and skin quality analysis method and device thereof

Technical Field

The present application relates to the field of beauty, and in particular to an electronic device and a skin quality analysis method and device thereof.

Background Art

Existing skin analysis methods generally use AI algorithms to directly process and analyze the input face images to obtain various skin quality parameters (roughness, spots, pores, wrinkles, acne, etc.). During the process of this method, the image quality has a great impact on the analysis results. Even if the same person is measured and analyzed in the same time period, the analysis results will vary greatly due to factors such as image quality, such as clarity, distance from the camera, deflection angle, and lighting. This volatility caused by uneven image quality makes the effectiveness of skin quality analysis, the results of measurements of different people, and the results of different measurements of the same person not very comparable.

Summary of the invention

The present application aims to solve at least one of the technical problems existing in the prior art.

In order to solve the above technical problems, the technical solution of this application is:

In a first aspect, the present application provides a skin quality analysis method, which is applied to an electronic device, and the skin quality analysis method comprises the steps of:

Controlling the camera device to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

Selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image of the video stream as at least one frame of target image;

Performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The skin quality analysis result is outputted.

In a second aspect, the present application provides an electronic device, including a processor, a memory, and a camera device, wherein the camera device and the memory are electrically connected to the processor, respectively, and a computer program is stored in the memory, and the processor runs the computer program to perform the steps of the skin quality analysis method:

Controlling the camera device to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

Selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image of the video stream as at least one frame of target image;

Performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The skin quality analysis result is outputted.

In a third aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program can be run by a processor to perform the steps of the skin quality analysis method:

Controlling the camera device to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

Selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image of the video stream as at least one frame of target image;

Performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The skin quality analysis result is outputted.

In a fourth aspect, the present application also provides a skin quality measurement device, comprising:

An acquisition control module, used to control the camera device to acquire a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

An image selection module, used to select at least one frame of image that meets the image quality requirement from the plurality of frames of image in the video stream as at least one frame of target image;

a skin quality analysis module, configured to perform skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The output control module is used to output the skin quality analysis result.

Compared with the prior art, the beneficial effects of this application are:

Therefore, in an open environment, video streams can be collected in real time rather than statically collecting pictures, achieving efficient and seamless collection and improving user experience. Moreover, all images used for skin analysis can be controlled at the same quality level, improving the stability and comparability of skin analysis results, removing noise problems caused by image quality problems themselves, and improving the accuracy of skin analysis.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of a module of an electronic device in an embodiment of the present application.

FIG. 2 is a schematic flow chart of a skin quality analysis method in one embodiment of the present application.

FIG. 3 is a statistical example of various situations of marking frame images in an embodiment of the present application.

FIG. 4 is a schematic flow chart of a skin quality analysis method in another embodiment of the present application.

FIG. 5 is a schematic diagram of a module of a skin quality analysis device provided in an embodiment of the present application.

DETAILED DESCRIPTION

Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

In this application, unless otherwise clearly specified and limited, the terms "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

Please refer to Figure 1, which is a module schematic diagram of an electronic device 1 in an embodiment of the present application. The electronic device 1 is used to perform skin quality analysis. The electronic device 1 can be, but is not limited to, a skin analyzer, a beauty instrument or intelligent terminal with a skin detection function, or a skin analysis system composed of a camera with a video acquisition function and a skin analysis device with a data analysis function, or other devices capable of realizing video acquisition and data analysis functions, which are not limited here. Specifically, the electronic device 1 includes a memory 11 and a processor 12. The memory 11 is electrically connected to the processor 12. A computer program is stored in the memory 11. The processor 12 runs the computer program to execute the steps of the skin quality analysis method. The electronic device 1 also includes a camera 13. The camera 13 is electrically connected to the processor 12. The camera 13 may include a camera or a camera system composed of multiple cameras, as long as it can face the user's skin when doing skin quality testing and collect image data in a timely and accurate manner, which is not limited here. In this embodiment, when the electronic device 1 is a device integrating video acquisition function and data analysis function, the camera 13 includes a front camera. It is understandable that, in other embodiments, the camera device 13 includes not only a front camera but also a rear camera, and, depending on different situations, the camera used to capture the video stream at the target skin can be switched between the front camera and the rear camera.

Please refer to Figure 2, which is a schematic diagram of the process of the skin quality analysis method in one embodiment of the present application. The skin quality analysis method can be applied to the above-mentioned electronic device 1 to implement skin quality analysis. It is understandable that some steps of the skin quality analysis method can be added or deleted or the order can be changed, which is not limited here. Specifically, the skin quality analysis method includes:

Step S210: Control the camera device 13 to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period.

Step S220: selecting at least one frame of image that meets the image quality requirement from the plurality of frame images of the video stream as at least one frame of target image.

Step S230: performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result.

Step S240: outputting the skin quality analysis result.

In this application, the steps of the skin quality analysis method are: first, control the camera device 13 to collect the video stream at the target skin, then extract multiple frames of images according to the collected video stream sample information, and then select the frame images that meet the image quality requirements from the multiple frames for skin quality analysis. Thus, in an open environment, the video stream is collected in real time instead of statically collecting pictures, so as to achieve efficient and non-sensing collection and improve the user experience; moreover, all images used for skin quality analysis can be controlled at the same quality level, so as to improve the stability and comparability of the skin quality analysis results, remove the noise problems caused by the quality problems of the image itself, and improve the accuracy of skin quality analysis.

Among them, the processor 12 controls the camera device 13 to collect the video stream within a preset time period at the target skin. The duration of the preset time period can be set according to actual needs, for example, 5 seconds, 10 seconds, or 15 seconds, etc., which is not limited here. It can be understood that the longer the duration of the video stream, the more frame images the video stream includes, and therefore, the greater the probability of selecting a high-quality image. Of course, this is also accompanied by an increase in the amount of computing data. Therefore, in practical applications, it is necessary to make a certain trade-off between high-quality images and the amount of computing data.

Since the multiple frames of the video stream are generated at different times, the shooting parameters at different times may change slightly. Therefore, the image quality of different frames shot under different shooting parameters is also different. Some frames have relatively good image quality, while some frames have relatively poor image quality. Therefore, at least one frame that meets the image quality requirements is selected from the multiple frames of the video stream, and each frame is used as a target image. The noise generated by the frames that do not meet the quality requirements for skin quality analysis can be eliminated, which can further improve the accuracy of skin quality analysis.

In some embodiments, there may be multiple ways to select at least one frame of image that meets the image quality requirement from a plurality of frames of image in the video stream, which are not limited here.

Two of these options are described in detail below.

The first method is:

The step of selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image in the video stream as at least one frame of target image comprises:

Extracting multiple frames of images from the video stream;

Scoring the multiple frames of images respectively to obtain an image quality score for each frame of image;

At least one frame of image that meets the image quality requirement is selected from the multiple frames of image according to the image quality score of each frame of image as the at least one frame of target image.

Therefore, the first method needs to first perform an image quality score on each frame of the multiple frames extracted. After obtaining the image quality score of each frame of the multiple frames extracted, at least one frame of the image can be selected as the at least one target image.

In some embodiments, the step of selecting at least one frame of image that meets the image quality requirement from the multiple frames of image according to the image quality score of each frame of image as the at least one frame of target image includes:

According to the image quality score of each frame of image, one frame with the highest image quality score or at least two frames of image with the relatively highest image quality scores are selected from the multiple frames of image as the at least one frame of target image; or

At least one frame of image that meets the image quality requirement is randomly selected from the multiple frames of image according to the image quality score of each frame of image as the at least one frame of target image.

Therefore, through the first method above, the frame image with the best or relatively best image quality among the multiple frames of the video stream can be selected as the target image, which can further improve the accuracy of skin quality analysis.

The second method is:

The step of selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image in the video stream as at least one frame of target image comprises:

Extracting multiple frames of images from the video stream;

Scoring the multiple frames of images in sequence starting from the first frame of image, and after scoring each frame of image to obtain an image quality score, determining whether the image quality score of the frame of image meets the image quality requirement, and if the image quality score of the frame of image meets the image quality requirement, determining the frame of image to be a target image;

If the image quality score of the frame image does not meet the image quality requirement, the next frame image in the multiple frames of images is scored until a target image whose image quality score meets the image quality requirement is determined.

For example, firstly, a first frame of the multiple frames of images is scored to obtain an image quality score of the first frame of the image;

Determining whether the image quality score of the first frame image meets the image quality requirement, and if the image quality score of the first frame image meets the image quality requirement, determining that the first frame image is the target image;

If the image quality score of the first frame image does not meet the image quality requirement, scoring the second frame image in the multiple frames of images to obtain the image quality score of the second frame image;

Determining again whether the image quality score of the second frame image meets the image quality requirement, and if the image quality score of the second frame image meets the image quality requirement, determining that the second frame image is the target image;

If the image quality score of the second frame image does not meet the image quality requirement, the third frame image in the multiple frames of images is scored; and this process is repeated until a target image whose image quality score meets the image quality requirement is determined.

Thus, in the second method, the image quality score is performed starting from the first frame image and it is judged whether the image quality score of the first frame image meets the image quality requirements. If the first frame image meets the image quality requirements, the first frame image is used as the target image. At this time, if the purpose is to select only one frame of target image for skin quality analysis, the target image selection process can be terminated, and there is no need to perform image quality scores on the second frame image, the third frame image, etc. in the multiple frames of images and judge whether they meet the image quality requirements. Therefore, the amount of data calculation can be greatly reduced. If after determining one frame of target image, it is necessary to determine the second frame of target image, the third frame of target image, etc., then continue to perform a similar judgment process until the second frame of target image, the third frame of target image, etc. are selected, and then the target image selection process is terminated.

In some embodiments, if after the multiple frame images have been scored for image quality and judged whether they meet the image quality requirements, a frame image that meets the image quality requirements has not been selected as the target image, then the next group of multiple frame images that are different from the multiple frame images are extracted from the video stream, and the image quality of the next group of multiple frame images is scored again to select a target image that meets the image quality requirements, until a target image that meets the image quality requirements is selected.

In some embodiments, a group of multi-frame images is extracted from a video stream, for example, a group of multi-frame images may be a group of 10 consecutive frames, or may be a group of multi-frame images selected from the starting position of the video stream, and the next group of multi-frame images is extracted from the end of the group of multi-frame images, for example, 10 consecutive frames starting from the 11th frame image, and this is repeated until a target image whose image quality score meets the image quality requirement is determined. In other embodiments, a group of multi-frame images is extracted from a video stream, and a group of multi-frame images may be selected from any position of the video stream, and the next group of multi-frame images is extracted from another position that does not overlap with the group of multi-frame images, in short, as long as the next group of frame images is guaranteed not to overlap with the frame images of the group of multi-frame images. For example, a group of multi-frame images may be a group of 10 consecutive frames starting from the 21st frame image, and the next group of multi-frame images may be a group of 10 consecutive frames starting from the 41st frame image.

In some embodiments, performing an image quality score on each frame of image includes:

Performing quality marking on each frame of image from at least one dimension to obtain at least one marking result, wherein the at least one dimension includes at least one of clarity, illumination, and frontality; and

The image quality score of each frame of image is obtained according to the marking result of each frame of image.

It can be understood that, in other embodiments, the at least one dimension may also include other dimensions, which are not limited here.

Please refer to FIG. 3 , which is a statistical example of various situations of marking frame images in an embodiment of the present application.

FIG3 shows three dimensions for marking each frame of image, namely, clarity, frontality and illumination. Each dimension includes qualified and unqualified situations. When the qualified situation is met, the dimension of the frame image is marked as the first label, and when the unqualified situation is met, the dimension of the frame image is marked as the second label. The first label and the second label each represent different meanings. For example, in the clarity dimension, the first label is 1 clear and the second label is 0 unclear. The definition of qualified clarity is that the face is clear and the aesthetic features are distinguishable. The situations of unqualified clarity include: obvious blur, indistinguishable acne, moles and fine lines, and partial blur of the face. In the frontality dimension, the first label is 1 positive and the second label is 0 unpositive. The definition of qualified frontality is frontal imaging of the face and no deflection and occlusion. The situations of unqualified frontality include: bowing and raising the head, left and right deviation, incomplete or blocked, obvious expression, etc. In the illumination dimension, the first label is 1 good lighting and the second label is 0 poor lighting. The definition of qualified illumination is that the illumination is sufficient and uniform, there is no strong light spot, and the color deviation does not affect the judgment of spots, moles and acne. The situations of unqualified illumination include: the illumination is too strong or too dark, the illumination is uneven, it is reddish or greenish, there are strong light spots, etc.

In some embodiments, outputting a marking result for each frame of image includes:

Output at least one dimension of labeling results for each frame of image, wherein the labeling result of each dimension indicates the probability value of the frame of image performing well in the dimension.

For example, in one example, an example of image quality evaluation of a target image is as follows:

The output of the image quality assessment model for a frame of image is On = (Pqo, Pzo, Pgo), where Pqo, Pzo, and Pgo represent the probability values of clarity, frontality, and good illumination, respectively, and the value range is [0, 1]. For example, a Pqo value of 0.7 means that the probability of a frame image being clear is 0.7; Pzo = 0.3 means that the probability of a frame image being frontal is 0.3 (i.e., not frontal); and Pgo = 0.5 means that the probability of a frame image being well illuminated is 0.5 (between good and bad).

In some embodiments, the image quality score of each frame of image is obtained according to the marking result of each frame of image, including:

Make a comprehensive score for the evaluation probability of each dimension of the frame image.

For example, in the above example, the comprehensive score of the frame image = (Pqo+Pzo+Pgo)/3*100%. The comprehensive score is the image quality score of each frame image. It is understandable that in other embodiments, after obtaining the probability value of each frame image performing well in each dimension, the evaluation probability of each dimension of the frame image is used for comprehensive scoring, which may not be limited to the above-mentioned method of finding the average score, but may also be a weighted coefficient for each dimension, and then find the average, or other methods, which are not limited here.

In some embodiments, selecting at least one frame of image that meets the image quality requirement includes:

The image quality score of each frame image is compared with the system setting threshold. If it exceeds the system setting threshold, it is qualified, and if it is lower than the system setting threshold, it is unqualified. It is necessary to continue selecting from the frame images until at least one frame image that meets the image quality requirements is selected as at least one target image.

In some embodiments, before performing quality marking on each frame of image from at least one dimension to obtain at least one marking result, the method further includes:

Inputting a plurality of training images, wherein the plurality of training images cover different situations of the at least one dimension;

Training an intelligent scoring model according to the plurality of training images;

After the training of the intelligent scoring model is completed, the image quality scoring of each frame of image is performed by inputting each frame of image into the intelligent scoring model to perform image quality scoring.

In some embodiments, the training process of the intelligent scoring model is as follows:

1. Data labeling. Label and classify all training images according to the above method, and classify all training images to obtain sample training samples and test samples. Among them, the label of each image, Ln = (Pq, Pz, Pg), Ln represents the label of the nth image, where Pq, Pz, Pg represent the values of the image in the dimensions of clarity, frontality, and illumination, respectively, and the values are 0 or 1, where 0 represents unclear, incorrect, or poorly illuminated, and 1 represents clear, correct, or well-illuminated. For example, if the image is clear, incorrect, and poorly illuminated, the image label is (1, 0, 0).

2. Build a CNN (convolutional neural network) model. Build a three-classification (clear, frontal, and illumination) CNN face image evaluation model, set the model loss function and optimizer, and initialize the model parameters.

Model training: The training samples are input into the CNN model, and the model parameters are subjected to multiple rounds of learning iterations according to the loss function and optimizer settings until the model converges.

Model evaluation: Test samples are input into the trained CNN model, and the classification results predicted by the model are compared with the labels to evaluate the accuracy of the model prediction. If the accuracy is greater than the control threshold (for example, 99%), the model training is completed. Otherwise, the learning parameters or number of iterations in the model training and model evaluation are adjusted and retraining is performed.

3. Definition of model accuracy: Assume that all predictions of the model are positive samples (clear, positive and well-lit) and the number of correct predictions is m, and the number of positive samples in the sample set is n, then the model accuracy is m/n.

The reason why accuracy is chosen as the model evaluation indicator is to ensure that the error rate of the screened positive sample images is small and the screened images are of high quality.

4. Save and deploy the model. Save the trained model and deploy it in the actual running system.

It is understandable that in other embodiments, the above intelligent scoring model can be obtained by training with other algorithms, which is not limited here.

In some embodiments, performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result includes:

Extracting key point information in each of the target images, wherein the key point information includes at least one of nasolabial folds, dark circles, pores, wrinkles, blackheads, and freckles; and,

The skin quality is evaluated according to the key point information in the at least one frame of the target image to obtain a skin quality analysis result.

In some embodiments, the at least one target image frame includes one target image frame and at least two icon images. When the target image is a one-frame target image, skin quality analysis is performed on the target image to obtain the skin quality analysis result. When the target image is a multi-frame target image, skin quality analysis is performed on the multi-frame target images respectively to obtain multiple analysis results, and the skin quality analysis result is obtained after comprehensive analysis based on the multiple analysis results.

In some embodiments, the method further comprises:

Output the image quality score of the at least one frame of target image.

In some embodiments, when the at least one frame of target image is a frame of target image, an image quality score of the frame of target image is output.

In some other embodiments, when the at least one frame of target image is two or more frames of target image, a comprehensive image quality score of the two or more frames of target image may be output.

Please refer to FIG. 4 , which is a flow chart of a skin quality analysis method in another embodiment of the present application.

Step S410: Control the camera device 13 to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period.

Step S420: extracting images from the video stream.

Step S430: performing image quality scoring on the extracted image.

Step S440: Determine whether the image quality score is greater than a system-set threshold, if so, proceed to step S450, otherwise, proceed to step S410.

Step S450: performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result.

Step S460: output the skin quality analysis result and the image quality score.

The overall idea of skin quality analysis in this application is: collect the total video stream, then extract continuous multi-frame images from the video stream, and then extract the face image labels of the continuous multi-frame photos according to the picture quality detection AI algorithm, score the images, and store the output image quality scores. Images that do not meet the image quality requirements are eliminated. If no images that meet the quality requirements are found in the multi-frame images, continuous multi-frame images are extracted from the video stream again, and the image labels are extracted and the evaluation results are scored until the image that meets the image quality requirements is screened out as the target image. Then, the skin quality analysis AI algorithm is used to analyze the skin quality of the target image. Thus, this application realizes skin quality analysis based on high-quality images by connecting the image quality detection AI algorithm and the skin quality analysis AI algorithm in series, so that the analysis results are more stable and the results of different measurements are more comparable.

The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program can be run by a processor to perform the steps of the skin quality analysis method:

Controlling the camera device 13 to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

Selecting at least one frame of image that meets the image quality requirement from the plurality of frames of image of the video stream as at least one frame of target image;

Performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The skin quality analysis result is outputted.

In addition, the memory 11 may include: a flash disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. The processor 12 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a readily available programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The processor may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The processor may be an image processor, a microprocessor, or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, for example, the processor 12 may read an application, a computer instruction, or data in the memory, and complete the steps of the above method executed by the electronic device 1 in combination with its hardware.

Please refer to FIG. 5 , the present application further provides a skin quality analysis device 500, the skin quality analysis device 500 comprising:

An acquisition control module 510 is used to control the camera device to acquire a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period;

An image selection module 520, configured to select at least one frame of image that meets the image quality requirement from the plurality of frames of image in the video stream as at least one frame of target image;

A skin quality analysis module 530, configured to perform skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and

The output control module 540 is used to output the skin quality analysis result.

In the several embodiments provided in the present application, it should be understood that the disclosed skin quality analysis device 500 can be implemented in other ways. For example, the embodiment of the skin quality analysis device 500 described above is only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical or other forms.

In summary, it can be seen that the present application has the above-mentioned excellent characteristics, which can enhance the performance unprecedented in the prior art and become a product with great practical value.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions or improvements made within the ideas and principles of the present application should be included in the protection scope of the present application.

Claims (8)

1. A skin quality analysis method, applied to an electronic device, characterized in that the skin quality analysis method comprises the steps of: Controlling the camera device to collect a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period; Selecting at least one frame of image that meets the image quality requirement from the plurality of frame images of the video stream as at least one frame of target image, wherein selecting at least one frame of image that meets the image quality requirement from the plurality of frame images of the video stream as at least one frame of target image comprises: Extracting multiple frames of images from the video stream; Scoring the multiple frames of images in sequence starting from the first frame of image, and after scoring each frame of image to obtain an image quality score, determining whether the image quality score of the frame of image meets the image quality requirement, and if the image quality score of the frame of image meets the image quality requirement, determining the frame of image to be a target image; If the image quality score of the frame image does not meet the image quality requirement, scoring the next frame image in the multiple frames of images until a target image whose image quality score meets the image quality requirement is determined; When a target image that meets the image quality requirement is not found from the multiple frames of images, a next group of multiple frames of images that are different from the multiple frames of images are extracted from the video stream, and the image quality of the next group of multiple frames of images is scored again until a target image that meets the image quality requirement is selected; The position of each group of multi-frame images in the video stream is random, and the frame images at the same position only appear in one group of multi-frame images; Performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and The skin quality analysis result is outputted. 2. The skin quality analysis method according to any one of claim 1, characterized in that the method further comprises: Output the image quality score of the at least one frame of target image. 3. The skin quality analysis method according to claim 1, characterized in that the step of performing skin quality analysis according to the target image to obtain a skin quality analysis result comprises: When the target image is a frame of target image, skin quality analysis is performed on the target image to obtain the skin quality analysis result; or, When the target image is a multi-frame target image, skin quality analysis is performed on the multi-frame target images respectively to obtain multiple analysis results, and the skin quality analysis result is obtained after comprehensive analysis based on the multiple analysis results. 4. The skin quality analysis method according to claim 1, characterized in that the method further comprises: Inputting a plurality of training images, wherein the plurality of training images cover different situations of the at least one dimension; Training an intelligent scoring model according to the plurality of training images; After the training of the intelligent scoring model is completed, the image quality scoring of each frame of image is performed by inputting each frame of image into the intelligent scoring model to perform image quality scoring. 5. The skin quality analysis method according to claim 1, characterized in that the step of performing skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result comprises: Extract key point information in each frame of the target image, wherein the key point information includes at least one of nasolabial folds, dark circles, pores, wrinkles, blackheads, and freckles; The skin quality is evaluated according to the key point information in the at least one frame of the target image to obtain the skin quality analysis result. 6. An electronic device, characterized in that it comprises a processor, a memory and a camera device, wherein the camera device and the memory are electrically connected to the processor respectively, the memory stores a computer program, and the processor runs the computer program to execute the steps of the skin quality analysis method according to any one of claims 1 to 5. 7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program can be run by a processor to perform the steps of the skin quality analysis method described in any one of claims 1 to 5. 8. A skin quality analysis device, comprising: An acquisition control module, used to control the camera device to acquire a video stream at the target skin, wherein the video stream includes a plurality of frame images within a preset time period; Image selection module for: Selecting at least one frame of image that meets the image quality requirement from the plurality of frame images of the video stream as at least one frame of target image, wherein selecting at least one frame of image that meets the image quality requirement from the plurality of frame images of the video stream as at least one frame of target image comprises: Extracting multiple frames of images from the video stream; Scoring the multiple frames of images in sequence starting from the first frame of image, and after scoring each frame of image to obtain an image quality score, determining whether the image quality score of the frame of image meets the image quality requirement, and if the image quality score of the frame of image meets the image quality requirement, determining the frame of image to be a target image; If the image quality score of the frame image does not meet the image quality requirement, scoring the next frame image in the multiple frames of images until a target image whose image quality score meets the image quality requirement is determined; When a target image that meets the image quality requirement is not found from the multiple frames of images, a next group of multiple frames of images that are different from the multiple frames of images are extracted from the video stream, and the image quality of the next group of multiple frames of images is scored again until a target image that meets the image quality requirement is selected; The position of each group of multi-frame images in the video stream is random, and the frame images at the same position only appear in one group of multi-frame images; a skin quality analysis module, configured to perform skin quality analysis according to the at least one frame of target image to obtain a skin quality analysis result; and The output control module is used to output the skin quality analysis result.