Skin sebum detection method, device and system

Abstract

The application discloses a skin oil detection method, device and system, and relates to the technical field of skin oil detection. The method comprises the following steps: acquiring an electrical resistance value collected when a bioelectric resistance probe is pressed against the skin; controlling a camera component to collect a skin image and obtain a skin original image; performing hair segmentation on the skin original image to obtain a skin segmentation image and a corresponding hair area, calculating a hair area-to-skin original image area ratio to obtain a hair proportion value; obtaining a reflection image of liquid area mirror reflection based on the skin segmentation image, calculating a reflection image area-to-skin segmentation image area ratio to obtain a mirror reflection area proportion value; and obtaining a skin oil value based on the electrical resistance value, the hair proportion value and the mirror reflection area proportion value. The application has the advantages of fast skin oil detection speed, low cost and accurate detection result.

Description

Technical Field

[0001] This invention relates to the field of skin testing technology, and in particular to a method, apparatus and system for detecting skin oil. Background Technology

[0002] Currently, there are two main internationally recognized methods for measuring sebum (skin oil). The first uses the Sebumeter SM810 (Germany CK), which employs internationally recognized... The first method, based on the principle of oil spot photometry, involves pressing a 0.1mm special matte adhesive tape onto the skin. After absorbing the skin's oils, the tape becomes translucent, and the light transmittance changes accordingly. Therefore, its transparency is proportional to the amount of oil absorbed; the more oil absorbed, the greater the light transmittance. The skin's oil content is measured by determining the light transmittance. The second method uses image analysis. After degreasing the skin, an oil-absorbing, viscous microporous membrane is pressed onto it. Since oil does not scatter light, when the air in the micropores of the membrane is replaced by absorbed oil, the membrane becomes transparent, forming light-transmitting spots corresponding to the hair follicle openings. After collecting the tape, specialized image analysis software is used to quantify the number of sebaceous spots, the maximum and minimum values, and the sebum excretion rate of the measured area. Both methods have certain limitations.

[0003] The limitations of the first method are as follows:

[0004] 1. High cost: The CK sebum detection equipment costs tens of thousands of yuan and requires specific oil-absorbing paper consumables;

[0005] 2. Oil-absorbing paper is still affected by moisture, which can lead to a decrease in accuracy;

[0006] 3. The detection results are less accurate for rough skin areas, such as the scalp and other hair-containing areas;

[0007] 4. The process is lengthy; the oil-absorbing paper requires 15 seconds to use, followed by tens of seconds of equipment analysis time.

[0008] The limitations of the second method are as follows:

[0009] 1. The cost is relatively high, and oil-absorbing paper is required during use;

[0010] 2. The detection results are less accurate for rough skin areas, such as the scalp and other hair-containing areas;

[0011] 3. Oil-absorbing paper is still affected by moisture, which can lead to a decrease in accuracy;

[0012] In addition, both methods are performed in a laboratory or the subject is unable to complete the sebum test in the designated area on their own. Summary of the Invention

[0013] The main objective of this invention is to propose a method, device, and system for detecting skin oil, which overcomes the shortcomings of the prior art. It obtains skin oil values ​​based on resistance value, hair ratio value, and specular reflection area ratio value, and has a fast detection speed, low cost, and accurate results.

[0014] The present invention adopts the following technical solution:

[0015] Firstly, a method for detecting skin oil includes:

[0016] Obtain the resistance value when the bioelectrical impedance probe is pressed against the skin;

[0017] Control the camera component to capture skin images and obtain the original skin image;

[0018] Perform hair segmentation on the original skin image to obtain the skin segmentation image and the corresponding hair area. Calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value.

[0019] Based on the skin segmentation map, a reflection image of the liquid region is obtained by specular reflection. The area of ​​the reflection image and the area of ​​the skin segmentation map are calculated to obtain the ratio of the specular reflection area.

[0020] The skin oil value is obtained based on the resistance value, the hair ratio, and the specular reflection area ratio.

[0021] Preferably, after acquiring the resistance value collected when the bioelectrical impedance probe is pressed against the skin, the process specifically includes:

[0022] Multiple resistance values ​​are acquired during the acquisition time, and the final resistance value is obtained after noise reduction and filtering.

[0023] Preferably, filtering the resistance value specifically includes:

[0024] After denoising, a list of resistance values ​​is obtained. The mode of each interval in the resistance value list is obtained, and the average of the modes of all intervals is calculated to obtain the final resistance value.

[0025] Preferably, after obtaining the original skin image, the method further includes:

[0026] Based on a skin classification algorithm, the system identifies whether the original skin image contains skin. If it does, further processing steps are performed; otherwise, no further processing steps are performed, and feedback is provided.

[0027] Preferably, hair segmentation is performed on the original skin image to obtain a skin segmentation image, wherein the skin segmentation image is a skin segmentation image obtained based on the first Mask method, specifically including:

[0028] Convert the original skin image to a grayscale image;

[0029] Perform adaptive histogram equalization to enhance contrast;

[0030] Count and suppress low-brightness pixels;

[0031] Use OTSU for adaptive threshold binarization to obtain a binarized image;

[0032] Gaussian filtering, erosion, and median filtering are applied to the binarized image.

[0033] The skin segmentation map is obtained by performing bit operations on the image after median filtering and the original skin image.

[0034] Preferably, the step of obtaining a reflection image of specular reflection in the liquid region based on the skin segmentation map, wherein the reflection image is a reflection image obtained based on the second masking method, specifically including:

[0035] Read the HSV color space of the skin segmentation map;

[0036] The channels are divided to obtain hue (b), saturation (g), and brightness (v).

[0037] Calculate the mean value of the luminance v channel, then perform mean-removing standardization on the luminance v channel to remove the average luminance value of the channel.

[0038] The brightness v channel is segmented by binarization to obtain the reflection image of the specular reflection in the liquid region.

[0039] Preferably, obtaining the skin oil value based on the resistance value, hair ratio value, and specular reflection area ratio value specifically includes:

[0040] Substituting the resistance value, hair ratio value, and specular reflection area ratio value into the established ternary linear equation, the skin oil value is obtained.

[0041] Preferably, the three-variable linear equation is expressed as follows:

[0042] y = w1*A + w2*B + w3*C + b

[0043] Where y represents the skin oil value; A represents the resistance value; B represents the hair ratio; C represents the specular reflection area ratio; w1, w2, and w3 are coefficients; and b represents a constant term.

[0044] Secondly, a skin oil detection device includes:

[0045] The resistance value acquisition module is used to acquire the resistance value collected when the bioelectrical impedance probe is pressed against the skin;

[0046] The raw skin image acquisition module is used to control the camera component to acquire skin images and obtain raw skin images;

[0047] The hair proportion calculation module is used to segment the hair in the original skin image, obtain the skin segmentation image and the corresponding hair area, and calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value.

[0048] The module for calculating the proportion of specular reflection area is used to obtain a reflection image of the liquid region based on the skin segmentation map, and calculate the proportion of the specular reflection area by comparing the area of ​​the reflection image with the area of ​​the skin segmentation map.

[0049] The skin oil value acquisition module is used to obtain the skin oil value based on the resistance value, hair ratio value, and specular reflection area ratio.

[0050] Thirdly, a skin oil detection system includes: a skin oil detector; the skin oil detector includes a detection head and a housing; two bioelectrical impedance probes are disposed on the surface of the detection head; an imaging component inside the detection head maintains a fixed focal length with the skin in contact with it through a fixed-focus channel; a control circuit board is disposed inside the housing; the control circuit board is respectively connected to the bioelectrical impedance probes and the imaging component; the control circuit board includes the skin oil detection device as described in claim 9.

[0051] Preferably, the skin oil detector further includes a control switch connected to the control circuit board.

[0052] Fourthly, a skin oil detection system includes: a skin oil detector and an external terminal device;

[0053] The skin oil detector includes a detection head and a housing; two bioelectrical impedance probes are disposed on the surface of the detection head; the camera component inside the detection head maintains a fixed focal length with the skin in contact with it through a fixed-focus channel; a control circuit board is disposed inside the housing; the control circuit board is connected to the bioelectrical impedance probes and the camera component respectively; the control circuit board is connected to the external terminal device to send the collected resistance values ​​and the original skin image;

[0054] The external terminal device includes the skin oil detection device.

[0055] Preferably, the skin oil detector further includes a control switch connected to the control circuit board.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0057] (1) The present invention performs skin oil detection based on the collected bioelectric resistance value and skin image. Its advantage is that the user can quickly and independently complete the skin oil detection at a low cost. Furthermore, the present invention performs skin hair segmentation and liquid specular reflection detection based on skin image, which is not affected by the skin area (skin area or scalp area, etc.), making the skin oil detection on skin areas with hair more accurate.

[0058] (2) The present invention performs noise reduction and filtering on multiple resistance values ​​obtained during the acquisition time, so that the final resistance value is more accurate;

[0059] (3) The present invention acquires the original image of the skin through a camera component. The camera component includes a camera and an LED light. The camera is a high-definition fixed-focus camera. It maintains a fixed focal length with the user's skin through a fixed-focus channel, which plays a role in stable acquisition. The camera is equipped with an LED light, which can ensure that the acquired image data is the brightness of the screen.

[0060] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are listed below.

[0061] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0062] Figure 1 This is a flowchart of the skin oil detection method according to Embodiment 1 of the present invention;

[0063] Figure 2 This is a detailed flowchart of the skin oil detection method according to Embodiment 1 of the present invention;

[0064] Figure 3 This is a flowchart of the skin and hair segmentation method according to Embodiment 1 of the present invention;

[0065] Figure 4 This is a diagram showing the effect of skin and hair segmentation according to Embodiment 1 of the present invention; wherein, the left side is the original image and the right side is the segmented image;

[0066] Figure 5 The mirror reflection effect of the liquid area in Embodiment 1 of the present invention Figure 1 The image on the left is the original image, and the image on the right is the one without mirror reflection.

[0067] Figure 6 The mirror reflection effect of the liquid area in Embodiment 1 of the present invention Figure 2The image on the left is the original image, and the white dots on the right represent specular reflections.

[0068] Figure 7 The mirror reflection effect of the liquid area in Embodiment 1 of the present invention Figure 1 The image on the left is the original image, while the white dots on the right show a small amount of specular reflection.

[0069] Figure 8 This is a liquid area mirror reflection effect, which is an embodiment of the invention. Figure 2 The image on the left is the original image, while the image on the right shows a large amount of white mirror reflection.

[0070] Figure 9 This is a schematic diagram illustrating the positive correlation between the skin oil value calculated in Embodiment 1 of the present invention and the actual amount of oil.

[0071] Figure 10 This is a structural block diagram of the skin oil detection device according to Embodiment 1 of the present invention;

[0072] Figure 11 This is a schematic diagram of the skin oil detector of the skin oil detection system according to Embodiment 2 of the present invention;

[0073] Figure 12 This is a structural block diagram of the skin oil detection system according to Embodiment 3 of the present invention. Detailed Implementation

[0074] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0075] In the description of this invention, it should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0076] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," "top / bottom," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0077] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installed", "equipped", "sleeved / connected", "connected", etc., should be interpreted broadly. For example, "connection" 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 a connection within two components. For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances.

[0078] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the step identifiers S101, S102, S103, etc. are used only for convenience of description and do not indicate the execution order. The corresponding execution order can be adjusted.

[0079] Example 1

[0080] See Figure 1 and Figure 2 As shown, this embodiment of a skin oil detection method includes:

[0081] S101, Obtain the resistance value collected when the bioelectrical impedance probe is pressed against the skin;

[0082] S102, control the camera component to acquire skin images and obtain the original skin image;

[0083] S103, Perform hair segmentation on the original skin image to obtain the skin segmentation image and the corresponding hair area, and calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value.

[0084] S104. Based on the skin segmentation map, obtain the reflection image of the liquid region's specular reflection, and calculate the ratio of the area of ​​the reflection image to the area of ​​the skin segmentation map to obtain the specular reflection area ratio.

[0085] S105 obtains the skin oil value based on the resistance value, the hair ratio value, and the specular reflection area ratio value.

[0086] Specifically, the execution entity of S101 to S105 can be the control circuit board of the skin oil detector, specifically the control module on the control circuit board (such as a microcontroller or MCU control chip), or the execution entity of S101 to S106 can be an external terminal device or a cloud server, or some steps can be implemented on the control circuit board of the skin oil detector and some steps can be implemented on an external terminal device (mobile phone, tablet computer, embedded device, etc.) or a cloud server. The specific settings can be configured as needed, and this embodiment does not impose any restrictions.

[0087] In this embodiment, the bioelectrical impedance probe is disposed on the surface of the detection head of the skin oil detector. In actual use, the user holds the skin oil detector, places the detection head (the end with the bioelectrical impedance probe) close to and against the skin area to be tested, operates the control switch to turn on the device, activates the camera assembly, and simultaneously acquires bioelectrical impedance values ​​and RGB image data. The skin oil detection in the test area is then completed through the control circuit board and / or terminal device.

[0088] Specifically, the detection head has two bioelectrical impedance probes on its surface and a high-definition magnifying camera (such as an RGB camera) inside.

[0089] The two bioelectrical impedance probes used employ a two-probe method to measure resistivity. The principle is that water has high conductivity, while oil does not. Current flows into the skin through one probe, travels a fixed distance, and is received by the other probe. The resistivity is calculated by analyzing the potential difference between the two probes. Therefore, bioelectrical impedance probes are used to detect the skin's moisture level.

[0090] Skin images are acquired by an RGB camera, a high-definition fixed-focus camera that maintains a fixed focal length with the subject's skin through the device's fixed-focus channel, thus providing stability. The RGB camera is equipped with LEDs to ensure the acquired image data reflects the brightness of the scene.

[0091] In this embodiment, after obtaining the resistance value collected when the bioelectrical impedance probe is pressed against the skin, the specific steps include:

[0092] Multiple resistance values ​​are acquired within the acquisition time (e.g., multiple resistance values ​​within the image capture time). After removing corresponding noise data, a list of valid resistance values ​​is obtained. A resistance value filtering algorithm is then used to obtain the final bioresistance value for further data fusion analysis. The filtering algorithm can be used to obtain the mode of each interval in the list and calculate the average of the modes of all intervals to obtain the final resistance value A.

[0093] Furthermore, after obtaining the original skin image, the process also includes:

[0094] Based on a skin classification algorithm, the system identifies whether the original skin image contains skin. If it does, further processing steps are performed; otherwise, no further processing steps are performed, and feedback is provided.

[0095] Specifically, skin classification algorithms can use deep classification models. By collecting data containing skin and non-skin data, a classification model is trained, and the classification model is used to classify skin and non-skin data.

[0096] The main purpose of skin classification detection is to prevent images from being entirely composed of non-skin areas, which would make it impossible to accurately analyze oil levels. For example, if only hair is captured and the scalp is not, the detection results may be inaccurate. Therefore, timely prompts are provided during image capture to improve the user experience.

[0097] See Figure 3 As shown, the hair segmentation of the original skin image is performed to obtain a skin segmentation image, wherein the skin segmentation image is a skin segmentation image obtained based on the first Mask method, specifically including:

[0098] Convert the original skin image to a grayscale image;

[0099] Perform adaptive histogram equalization to enhance contrast;

[0100] Count and suppress low-brightness pixels;

[0101] Use OTSU for adaptive threshold binarization to obtain a binarized image;

[0102] Gaussian filtering, erosion, and median filtering are applied to the binarized image.

[0103] The skin segmentation map is obtained by performing bit operations on the image after median filtering and the original skin image.

[0104] Specifically, since users may need to detect oiliness on their scalp, skin and hair segmentation is required. As shown above, the original skin image is converted to grayscale, and a series of image algorithm operations are used to obtain the skin segmentation map (i.e., the first mask image, see [link]). Figure 4 (On the right side), the obtained first mask image is subjected to bitwise operations with the original image to achieve hair segmentation, and the hair proportion value B is calculated by comparing the hair area with the image area. The hair area and the original image area are calculated by calculating the image resolution.

[0105] Furthermore, a Frangi filter can be used for direct filtering, extracting features while simultaneously calculating gradients and setting a brightness threshold to suppress low-brightness pixels. The brightness threshold is set manually using a large amount of statistical data.

[0106] In this embodiment, the step of obtaining a reflection image of the liquid region based on the skin segmentation map, wherein the reflection image is a reflection image obtained based on the second Mask method, specifically including:

[0107] Read the HSV color space of the skin segmentation map;

[0108] The channels are divided to obtain hue (b), saturation (g), and brightness (v).

[0109] Calculate the mean value of the luminance v channel, then perform mean-removing standardization on the luminance v channel to remove the average luminance value of the channel.

[0110] The brightness v channel is segmented by binarization to obtain the reflection image of the specular reflection in the liquid region.

[0111] Based on the obtained reflection image (i.e. the second mask image), the ratio of the reflective area to the skin segmentation area is calculated to obtain the specular reflection area ratio C.

[0112] See the image showing the specular reflection effect of liquid areas on the skin and scalp. Figures 5-8 As shown.

[0113] Furthermore, the method of obtaining skin oil value based on resistance value, hair ratio value, and specular reflection area ratio specifically includes:

[0114] Substituting the resistance value, hair ratio value, and specular reflection area ratio value into the established ternary linear equation, the skin oil value is obtained.

[0115] The three-variable linear equation is expressed as follows:

[0116] y = w1*A + w2*B + w3*C + b

[0117] Where y represents the skin oil value; A represents the resistance value; B represents the hair ratio; C represents the specular reflection area ratio; w1, w2, and w3 are coefficients; and b represents a constant term.

[0118] In this embodiment, the fitted values ​​of w1, w2, and w3 are -0.00357934, 0.16272439, and 0.45652927, respectively, and the fitted value of b is 0.33126512.

[0119] The specific fitting process for a ternary linear equation can be based on the test data in Table 1 below.

[0120] Table 1

[0121]

[0122] Specifically, the actual amount of sebum can be obtained experimentally for different oil ranges (oil area percentage), water-oil ratios, resistivity, hair percentage, and specular reflection area percentage. A ternary linear equation is then fitted, with resistivity, hair percentage, and specular reflection area percentage as variables. In actual testing, skin sebum is calculated based on the obtained resistivity, hair percentage, and specular reflection area percentage as variables. A schematic diagram showing the fitting between the calculated skin sebum value and the actual sebum amount is shown below. Figure 9 As shown, from Figure 9 It can be seen that the skin oil value obtained through this embodiment is positively correlated with the actual amount of oil, indicating that the method of the present invention has high accuracy and conforms to the real situation.

[0123] See Figure 10 As shown, this embodiment also discloses a skin oil detection device, including:

[0124] The resistance value acquisition module 1001 is used to acquire the resistance value collected when the bioelectrical impedance probe is pressed against the skin;

[0125] The raw skin image acquisition module 1002 is used to control the camera component to acquire skin images and obtain raw skin images.

[0126] The hair proportion calculation module 1003 is used to perform hair segmentation on the original skin image, obtain the skin segmentation image and the corresponding hair area, and calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value.

[0127] The specular reflection area ratio calculation module 1004 is used to obtain a reflection image of the specular reflection of the liquid region based on the skin segmentation map, and calculate the area of ​​the reflection image and the area of ​​the skin segmentation map to obtain the specular reflection area ratio.

[0128] The skin oil value acquisition module 1005 is used to obtain the skin oil value based on the resistance value, hair ratio value, and specular reflection area ratio value.

[0129] The specific implementation of each module of a skin oil detection device and the same skin oil detection method will not be described again in this embodiment.

[0130] Example 2

[0131] See Figure 11As shown, this embodiment discloses a skin oil detection system, comprising: a skin oil detector; the skin oil detector includes a detection head 111 and a housing 112; two bioelectrical impedance probes 1111 are disposed on the surface of the detection head 111; an imaging component 1112 inside the detection head 111 maintains a fixed focal length with the skin in contact through a fixed-focus channel 1113; a control circuit board 1121 is disposed inside the housing 112; the control circuit board 1121 is respectively connected to the bioelectrical impedance probes 1111 and the imaging component 1112; the control circuit board 1121 includes the skin oil detection device, i.e., used to execute the steps of the skin oil detection method.

[0132] The skin oil detector also includes a control switch 1122 connected to the control circuit board 1121.

[0133] After activating the control switch 1122, the skin oil detector is powered on. Once the detection head 111 touches the skin, resistance acquisition and image acquisition can be initiated.

[0134] In this embodiment, the control circuit board 1121 can send the calculated skin oil value to an external terminal device, which can then display the detection result to the user. Alternatively, the control circuit board 1121 can control a voice prompt to inform the user of the detection result. This embodiment does not limit how the result is presented.

[0135] Example 3

[0136] See Figure 12 As shown in the figure, this embodiment of a skin oil detection system includes: a skin oil detector 1201 and an external terminal device 1202; the skin oil detector includes a detection head and a housing; two bioelectrical impedance probes are disposed on the surface of the detection head; an imaging component inside the detection head maintains a fixed focal length with the skin in contact through a fixed-focus channel; a control circuit board is disposed inside the housing; the control circuit board is respectively connected to the bioelectrical impedance probes and the imaging component; the control circuit board is connected to the external terminal device to transmit the collected resistance values ​​and the original skin image; the external terminal device includes the aforementioned skin oil detection device.

[0137] The skin oil detector also includes a control switch connected to the control circuit board.

[0138] The structure of the skin oil detector is shown in [reference]. Figure 11 As shown.

[0139] In this embodiment, the skin oil detector 1201 and the external terminal device 1202 are connected via Wi-Fi. Specifically, the control circuit board contains a Wi-Fi transmitting component, which can establish a wireless connection with the external terminal device 1202 via Wi-Fi signal.

[0140] The external terminal device 1202 includes mobile phones, tablets, and embedded devices, which are connected to the skin oil detector 1201 through a mini-program or APP software.

[0141] The usage procedure of the skin oil detection system in this embodiment is as follows:

[0142] 1. Open the app or mini-program software on the external terminal device analysis system, and simultaneously press and hold the control switch to turn on the skin oil detector;

[0143] 2. After the skin oil detector is turned on, it can automatically emit a Wi-Fi signal. The App or mini-program on the external terminal device can connect to the device's Wi-Fi.

[0144] 3. After connecting, open the device camera through the App or mini-program, place the detection head of the skin oil detector on the skin area to be detected, and control the App or mini-program to collect skin data. Alternatively, you can use the control switch on the device to complete the skin data acquisition.

[0145] 4. The acquired skin data includes signals and RGB image data within the bioelectrical impedance probe time frame. The data is sent to the system app or mini-program via Wi-Fi signal.

[0146] 5. Click to confirm the completion of the skin oil test and generate a report on the App or mini-program;

[0147] 6. The APP or mini-program uses mobile phones, tablets, embedded devices, etc. as carriers to perform skin oil analysis after acquiring skin oil data.

[0148] For the specific skin oil analysis process, please refer to the specific implementation of the skin oil detection method in Example 1. This example will not provide a detailed description.

[0149] The above description is merely a preferred embodiment of the present invention; however, the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and its improved concepts, should be covered within the scope of protection of the present invention.

Claims

1. A method for detecting skin oil, characterized in that, include: Obtain the resistance value when the bioelectrical impedance probe is pressed against the skin; Control the camera component to capture skin images and obtain the original skin image; Perform hair segmentation on the original skin image to obtain the skin segmentation image and the corresponding hair area. Calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value. Based on the skin segmentation map, a reflection image of the liquid region is obtained by specular reflection. The area of ​​the reflection image and the area of ​​the skin segmentation map are calculated to obtain the ratio of the specular reflection area. Skin oil levels are obtained based on resistance, hair percentage, and specular reflection area percentage, specifically including: The resistance value, hair percentage value, and specular reflection area percentage value are input into a preset skin oil value calculation model, and the skin oil value is output through the calculation model; wherein the calculation model is a ternary linear equation: y = w1*A + w2*B + w3*C + b; Where y represents the skin oil value; A represents the resistance value; B represents the hair ratio value; C represents the specular reflection area ratio value; w1, w2 and w3 are coefficients; and b represents a constant term.

2. The method for detecting skin oil according to claim 1, characterized in that, After obtaining the resistance value collected when the bioelectrical impedance probe is pressed against the skin, the specific steps include: Multiple resistance values ​​are acquired during the acquisition time, and the final resistance value is obtained after noise reduction and filtering.

3. The method for detecting skin oil according to claim 2, characterized in that, Filtering the resistance value specifically includes: After denoising, a list of resistance values ​​is obtained. The mode of each interval in the resistance value list is obtained, and the average of the modes of all intervals is calculated to obtain the final resistance value.

4. The method for detecting skin oil according to claim 1, characterized in that, After obtaining the original skin image, the process also includes: Based on a skin classification algorithm, the system identifies whether the original skin image contains skin. If it does, further processing steps are performed; otherwise, no further processing steps are performed, and feedback is provided.

5. The method for detecting skin oil according to claim 1, characterized in that, Hair segmentation is performed on the original skin image to obtain a skin segmentation image, wherein the skin segmentation image is a skin segmentation image obtained based on the first Mask method, specifically including: converting the original skin image into a grayscale image; Perform adaptive histogram equalization to enhance contrast; Count and suppress low-brightness pixels; Use OTSU for adaptive threshold binarization to obtain a binarized image; Gaussian filtering, erosion, and median filtering are applied to the binarized image. The skin segmentation map is obtained by performing bit operations on the image after median filtering and the original skin image.

6. The method for detecting skin oil according to claim 1, characterized in that, The process involves obtaining a reflection image of the liquid region based on the skin segmentation map. This reflection image is obtained using a second masking method and specifically includes: Read the HSV color space of the skin segmentation map; The channels are divided to obtain hue (b), saturation (g), and brightness (v). Calculate the mean value of the luminance v channel, then perform mean-removing standardization on the luminance v channel to remove the average luminance value of the channel. The brightness v channel is segmented by binarization to obtain the reflection image of the specular reflection in the liquid region.

7. A skin oil detection device, characterized in that, include: The resistance value acquisition module is used to acquire the resistance value collected when the bioelectrical impedance probe is pressed against the skin; The raw skin image acquisition module is used to control the camera component to acquire skin images and obtain raw skin images; The hair proportion calculation module is used to segment the hair in the original skin image, obtain the skin segmentation image and the corresponding hair area, and calculate the ratio of the hair area to the area of ​​the original skin image to obtain the hair proportion value. The module for calculating the proportion of specular reflection area is used to obtain a reflection image of the liquid region based on the skin segmentation map, and calculate the proportion of the specular reflection area by comparing the area of ​​the reflection image with the area of ​​the skin segmentation map. The skin oil value acquisition module is used to obtain the skin oil value based on the resistance value, hair ratio value, and specular reflection area ratio. Skin oil levels are obtained based on resistance, hair percentage, and specular reflection area percentage, specifically including: The resistance value, hair percentage value, and specular reflection area percentage value are input into a preset skin oil value calculation model, and the skin oil value is output through the calculation model; wherein the calculation model is a ternary linear equation: y = w1*A + w2*B + w3*C + b; Where y represents the skin oil value; A represents the resistance value; B represents the hair ratio value; C represents the specular reflection area ratio value; w1, w2 and w3 are coefficients; and b represents a constant term.

8. A skin oil detection system, characterized in that, include: A skin oil detector; the skin oil detector includes a detection head and a housing; two bioelectrical impedance probes are disposed on the surface of the detection head; an imaging component inside the detection head maintains a fixed focal length with the skin in contact with it through a fixed-focus channel; a control circuit board is disposed inside the housing; the control circuit board is respectively connected to the bioelectrical impedance probes and the imaging component; the control circuit board includes the skin oil detection device as described in claim 7.

9. The skin oil detection system according to claim 8, characterized in that, The skin oil detector also includes a control switch connected to the control circuit board.

10. A skin oil detection system, characterized in that, include: Skin oil analyzer and external terminal equipment; The skin oil detector includes a detection head and a housing; two bioelectrical impedance probes are disposed on the surface of the detection head; the camera component inside the detection head maintains a fixed focal length with the skin in contact with it through a fixed-focus channel; a control circuit board is disposed inside the housing; the control circuit board is connected to the bioelectrical impedance probes and the camera component respectively; the control circuit board is connected to the external terminal device to send the collected resistance values ​​and the original skin image; The external terminal device includes the skin oil detection device as described in claim 7.

11. The skin oil detection system according to claim 10, characterized in that, The skin oil detector also includes a control switch connected to the control circuit board.

Images