Method and device for acquiring skin sub-information by using multiple wavelengths

Abstract

According to various embodiments, as a multi-wavelength skin analysis device, the multi-wavelength skin analysis device may include: a skin state measurement unit that measures a skin state of a user using a camera and a multi-wavelength light source unit; a multi-purpose skin analysis information acquisition unit that acquires skin analysis information of the user by using the multi-wavelength image acquired by the multi-wavelength light source unit; and a solution provision unit that provides recommended cosmetic-related information corresponding to the measured skin state, the multi-purpose skin analysis information acquisition unit may include: a melanin distribution confirmation unit that determines a melanin state of the skin of the user; a black eye cause determination unit for determining black eye causes; and a wrinkle cause determination unit that corresponds to the wrinkle generation layer classification.

Description

Technical Field

[0001] The present invention relates to a method and device for obtaining skin analysis information using multiple wavelengths, and in particular to a method and device for obtaining multi-purpose skin analysis information such as skin melanin distribution, classification of dark circle causes, and cause judgment based on wrinkle generation layer classification using multiple wavelengths. Background Art

[0002] Unless otherwise stated in this specification, the content described in this section is not prior art related to the claims of this application and cannot be admitted to be prior art by virtue of inclusion in this section.

[0003] Recently, people are paying more and more attention to skin health, especially facial skin health. With the increase of people's attention to skin health, various cosmetics and beauty equipment have emerged on the market. In particular, a skin condition measurement method has been developed that analyzes various skin problems (such as wrinkles, pores, and acne) on the user's face by photographing the user's facial skin.

[0004] In the skin condition measurement method currently used to analyze the skin, a skin condition measuring device or even an instrument is used to photograph the user's face according to pre-set shooting parameters (such as the intensity, direction, aperture value or shutter speed of the light source, etc.) and the user's skin condition is measured based on the photographed facial micro-basis of the user.

[0005] However, the parameters used in the above-mentioned method for measuring the skin condition of a user based on a facial image are not sufficient for diagnosing the skin, and can only diagnose the surface skin condition, making it difficult to find the root cause of the problem. For example, in the case of diagnosing the wrinkles of a user, when a 2D image analysis system using only white light or ultraviolet (UV) wavelength as a light source is used to diagnose the wrinkles of a user, it is difficult to classify the fine lines of the epidermis and the deep wrinkles generated in the dermis because they are mixed with each other.

[0006] Furthermore, with the above method, it is difficult to perform multiple analyses on the skin with only one measurement. Therefore, it is necessary to develop a method that can obtain multi-purpose skin analysis information using a multi-wavelength light source when diagnosing the skin. Summary of the invention

[0007] Problem that the invention aims to solve

[0008] The present invention aims to solve the above-mentioned problems, and its purpose is to provide a method and device for simultaneously acquiring multi-purpose skin analysis information through multiple wavelengths by utilizing the changes in absorption and scattering in the skin according to the wavelength length and the difference in light penetration depth.

[0009] Solutions for solving problems

[0010] According to multiple embodiments, a multi-wavelength skin analysis device may include: a skin condition measuring unit, which uses a camera and a multi-wavelength light source unit to measure the skin condition of a user; a multi-purpose skin analysis information acquisition unit, which acquires the skin analysis information of the user by using the multi-wavelength image acquired by the multi-wavelength light source unit; and a solution providing unit, which provides information related to recommended cosmetics corresponding to the measured skin condition.

[0011] According to multiple embodiments, the multi-purpose skin analysis information acquisition unit may include: a melanin distribution confirmation unit, which determines the melanin status of the user's skin; a dark circle cause judgment unit, which determines the cause of dark circles; and a wrinkle cause judgment unit, which corresponds to the wrinkle generation layer classification; etc.

[0012] According to a plurality of embodiments, the melanin distribution confirmation unit may acquire a first wavelength image using a first light source of a first wavelength, and acquire a second wavelength image using a second light source of a second wavelength having a wavelength smaller than the first wavelength, extract a first melanin region image based on the first wavelength image, and extract a second melanin region image based on the second wavelength image, and then combine the first melanin region image and the second melanin region image with the skin image of the user, thereby acquiring a melanin distribution image through the combination. As a similar method, a method may be included in which the wavelength image acquisition and melanin region image extraction processes are repeatedly performed using two or more light sources of different wavelengths, and a method of acquiring a melanin multi-stage distribution image corresponding to the melanin light absorption characteristics of each wavelength through the combination may be included.

[0013] According to multiple embodiments, the melanin distribution confirmation unit can use a third light source with the longest third wavelength among the multiple wavelength light sources to obtain a third wavelength image, and use a fourth light source with the shortest fourth wavelength among the multiple wavelength light sources to obtain a fourth wavelength image, and then generate a differential image based on the third wavelength image and the fourth wavelength image, thereby obtaining a melanin distribution image that highlights the melanin area based on the generated differential image.

[0014] According to multiple embodiments, the dark circle cause judgment unit can detect the dark circle area of ​​the user from the skin image of the user acquired by the camera, and when a melanin component exceeding a pre-set first component amount is detected from the detected dark circle area, the cause of the dark circles of the user is determined to be caused by pigmentation; and when a hemoglobin component exceeding a pre-set second component amount is detected from the detected dark circle area, the cause of the dark circles of the user is determined to be caused by vasodilation.

[0015] According to multiple embodiments, the wrinkle cause determination unit can obtain a first wrinkle image based on a fifth light source having a fifth wavelength among the multiple wavelengths, and obtain a second wrinkle image based on a sixth light source having a sixth wavelength having a wavelength greater than the fifth wavelength, and then determine a wrinkle classification according to the wrinkle generating layer of the user and a corresponding main wrinkle cause based on the first wrinkle image and the second wrinkle image, wherein the first wrinkle image is an epidermal wrinkle image, and the second wrinkle image is a dermal wrinkle image.

[0016] Effects of the Invention

[0017] Through the various embodiments disclosed in this document, multi-purpose skin analysis information can be obtained simultaneously using multiple wavelengths.

[0018] Furthermore, through various embodiments, the distribution of melanin in the user's skin may be confirmed using a multi-wavelength light source.

[0019] In addition, through multiple embodiments, the causes of dark circles can be clarified using a multi-wavelength light source, and a solution to the dark circles can be provided based on the causes.

[0020] In addition, through multiple embodiments, a multi-wavelength light source can be used to classify superficial wrinkles on the epidermis and deep wrinkles generated on the dermis, and a user-personalized solution can be proposed based on the wrinkle generation layer classification.

[0021] Furthermore, various effects that can be grasped directly or indirectly through this document can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic diagram illustrating a multi-wavelength skin analysis system according to an embodiment.

[0023] Figure 2 This is a schematic diagram illustrating the main components of a multi-wavelength skin analysis device.

[0024] Figure 3 This is a schematic diagram related to the process of confirming the melanin distribution of the user's skin through a multi-wavelength light source.

[0025] Figure 4 A schematic diagram relating to a process of determining the cause of a user's dark circles using a multi-wavelength light source.

[0026] Figure 5 It is a schematic diagram related to a process of determining the cause of wrinkles classified according to the wrinkle generating layer of the user's skin by using a multi-wavelength light source.

[0027] Figure 6 It is based on Figure 1 A schematic diagram illustrating the hardware structure of a multi-wavelength skin analysis device. DETAILED DESCRIPTION

[0028] The present invention can be modified in many ways and has many embodiments. Specific embodiments will be illustrated in the accompanying drawings and described in detail. However, this is not intended to limit the present invention to a specific embodiment, but should be understood to include all modifications, equivalents and even substitutes included in the concept and technical scope of the present invention. In the process of describing each of the drawings, similar reference numbers are used for similar components.

[0029] In the process of describing multiple components, terms such as first, second, A and B may be used, but the components are not limited by the terms. The terms are only used to distinguish one component from other components. For example, without departing from the scope of the claims of the present invention, the first component can be named as the second component, and similarly, the second component can be named as the first component. The term and / or includes a combination of multiple related recorded items or one of multiple related recorded items.

[0030] When a certain component is recorded as being "connected" or "connected" to other components, it may be directly connected or connected to the other components, but it should be understood that other components may exist between the two. On the contrary, when a certain component is recorded as being "directly connected" or "directly connected" to other components, it should be understood that no other components exist between the two.

[0031] The terms used in this application are only used to illustrate specific embodiments and are not intended to limit the present invention. Unless the context clearly indicates otherwise, singular statements also include plural meanings. In this application, terms such as "including" or "having" are only used to indicate the existence of features, numbers, steps, actions, constituent elements, parts or combinations described in the specification, and should not be understood as excluding in advance the possibility that one or more other features, numbers, steps, actions, constituent elements, parts or combinations described may exist or be added.

[0032] Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as those commonly understood by persons having general knowledge of the technical field to which the present invention belongs. Commonly used terms defined in dictionaries should be interpreted as consistent with the meaning in the context of the relevant technology, and should not be interpreted as overly idealized or exaggerated meanings unless clearly defined in this application.

[0033] Next, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

[0034] Figure 1 is a schematic diagram illustrating a multi-wavelength skin analysis system 10 according to an embodiment. Figure 1 The multi-wavelength skin analysis system 10 may include a multi-wavelength skin analysis device 100 and a user terminal 200 .

[0035] The multi-wavelength skin analysis device 100 may include a multi-wavelength light source unit (e.g., an ultraviolet light source unit, a visible light source unit, and a near infrared light source unit) and a photographing unit (e.g., a camera), and may measure the skin condition of the user through the multi-wavelength light source unit and the photographing unit. The multi-wavelength skin analysis device 100 may extract the melanin distribution, determine the cause of the user's dark circles, and determine the cause of the user's wrinkles based on the multi-wavelength image acquired through the multi-wavelength light source unit and the user's facial image acquired through the photographing unit.

[0036] The user terminal 200 may be a device capable of communication, such as a desktop computer, a laptop computer, a notebook, a smart phone, a tablet PC, a mobile phone, a smart watch, a smart glass, an e-book reader, a portable multimedia player (PMP), a portable game console, a navigation device, a digital camera, a digital multimedia broadcasting (DMB) player, a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, and a personal digital assistant (PDA).

[0037] The multi-wavelength skin analysis device 100 and the user terminal 200 may be respectively connected to a communication network and perform data transmission and reception between each other through the communication network. For example, as the communication network, a local area network (LAN), a metropolitan area network (MAN), a global system for mobile communications (GSM), an enhanced data rate for global mobile communications system evolution technology (EDGE), a high speed downlink packet access (HSDPA), a wideband code division multiple access (W-CDMA), a code division multiple access (CDMA), a time division multiple access (TDMA), a Bluetooth, a Zigbee, a wireless fidelity (Wi-Fi), a voice over Internet Protocol (VoIP), a long term evolution technology upgraded version (LTE Advanced), IEEE802.16m, an advanced wireless metropolitan area network (WirelessMAN-Advanced), a high speed packet access upgraded version (HSPA+), a long term evolution technology (Long Term Evolution) of the third generation partnership project (3GPP), a mobile global microwave interconnection access (Mobile WiMAX, IEEE 802.16e), Ultra Mobile Broadband (UMB, formerly known as EV-DO Rev. C), Flash-OFDM, iBurst, Mobile Broadband Wireless Access (MBWA, IEEE 802.20), High-Performance Wireless Metropolitan Area Network (HIPERMAN), Beam-Division Multiple Access (BDMA), World Interoperability for Microwave Access (Wi-MAX) and 5G, among other types of wired or wireless networks.

[0038] Figure 2 This is a schematic diagram illustrating the main components of the multi-wavelength skin analysis device 100. Figure 2The multi-wavelength skin analysis device 100 may include a skin condition measurement unit 101, a multi-purpose skin analysis information acquisition unit 102, a melanin distribution confirmation unit (or determination unit) 1021, a dark circle cause judgment unit (or determination unit) 1022, a wrinkle cause judgment unit (or determination unit) 1023, and a solution providing unit 103. For a general technician, the multi-purpose skin analysis information acquisition unit 102 is not limited to including the melanin distribution confirmation unit (or determination unit) 1021, the dark circle cause judgment unit (or determination unit) 1022, and the wrinkle cause judgment unit (or determination unit) 1023, and may also include other analysis units that can perform analysis using multiple wavelengths.

[0039] The skin condition measurement unit 101 may include an ultraviolet light source unit for irradiating ultraviolet rays, a visible light source unit for irradiating visible rays, and an infrared light source unit for irradiating near infrared rays. In addition to the multi-wavelength light source unit, the skin condition measurement unit 101 may also include an image capture unit equipped with a camera, a polarizing plate, a diffusion plate, and a distance detection sensor.

[0040] The skin condition measurement unit 101 may irradiate the user's skin with a multi-wavelength light source including ultraviolet (UV), visible light (VIS), and near infrared (NIR) light sources. The skin condition measurement unit 101 may photograph the user's skin through the photographing unit while irradiating the multi-wavelength light source. The skin condition measurement unit 101 may obtain a skin image of the user through the photographing.

[0041] The skin condition measuring unit 101 may sequentially irradiate multiple light sources such as ultraviolet rays, visible rays, and infrared rays, and obtain wavelength band images corresponding to the multiple light sources through a camera, and a wavelength band filter may be included in the light source or the camera.

[0042] Figure 3 This is a schematic diagram related to the process of confirming the melanin distribution of the user's skin through a multi-wavelength light source.

[0043] The melanin distribution confirmation unit 1021 can confirm the melanin distribution by using a multi-wavelength light source. The melanin distribution confirmation unit 1021 can obtain a melanin distribution image based on absorbance characteristics according to wavelengths by using a multi-wavelength light source and calculate a melanin index.

[0044] In step S310, the melanin distribution confirmation unit 1021 can use light sources of various wavelengths to obtain images of various wavelengths. At relatively short wavelengths (for example, visible light below 450nm and ultraviolet A), due to the higher melanin absorbance, even areas with low melanin density will show high contrast with surrounding skin tissue in the image. At relatively long wavelengths (for example, visible light above 750nm and near-infrared rays), due to the lower melanin absorbance, only areas with relatively high melanin density will show high contrast with surrounding skin tissue in the image.

[0045] In step S320, the melanin distribution confirmation unit 1021 can perform binarization on each wavelength image respectively (for example: Otsu's Thresholding). The melanin distribution confirmation unit 1021 can extract the melanin area of ​​each wavelength image that performs binarization respectively. In step S330, the melanin distribution confirmation unit 1021 can combine the extracted melanin area related image with the user's skin image (skin image). In step S340, the melanin distribution image can be obtained through the combination.

[0046] In other words, the melanin distribution confirmation unit 1021 can use a first light source with a first wavelength to obtain a first wavelength image, and use a second light source with a second wavelength having a wavelength smaller than the first wavelength to obtain a second wavelength image. The melanin distribution confirmation unit 1021 can extract a first melanin area based on the first wavelength image, and extract a second melanin area based on the second wavelength image. The melanin distribution confirmation unit 1021 can obtain a melanin distribution image by combining the first melanin area image and the second melanin area image with the skin image of the user. The melanin distribution confirmation unit 1021 can also include a method of repeatedly performing the wavelength image acquisition and melanin area image extraction processes using two or more light sources with different wavelengths, and obtaining a melanin multi-stage distribution image corresponding to the melanin light absorption characteristics of each wavelength through the combination.

[0047] In step S311, the melanin distribution confirmation unit 1021 can respectively determine two wavelengths of light sources with large differences in light absorption of melanin. In step S321, the melanin distribution confirmation unit 1021 can obtain two wavelength images (for example, a first wavelength image and a second wavelength image) with large differences in light absorption on melanin. In step S331, the melanin distribution confirmation unit 1021 can generate a differential image based on the first wavelength image and the second wavelength image.

[0048] In other words, the melanin distribution confirmation unit 1021 can use the third light source with the longest third wavelength among the multiple wavelength light sources to obtain a third wavelength image, and use the fourth light source with the shortest fourth wavelength among the multiple wavelength light sources to obtain a fourth wavelength image. The melanin distribution confirmation unit 1021 can generate a differential image based on the third wavelength image and the fourth wavelength image. In step S340, the melanin distribution confirmation unit 1021 can generate a melanin distribution image (e.g., a melanin emphasized image) based on the differential image.

[0049] The melanin distribution confirmation unit 1021 may calculate the ratio of the pixel value included in the melanin region to the light source intensity before light absorption, and calculate the melanin level (melanin index) based on the calculated ratio.

[0050] In other words, when the ratio of the irradiated light to the detected light diffused and reflected inside the skin (diffuse reflectance) is defined as "R", the optical density (OD) is as follows, and the melanin index image can be obtained by multiplying the optical density difference of the pixels corresponding to the same position in the two wavelength images with different light absorbance by a complementary constant to calculate the optical density gradient, and then the melanin level can be calculated by calculating the index average value of the entire image or the melanin area.

[0051] [Formula 1]

[0052] .

[0053] In Math Formula 1, OD may refer to the optical density, and R may refer to the ratio of irradiation light to detection light diffused and reflected inside the skin.

[0054] Figure 4 A schematic diagram relating to a process of determining the cause of a user's dark circles using a multi-wavelength light source.

[0055] The dark circle cause determination unit 1022 may measure the melanin component and the hemoglobin component by using multiple wavelengths, and determine the cause of the dark circle based on the measured melanin component and the hemoglobin component.

[0056] The dark circle cause determination unit 1022 may detect an eye region from the user's facial image. The dark circle cause determination unit 1022 may detect a dark circle region adjacent to the eye region from the user's facial image. The dark circle cause determination unit 1022 may further restrictively select a dark circle region, and determine a dark circle expected region in order to detect dark circles within a restricted region. The dark circle cause determination unit 1022 may detect a left eye and a right eye in the acquired facial image, and determine the outermost contours of the detected left eye and right eye, respectively, and further determine a position bent at an angle greater than a preset angle from the determined outermost contours. For example, the dark circle cause determination unit 1022 may determine a first position and a second position bent at an angle greater than a preset angle from a first outermost contour corresponding to the left eye, and determine a third position and a fourth position bent at an angle greater than a preset angle from a second outermost contour corresponding to the right eye.

[0057] The dark circle cause determination unit 1022 may calculate a first distance between the first position and the second position, and calculate a second distance between the third position and the fourth position. The dark circle cause determination unit 1022 may determine a first area from the first lowermost position of the first outermost contour corresponding to the left eye to a position at a first distance downward, and a second area from the second lowermost position of the second outermost contour corresponding to the right eye to a position at a second distance downward as the expected dark circle area.

[0058] The dark circle cause determination unit 1022 may learn the artificial neural network model, i.e., the dark circle region detection model, and input the user's facial image into the learned dark circle region detection model. In step S410, the dark circle cause determination unit 1022 may detect or even determine the dark circle region by inputting the user's facial image into the model.

[0059] The dark circle cause determination unit 1022 may use facial images of people with dark circles as learning data. The facial images of people with dark circles may be obtained from a database included in the device 100 or even the terminal 200, or from an external database (DB). According to an embodiment, the learning data may be training data that uses feature points of a facial image as input values ​​and feature points of a dark circle region in the facial image as output values. The feature points may be pixel values ​​or even color values ​​corresponding to each pixel.

[0060] The dark circle cause determination unit 1022 can use the learning data to learn the dark circle area detection model. The dark circle area detection model can use the "feature points of the facial image" and the "feature points of the dark circle area in the facial image" for guided learning. Guided learning refers to a learning method that uses data containing input values ​​and their corresponding output values ​​as learning data and finds the corresponding output values ​​based on the given input values. It refers to learning performed in a state where the correct answer is known. The set of input values ​​and output values ​​provided in guided learning is called training data. That is, the "feature points of the facial image" and "feature points of the dark circle area in the facial image" mentioned above are input values ​​and output values, respectively, and can be used as training data for guiding learning of the dark circle area detection model.

[0061] For example, the dark circle cause determination unit 1022 may generate input values ​​by converting the feature points of the facial image into an inherent first one-hot vector, and generate output values ​​by converting the feature points of the dark circle region in the facial image into a second one-hot vector, and then use the generated input values ​​and output values ​​to guide the learning of the dark circle region detection model. The first one-hot vector and the second one-hot vector may be vectors in which one of the component values ​​constituting the vector is composed of "1" and the remaining component values ​​are all composed of "0".

[0062] In one embodiment, the dark circle area detection model may include: an input layer that receives an input value and has nodes corresponding to the number of components of the first unique hot vector; one or more hidden layers that multiply each output value of the input layer by the connection strength (or weight) and then add a bias for output; and an output layer that multiplies each output value of the hidden layer by the connection strength (or weight) and then outputs the result using an activation function. For example, the activation function may be a rectified linear unit (ReLU) function or a normalized exponential (Softmax) function, but is not limited thereto. The connection strength and bias may be continuously updated through guided learning.

[0063] Specifically, the dark circle area detection model can minimize the output value of the loss function according to the given input value (first unique hot vector) and output value (second unique hot vector) by guided learning. For example, the loss function (H(Y, Y')) can be defined according to the following mathematical formula 2.

[0064] [Formula 2]

[0065] .

[0066] In the above-mentioned Mathematical Formula 2, Ym is the m-th component of the second one-hot vector, and Y′m is the m-th component of the output vector outputted from the average facial image estimation model 503 by receiving the input of the first one-hot vector.

[0067] The dark circle cause determination unit 1022 determines the dark circle region based on the output value of the dark circle detection model, i.e., “the feature points of the dark circle region in the facial image”, and can determine the dark circle region by additionally considering the determined dark circle expected region. For example, the dark circle cause determination unit 1022 can determine the dark circle region based on the feature points of the “feature points of the dark circle region in the facial image” that overlap with the dark circle expected region.

[0068] The dark circle cause determination unit 1022 may calculate a first average value of pixel values ​​of pixels included in the determined or even detected dark circle area, and calculate a second average value of pixel values ​​of pixels included in a non-dark circle area adjacent to the dark circle area.

[0069] The dark circle cause judgment unit 1022 can determine that the user's dark circles are caused by pigmentation when the difference between the first average value and the second average value is greater than a pre-set difference value and the melanin index detected in the dark circle area is greater than a pre-set melanin critical index.

[0070] The dark circle cause judgment unit 1022 can determine that the user's dark circles are caused by pigmentation when the difference between the first average value and the second average value is greater than a pre-set difference value and the hemoglobin index detected in the dark circle area is greater than a pre-set hemoglobin critical index.

[0071] In other words, because melanin in the skin components is directly related to pigmentation and hemoglobin is directly related to vascular dilation, the dark circle cause judgment unit 1022 can determine the cause of the user's dark circles as pigmentation when a melanin component exceeding a pre-set first component amount is detected, and determine the cause of the user's dark circles as vascular dilation when a hemoglobin component exceeding a pre-set second component amount is detected.

[0072] The dark circle cause determination unit 1022 can determine the melanin measurement wavelength and the hemoglobin measurement wavelength based on the light absorption characteristics. The dark circle cause determination unit 1022 can respectively obtain the light source images of each measurement wavelength (e.g., the melanin measurement wavelength light source image and the hemoglobin measurement wavelength light source image) using the reflector and the detection light images of each wavelength diffused and reflected in the skin tissue of the dark circle area, and calculate the optical density of the pixels contained in the dark circle area based on the intensity ratio of each pixel of the two images.

[0073] The melanin index image can be derived by multiplying the optical density difference of pixels corresponding to the same position in two wavelength images with different light absorption of melanin by a complementary constant to calculate the optical density gradient between the two wavelengths, which may include using a light source with wavelengths of about 600nm and 700nm, especially using a light source with wavelengths of 650nm and 700nm. The hemoglobin index image can be derived by calculating the width of the area between about 500nm and 600nm in the skin optical density chart, that is, calculating the optical density gradient between about 560nm and 650nm wavelengths and / or calculating the optical density difference between two wavelength images with different light absorption of hemoglobin.

[0074] The dark circle cause determination unit 1022 may generate a melanin index image and a hemoglobin index image through the calculation, and determine or even calculate the melanin index and the hemoglobin index based on the melanin index image and the hemoglobin index image.

[0075] Figure 5 is a schematic diagram related to a process of determining the cause of skin wrinkles of a user by using a multi-wavelength light source.

[0076] The wrinkle cause determination unit 1023 can obtain wrinkle information through multiple wavelengths. In step S510, the wrinkle cause determination unit 1023 can use the fifth wavelength (e.g., ultraviolet (UV) wavelength) in the multiple wavelengths to obtain first wrinkle information (e.g., shallow wrinkle emphasis information), and in step S520, the sixth wavelength (e.g., near infrared wavelength) in the multiple wavelengths can be used to obtain second wrinkle information (e.g., deep wrinkle information). In other words, the wrinkle cause determination unit 1023 can use the characteristic of the difference in light penetration depth caused by changes in absorption and scattering in skin tissue according to the wavelength of light to determine the fine lines of the epidermis that are difficult to distinguish through existing white light or ultraviolet (UV) wavelength light sources and the degree of deep wrinkles generated in the dermis. Due to the difference in light penetration depth, a mixed image of deep wrinkles with shallow wrinkles in the epidermis layer emphasized can be obtained under the fifth wavelength (e.g., ultraviolet (UV) wavelength), a mixed image of shallow wrinkles and deep wrinkles can be obtained under a visible light source, and a deep wrinkle image of the dermis layer can be obtained under the sixth wavelength (e.g., near infrared). The wrinkle degree calculation method based on the acquired multi-wavelength skin image may include using a wrinkle detection model that learns training data with wrinkle region feature points as output values, or a wrinkle region emphasis method based on image processing.

[0077] In step S530, wrinkle cause determination unit 1023 may determine the cause of the user's wrinkles based on the acquired wrinkle information.

[0078] The wrinkle cause determination unit 1023 may obtain a first wrinkle image of the user by using a light source having a fifth wavelength, and obtain a second wrinkle image of the user by using a light source having a sixth wavelength having a wavelength greater than the fifth wavelength.

[0079] For example, the wrinkle cause determination unit 1023 may determine that the user's wrinkles are shallow wrinkles generated in the epidermis layer, based on the shallow wrinkle information obtained through the fifth wavelength (e.g., ultraviolet (UV) wavelength) or the difference image between the fifth wavelength and the sixth wavelength, if the user's shallow wrinkle level is above a predetermined level, and if the user's wrinkles are determined to be shallow wrinkles, determine that the main cause of the user's wrinkles is lack of water.

[0080] For example, the wrinkle cause determination unit 1023 can determine that the user's wrinkles are deep wrinkles generated in the dermis layer based on the deep wrinkle information obtained through the sixth wavelength (e.g., near infrared rays) when the user's deep wrinkle level is above a predetermined level, and when it is determined that the user's wrinkles are deep wrinkles, determine that the main cause of the user's wrinkles is insufficient elasticity.

[0081] The solution providing unit 103 may provide the user terminal 200 with information related to recommended cosmetics or even recommended products corresponding to the measured skin condition. When it is determined that the main cause of the user's wrinkles is insufficient moisture, the solution providing unit 103 may determine cosmetics or even products with good moisturizing effects as cosmetics or even products that need to be recommended to the user, and when it is determined that the main cause of the user's wrinkles is insufficient elasticity, the solution providing unit 103 may determine cosmetics or even products that are beneficial to skin elasticity as cosmetics or even products that need to be recommended to the user. When it is determined that the measured skin condition of the user has a high melanin index, the solution providing unit 103 may determine cosmetics or even products that are beneficial to whitening or improving pigmentation as cosmetics or even products that need to be recommended to the user, and when it is determined that the skin condition of the user has a high hemoglobin index, the solution providing unit 103 may determine cosmetics or even products that are beneficial to whitening or improving pigmentation as cosmetics or even products that need to be recommended to the user, and when it is determined that the skin condition of the user has a high hemoglobin index, the solution providing unit 103 may determine cosmetics or even products that can improve redness or vasodilation as cosmetics or even products that need to be recommended to the user.

[0082] Figure 6 It is based on Figure 1 A schematic diagram illustrating the hardware structure of the device 100.

[0083] See also Figure 6 The multi-wavelength skin analysis device 100 may include at least one processor 110 and a memory storing instructions for instructing the at least one processor 110 to perform at least one operation.

[0084] The at least one action may include at least a portion of the actions or functions of the device 100 as described above, and is further implemented in the form of instructions and executed by the processor 110.

[0085] Among them, at least one processor 110 may refer to a central processing unit (CPU), a graphics processing unit (GPU) or a dedicated processor for executing the method according to an embodiment of the present invention. The memory 120 and the storage device 160 may be respectively composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 120 may be one of a read only memory (ROM) and a random access memory (RAM), and the storage device 160 may be a flash memory, a hard disk drive (HDD), a solid state drive (SSD) or various memory cards (such as a micro secure digital storage (micro SD) card), etc.

[0086] In addition, the multi-wavelength skin analysis device 100 may include a transceiver 130 for performing communication via a wireless network. In addition, the device 100 may also include an input interface device 140, an output interface device 150, and a storage device 160. The various components included in the multi-wavelength skin analysis device 100 can be connected via a bus 170 and perform communication with each other. Figure 6 In the description, the multi-wavelength skin analysis device 100 is taken as an example, but it is not limited to this. For example, the plurality of user terminals may include Figure 6 constituent elements.

[0087] The method according to the present invention can be implemented in the form of program instructions that can be executed by various computing devices and recorded in a computer-readable medium. The computer-readable medium can contain program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded in the computer-readable medium can be specially designed or constructed for the present invention, or can be well known and usable by computer software practitioners.

[0088] Examples of computer-readable media include hardware devices that are specially configured to store and execute program instructions, such as read-only memory (ROM), random access memory (RAM), and flash memory. Examples of program instructions include not only machine language codes generated by a compiler, but also high-level language codes that run on a computer using an interpreter. The hardware devices described above may be configured in a manner that runs at least one software module in order to perform the actions of the present invention, and vice versa.

[0089] Furthermore, the methods or devices described above may be implemented in combination or separately in whole or in part in terms of their configurations or functions.

[0090] In the above content, the preferred embodiments of the present invention are described with reference to each other, but those skilled in the art should understand that the present invention can be modified and changed in many ways without departing from the scope of the ideas and spirit of the present invention as described in the attached claims.

Claims

1. A multi-wavelength skin analysis device, comprising: A skin condition measurement unit, which uses a camera and a multi-wavelength light source unit to measure the user's skin condition; a multi-purpose skin analysis information acquisition unit, which acquires the skin analysis information of the user by using the multi-wavelength image acquired by the multi-wavelength light source unit; as well as, A solution providing unit, providing information related to recommended cosmetics corresponding to the measured skin condition; The multi-purpose skin analysis information acquisition unit comprises: a melanin distribution confirmation unit that determines the melanin status of the user's skin; a dark circle cause determination unit that determines the cause of the dark circle; and a wrinkle cause determination unit that determines the cause of the wrinkle according to the wrinkle generation layer classification.

2. The multi-wavelength skin analysis device according to claim 1, The melanin distribution confirmation unit, Acquire a first wavelength image using a first light source of a first wavelength, and using a second light source having a second wavelength smaller than the first wavelength to acquire a second wavelength image, Extracting a first melanin region image based on the first wavelength image, and extracting a second melanin region image based on the second wavelength image, The first melanin area image and the second melanin area image are then combined with the skin image of the user, so that a melanin distribution image is acquired through the combination.

3. The multi-wavelength skin analysis device according to claim 1, The melanin distribution confirmation unit, Acquire a third wavelength image using a third light source having a third wavelength with the longest wavelength among the multiple wavelength light sources, and using a fourth light source having a fourth wavelength with the shortest wavelength among the multiple wavelength light sources to acquire a fourth wavelength image, Then, a differential image is generated based on the third wavelength image and the fourth wavelength image. Therefore, a melanin distribution image highlighting the melanin area is obtained based on the generated differential image.

4. The multi-wavelength skin analysis device according to claim 1, The dark circles cause determination unit, detecting a dark circle area of ​​the user from the skin image of the user acquired by the camera, When a melanin component exceeding a preset first component amount is detected in the detected dark circle area, the cause of the dark circles of the user is determined to be pigmentation, When a hemoglobin component exceeding a preset second weight is detected in the detected dark circle region, the cause of the user's dark circles is determined to be vascular dilation.

5. The multi-wavelength skin analysis device according to claim 1, Wrinkle Cause Judgment Department, acquiring a first wrinkle image based on a fifth light source of a fifth wavelength in the multiple wavelengths, and acquiring a second wrinkle image based on a sixth light source having a sixth wavelength greater than the fifth wavelength, further determining a wrinkle classification according to the wrinkle generating layer of the user and a main wrinkle cause corresponding to the wrinkle classification based on the first wrinkle image and the second wrinkle image, The first wrinkle image is an epidermal wrinkle image, and the second wrinkle image is a dermal wrinkle image.

Images