WO2024005509A1 - 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 - Google Patents
다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 Download PDFInfo
- Publication number
- WO2024005509A1 WO2024005509A1 PCT/KR2023/008955 KR2023008955W WO2024005509A1 WO 2024005509 A1 WO2024005509 A1 WO 2024005509A1 KR 2023008955 W KR2023008955 W KR 2023008955W WO 2024005509 A1 WO2024005509 A1 WO 2024005509A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- wavelength
- image
- wrinkle
- melanin
- skin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/442—Evaluating skin mechanical properties, e.g. elasticity, hardness, texture, wrinkle assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1032—Determining colour of tissue for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/443—Evaluating skin constituents, e.g. elastin, melanin, water
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/444—Evaluating skin marks, e.g. mole, nevi, tumour, scar
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- the present invention relates to a method and device for obtaining skin analysis information using multiple wavelengths. More specifically, the present invention relates to a method and device for obtaining skin analysis information using multiple wavelengths. More specifically, the present invention relates to a multi-purpose skin analysis method such as skin melanin distribution, classification of dark circle causes, and determination of causes according to classification of wrinkle producing layer using multiple wavelengths. It relates to a method and device for obtaining analysis information.
- the conventional skin condition measurement method for skin analysis is to measure the user's face based on preset shooting parameters (e.g., intensity of light source, direction, aperture value, or shutter speed, etc.) through a skin condition measuring device or device.
- the skin condition of the user has been measured based on the photographed user's face image.
- this method of measuring a user's skin condition based on facial images uses insufficient parameters to diagnose the skin, and can only diagnose the superficial skin condition, making it difficult to find the underlying cause of the problem.
- a system that analyzes 2D images using only white light or UV wavelengths as a light source is used to distinguish between fine wrinkles in the epidermis and deep wrinkles created in the dermis. it's tough.
- the purpose of the present invention to solve the above problems is a method of simultaneously acquiring multi-purpose skin analysis information through multiple wavelengths using the change in absorption and scattering within the skin according to the length of the wavelength and the difference in light penetration depth characteristics. and providing devices.
- a multi-wavelength skin analysis device includes: a skin condition measuring unit that measures the user's skin condition using a camera and a multi-wavelength light source; A multi-purpose skin analysis information acquisition unit that acquires skin analysis information of the user through a multi-wavelength image acquired through the multi-wavelength light source unit; It may include a solution providing unit that provides information on recommended cosmetics corresponding to the measured skin condition.
- the multipurpose skin analysis information acquisition unit includes a melanin distribution confirmation unit that determines the melanin state 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 corresponds to the classification of the wrinkle producing layer. It may include parts, etc.
- the melanin distribution confirmation unit acquires a first wavelength image using a first light source having a first wavelength, and uses a second light source having a second wavelength that is shorter than the first wavelength. Acquire a second wavelength image, extract a first melanin region image based on the first wavelength image, extract a second melanin region image based on the second wavelength image, and extract the first melanin region image and the The second melanin region image can be combined with the skin image of the user, and a melanin distribution image can be obtained through the combination.
- a method of repeating the wavelength image acquisition and melanin region extraction process using two or more different wavelength light sources in the same manner, and obtaining a melanin multi-level distribution image corresponding to the melanin light absorbance characteristics of each wavelength through the combination. may include.
- the melanin distribution confirmation unit acquires a third wavelength image using a third light source having a third wavelength that is the longest wavelength among the multi-wavelength light sources, and the melanin distribution confirmation unit acquires a third wavelength image using a third wavelength image that is the longest wavelength among the multi-wavelength light sources.
- a fourth wavelength image is acquired using a fourth light source with four wavelengths, a difference image is generated based on the third wavelength image and the fourth wavelength image, and a melanin area is emphasized based on the generated difference image.
- Melanin distribution images can be obtained.
- the dark circle cause determination unit detects the user's dark circle area in the user's skin image obtained through the camera, and determines a first component amount in which the melanin component is preset in the detected dark circle area. If it is detected in excess, the cause of the user's dark circles is determined to be due to pigmentation, and if the hemoglobin component in the detected dark circle area is detected in excess of the preset second component amount, the cause of the user's dark circles is determined to be blood vessels. It can be determined that this is due to expansion.
- the wrinkle cause determination unit acquires a first wrinkle image based on a fifth light source having a fifth wavelength among the multiple wavelengths, and has a sixth wavelength that is longer than the fifth wavelength among the multiple wavelengths.
- Obtain a second wrinkle image based on a sixth light source determine wrinkle classification according to the user's wrinkle-generating layer and the corresponding main cause of wrinkle generation based on the first wrinkle image and the second wrinkle image, and 1 Wrinkle image may be an epidermal wrinkle image, and the second wrinkle information may be a dermal wrinkle image.
- multi-purpose skin analysis information can be obtained simultaneously using multiple wavelengths.
- the distribution of melanin in the user's skin can be confirmed using a multi-wavelength light source.
- the cause of dark circles can be revealed using a multi-wavelength light source, and a method for solving dark circles according to the cause of dark circles can be proposed.
- a multi-wavelength light source can be used to distinguish between shallow wrinkles in the epidermis and deep wrinkles created in the dermal layer, and a user-tailored solution method can be presented according to the distinction between wrinkle-generating layers.
- Figure 1 is a diagram illustrating a multi-wavelength skin analysis system according to an embodiment.
- Figure 2 is a diagram showing the main components of a multi-wavelength skin analysis device.
- Figure 3 is a diagram related to checking the melanin distribution of the user's skin through a multi-wavelength light source.
- Figure 4 is a diagram related to determining the cause of a user's dark circles using a multi-wavelength light source.
- Figure 5 is a diagram related to determining the cause of wrinkles according to the wrinkle-producing layer of the user's skin using a multi-wavelength light source.
- Figure 6 is a diagram showing the hardware configuration of the multi-wavelength skin analysis device according to Figure 1.
- first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.
- a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention.
- the term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.
- FIG. 1 is a diagram illustrating a multi-wavelength skin analysis system 10 according to an embodiment.
- the multi-wavelength skin analysis system 10 may include a multi-wavelength skin analysis device 100, a user terminal 200, and the like.
- 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 the user's skin may be formed through the multi-wavelength light source unit and the imaging unit. Status can be measured.
- the multi-wavelength skin analysis device 100 extracts melanin distribution, determines the cause of the user's dark circles, and determines the cause of the user's dark circles based on the multi-wavelength image acquired through the multi-wavelength light source unit and the user's facial image acquired through the photography unit. The cause of wrinkles can be determined.
- the user terminal 200 is a communication capable desktop computer, laptop computer, laptop, smart phone, tablet PC, mobile phone, or smart watch. (smart watch), smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital voice It may be a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, and a PDA (Personal Digital Assistant).
- the multi-wavelength skin analysis device 100 and the user terminal 200 are each connected to a communication network and can transmit and receive data with each other through the communication network.
- communication networks include Local Area Network (LAN), Metropolitan Area Network (MAN), Global System for Mobile Network (GSM), Enhanced Data GSM Environment (EDGE), High Speed Downlink Packet Access (HSDPA), and W-CDMA.
- Wi-Fi Wireless Local Area Network
- VoIP Voice over Internet Protocol
- LTE Advanced Long Term Evolution
- IEEE802.16m WirelessMAN-Advanced
- HSPA+ 3GPP Long Term Evolution
- Mobile WiMAX IEEE 802.16e
- UMB formerly EV-DO Rev. C
- Flash-OFDM iBurst and MBWA
- 802.20 HIPERMAN
- BDMA Beam-Division Multiple Access
- Wi-MAX Worldwide Interoperability for Microwave Access
- 5G 5G.
- FIG. 2 is a diagram showing the main components of the multi-wavelength skin analysis device 100.
- the multi-wavelength skin analysis device 100 includes a skin condition measurement unit 101, a multi-purpose skin analysis information acquisition unit 102, a melanin distribution confirmation unit (or determination unit) 1021, and a dark circle cause determination unit. It may include a determination unit (or decision unit) 1022, a wrinkle cause determination unit (or decision unit) 1023, and a solution provision unit 103.
- the multi-purpose skin analysis information acquisition unit 102 includes a melanin distribution confirmation unit (or determination unit) 1021, a dark circle cause determination unit (or determination unit) 1022, and a wrinkle cause determination unit (or determination unit) ( It is not limited to including 1023), and it is obvious to a person skilled in the art that other analysis units capable of analysis at multiple wavelengths may be additionally included.
- the skin condition measuring unit 101 may include an ultraviolet light source unit that irradiates ultraviolet rays, a visible light source unit that irradiates visible light, and an infrared light source unit that irradiates near infrared rays.
- the skin condition measuring unit 101 may acquire an image capturing unit including a camera, a polarizer, a diffusion plate, a distance sensor, etc. in addition to a multi-wavelength light source unit.
- the skin condition measurement unit 101 may irradiate multi-wavelength light sources, including ultraviolet (UV), visible (VIS), and near-infrared (NIR) light sources, to the user's skin.
- the skin condition measuring unit 101 can photograph the user's skin in a state irradiated with a multi-wavelength light source through the imaging unit.
- the skin condition measuring unit 101 may acquire an image of the user's skin through the above photographing.
- the skin condition measurement unit 101 sequentially irradiates a plurality of light sources such as ultraviolet rays, visible rays, and infrared rays, and can acquire wavelength band images corresponding to each of the plurality of light sources through a camera.
- a plurality of light sources such as ultraviolet rays, visible rays, and infrared rays
- Figure 3 is a diagram related to checking the melanin distribution of the user's skin through a multi-wavelength light source.
- the melanin distribution confirmation unit 1021 can check the melanin distribution through a multi-wavelength light source.
- the melanin distribution confirmation unit 1021 may acquire a melanin distribution image based on melanin absorbance characteristics according to wavelength through a multi-wavelength light source and calculate a melanin index.
- the melanin distribution confirmation unit 1021 can acquire images of each wavelength using a light source with each wavelength (S310), and at relatively short wavelengths (e.g., visible light below 450 nm and ultraviolet A), melanin is detected due to high melanin absorbance. Areas with low density also show high contrast with the surrounding skin tissue in the image, and due to low melanin absorbance at relatively long wavelengths (e.g., visible light and near-infrared rays over 750 nm), only areas with high melanin density are indistinguishable from the surrounding skin tissue in the image. It shows high contrast.
- relatively short wavelengths e.g., visible light below 450 nm and ultraviolet A
- the melanin distribution confirmation unit 1021 may perform binarization (e.g., Otsu's Thresholding) on each of the wavelength images (S320).
- the melanin distribution confirmation unit 1021 may extract melanin regions from each of the binarized wavelength images.
- the melanin distribution confirmation unit 1021 may combine images of the extracted melanin regions with the user's skin image (S330).
- the melanin distribution confirmation unit 1021 can acquire a melanin distribution image through the above combination (S340).
- the melanin distribution confirmation unit 1021 acquires a first wavelength image using a first light source with a first wavelength, and uses a second light source with a second wavelength that is shorter than the first wavelength to obtain a first wavelength image. Two-wavelength images can be acquired.
- the melanin distribution confirmation unit 1021 may extract a first melanin region based on the first wavelength image and extract a second melanin region based on the second wavelength image.
- the melanin distribution confirmation unit 1021 may obtain a melanin distribution image by combining the first melanin region image and the second melanin region image with the skin image of the user.
- the melanin distribution confirmation unit 1021 repeats the process of acquiring the wavelength image and extracting the melanin area using two or more different wavelength light sources, and through the combination, melanin multi-level distribution corresponding to the melanin light absorbance characteristics of each wavelength It may also include a method of acquiring an image.
- the melanin distribution confirmation unit 1021 may determine a light source having each of two wavelengths with a large difference in light absorption for melanin (S311).
- the melanin distribution confirmation unit 1021 may acquire two wavelength images (eg, a first wavelength image and a second wavelength image) in which the difference in light absorption of melanin is large (S321).
- the melanin distribution confirmation unit 1021 may generate a difference image based on the first wavelength image and the second wavelength image (S331).
- the melanin distribution confirmation unit 1021 acquires a third wavelength image using a third light source with a third wavelength, which is the longest wavelength among the multi-wavelength light sources, and uses a third wavelength image with the shortest wavelength among the multi-wavelength light sources.
- a fourth wavelength image can be obtained using a fourth light source with a wavelength.
- the melanin distribution confirmation unit 1021 may generate a difference image based on the third wavelength image and the fourth wavelength image.
- the melanin distribution confirmation unit 1021 may generate a melanin distribution image (eg, melanin-highlighted image) based on the difference image (S340).
- the melanin distribution confirmation unit 1021 may calculate the ratio of the pixel value included in the melanin area and the light source intensity before light absorption, and calculate the degree of melanin (melanin index) based on the calculated ratio.
- the optical density (OD) is as follows, and the two wavelength images with different light absorbance are A melanin index image can be obtained by calculating the optical density gradient between two wavelengths by multiplying the difference in optical density of pixels corresponding to the same location by a correction constant, and calculating the average index value of the entire image or melanin area to determine the degree of melanin. It can be calculated.
- Equation 1 OD may refer to the optical density, and R may refer to the ratio of irradiated light and detected light diffused and reflected inside the skin.
- Figure 4 is a diagram related to determining the cause of a user's dark circles using a multi-wavelength light source.
- the dark circle cause determination unit 1022 can measure melanin and hemoglobin components through multiple wavelengths and determine the cause of dark circles based on the measured melanin and hemoglobin components.
- the dark circle cause determination unit 1022 may detect the eye area in the user's face image.
- the dark circle cause determination unit 1022 may detect a dark circle area close to the eye area in the user's face image.
- the dark circle cause determination unit 1022 may select a more limited dark circle area and determine an expected dark circle area in order to detect dark circles within the limited area.
- the dark circle cause determination unit 1022 detects the left eye and the right eye in the acquired face image, determines the outermost line for each of the detected left eye and right eye, and moves the determined outermost line to an angle greater than a preset angle. The bent point can be determined.
- the dark circle cause determination unit 1022 determines the first and second points that are bent by more than a preset angle on the first outermost line corresponding to the left eye, and the second outermost point corresponding to the right eye.
- the third and fourth points that are bent more than a preset angle from the outer line can be determined.
- the dark circle cause determination unit 1022 may calculate a first distance between the first point and the second point, and calculate a second distance between the third point and the fourth point.
- the dark circle cause determination unit 1022 is configured to determine the first area from the first lowest point of the first outermost line corresponding to the left eye to a point that is a first distance away from the bottom and the second outermost line corresponding to the right eye.
- the second area from the second lowest point to the point that is a second distance away from the bottom may be determined as the expected dark circle area.
- the dark circle cause determination unit 1022 can train a dark circle area detection model, which is an artificial neural network model, and input the user's face image into the learned dark circle area detection model.
- the dark circle cause determination unit 1022 can detect or determine the dark circle area by inputting the user's face image into the model (S410).
- the dark circle cause determination unit 1022 can use facial images of people with dark circles as learning data. Face images of people with dark circles may be obtained from a database included in the device 100 or terminal 200 or may be obtained from an external DB.
- the learning data of one embodiment may be training data that has feature points of a face image as input values and feature points of a dark circle area within the face image as output values.
- the feature point may be a pixel value or a color value corresponding to each pixel.
- the dark circle cause determination unit 1022 may learn the dark circle area detection model using training data.
- the dark circle area detection model can be supervised learning using ‘feature points of the face image’ and ‘feature points of the dark circle area within the face image’.
- Supervised learning refers to learning to find an output value according to a given input value by using data with input values and corresponding output values as learning data, and refers to learning that takes place when the correct answer is known.
- the set of input and output values given to supervised learning is called training data. That is, the above-mentioned 'feature points of the face image' and 'feature points of the dark circle area in the face image' are input and output values, respectively, and can be used as training data for supervised learning of the dark circle area detection model.
- the dark circle cause determination unit 1022 generates an input value by converting the feature point of the face image into a unique first one-hot vector, and selects the feature point of the dark circle area in the face image. After converting to a unique second one-hot vector and generating an output value, a dark circle area detection model can be supervised using the generated input and output values.
- 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 '1' and the remaining component values are '0'.
- the dark circle area detection model receives an input value, multiplies the connection strength (or weight) for each of the input layer and the output value of the input layer with nodes corresponding to the number of components of the first one-hot vector, and , one or more hidden layers that add a bias and output; And it may include an output layer that multiplies each output value of the hidden layer by a connection strength (or weight) and outputs the result using an activation function.
- the activation function may be a ReLU function or a Softmax function, but is not limited thereto. Connection strengths and biases can be continuously updated by supervised learning.
- the dark circle area detection model may be supervised so that the output value of the loss function according to the given input value (first one-hot vector) and output value (second one-hot vector) is minimized.
- the loss function (H(Y, Y')) can be defined as Equation 2 below.
- Equation 2 Ym is the mth component of the second one-hot vector, and Y ⁇ m is the mth component of the output vector output by receiving the first one-hot vector from the average face image guessing model 503. It can be.
- the dark circle cause determination unit 1022 determines the dark circle area based on the 'feature points of the dark circle area in the face image', which is the output value of the dark circle area detection model, and additionally considers the determined dark circle expected area to determine the dark circle area.
- the area can be determined.
- the dark circle cause determination unit 1022 may determine the dark circle area based on feature points that overlap with the expected dark circle area among the 'feature points of the dark circle area in the face image'.
- the dark circle cause determination unit 1022 calculates a first average value for pixel values of pixels included in the determined or detected dark circle area, and pixels of pixels included in a non-dark circle area adjacent to the dark circle area. A second average value for the values may be calculated.
- the dark circle cause determination unit 1022 determines the user's dark It can be determined that the cause of the circles is due to pigmentation.
- the dark circle cause determination unit 1022 It can be determined that the cause of the circles is due to pigmentation.
- the dark circle cause determination unit 1022 determines the level of the user's dark circles when the melanin component is detected in excess of the preset first ingredient amount.
- the cause of the user's dark circles may be determined to be due to pigmentation, and if the hemoglobin component is detected to exceed the preset amount of the second component, the cause of the user's dark circles may be determined to be due to vasodilation.
- the dark circle cause determination unit 1022 may determine a melanin measurement wavelength and a hemoglobin measurement wavelength based on light absorption characteristics.
- the dark circle cause determination unit 1022 uses a reflector to determine each measurement wavelength light source image (e.g., melanin measurement wavelength light source image and hemoglobin measurement wavelength light source image) and the detection light generated by diffusion and reflection of each wavelength within the skin tissue in the dark circle area. Images can be acquired separately, and the optical density of pixels included in the dark circle area can be calculated based on the intensity ratio of each pixel of the two images.
- the melanin index image can be derived by calculating the optical density gradient between the two wavelengths by multiplying the difference in optical density of pixels corresponding to the same position in two wavelength images with different optical absorption for melanin by a correction constant, and is approximately Methods may include using 600 nm and 700 nm wavelength light sources, particularly 650 nm and 700 nm wavelength light sources.
- the hemoglobin index image is a method of calculating the area of the area between about 500 nm and 600 nm in the skin optical density graph, obtaining the optical density gradient between wavelengths of about 560 nm and 650 nm, and/or measuring the optical density between the wavelengths of about 560 nm and 650 nm. It can be derived by calculating the difference in optical density between the two wavelength images.
- the dark circle cause determination unit 1022 may generate a melanin index image and a hemoglobin index image through the above calculation, and determine or calculate the melanin index and the hemoglobin index based on the melanin index image and the hemoglobin index image. You can.
- Figure 5 is a diagram related to determining the cause of a user's skin wrinkles using a multi-wavelength light source.
- the wrinkle cause determination unit 1023 can obtain wrinkle information through multiple wavelengths.
- the wrinkle cause determination unit 1023 acquires first wrinkle information (e.g., shallow wrinkle emphasis information) using the fifth wavelength (e.g., UV wavelength) among the multiple wavelengths (S510), and uses the sixth wavelength (e.g., UV wavelength) among the multiple wavelengths.
- Fifth wavelength e.g., UV wavelength
- UV wavelength e.g., UV wavelength
- second wrinkle information e.g., deep wrinkle information
- the wrinkle cause determination unit 1023 uses the characteristic of the difference in light penetration depth due to changes in absorption and scattering within the skin tissue according to the light wavelength to determine fine wrinkles in the epidermis and dermis, which are difficult to distinguish using the existing white light or UV wavelength light source method.
- the degree of deep wrinkles created can be determined. Due to the difference in light penetration depth, the 5th wavelength (e.g. UV wavelength) is a deep wrinkle mixed image with shallow wrinkles in the epidermal layer emphasized, the visible light source is a mixed image of shallow wrinkles and deep wrinkles, and the 6th wavelength (e.g. near infrared) is a deep wrinkle mixed image in which the shallow wrinkles in the epidermal layer are emphasized. Deep wrinkle images can be obtained.
- a method of calculating the degree of wrinkles based on the acquired multi-wavelength skin image may include using a wrinkle detection model through learning training data with wrinkle area feature points as output values or a method of highlighting the wrinkle area based on image processing.
- the wrinkle cause determination unit 1023 may determine the cause of the user's wrinkles based on the obtained wrinkle information (S530).
- the wrinkle cause determination unit 1023 acquires the user's first wrinkle image through a light source with a fifth wavelength, and acquires the user's second wrinkle image through a light source with a sixth wavelength, which is a longer wavelength than the fifth wavelength. can do.
- the wrinkle cause determination unit 1023 determines the degree of shallow wrinkles of the user in advance based on shallow wrinkle information obtained based on the fifth wavelength (e.g., UV wavelength) or the difference image between the fifth and sixth wavelength images. If it is more than a set level, it is determined that the user's wrinkles are shallow wrinkles occurring in the epidermal layer, and in response to the user's wrinkles being determined to be shallow wrinkles, the main cause of the user's wrinkles may be determined to be lack of moisture.
- the fifth wavelength e.g., UV wavelength
- the wrinkle cause determination unit 1023 determines that the user's deep wrinkles are greater than a preset level based on the deep wrinkle information acquired through the sixth wavelength (e.g., near-infrared rays), the wrinkles of the user are deep wrinkles occurring in the dermal layer. It is determined that the wrinkles are wrinkles, and in response to the determination that the user's wrinkles are deep wrinkles, the main cause of wrinkles in the user may be determined to be lack of elasticity.
- a preset level based on the deep wrinkle information acquired through the sixth wavelength (e.g., near-infrared rays)
- the wrinkles of the user are deep wrinkles occurring in the dermal layer. It is determined that the wrinkles are wrinkles, and in response to the determination that the user's wrinkles are deep wrinkles, the main cause of wrinkles in the user may be determined to be lack of elasticity.
- the solution provider 103 may provide the user terminal 200 with information about recommended cosmetics or recommended products corresponding to the measured skin condition. If the user's main cause of wrinkles is determined to be lack of moisture, the solution provider 103 determines cosmetics or products with a good moisturizing effect as cosmetics or products to recommend to the user, and if the user's main cause of wrinkles is determined to be lack of elasticity, the solution provider 103 determines that the user's main cause of wrinkles is lack of moisture. In this case, cosmetics or products that are good for skin elasticity may be determined as cosmetics or products to recommend to the user.
- the solution provider 103 determines cosmetics or products that are good for whitening or pigmentation as cosmetics or products to recommend to the user, and determines that the user's skin condition has a high hemoglobin index. If determined, cosmetics or products that improve flushing or vasodilation may be determined as cosmetics or products to be recommended to the user.
- FIG. 6 is a diagram showing the hardware configuration of the device 100 according to FIG. 1.
- the multi-wavelength skin analysis device 100 includes at least one processor 110 and instructions instructing the at least one processor 110 to perform at least one operation. May include storage memory.
- the at least one operation includes at least some of the operations or functions of the above-described device 100 and may be implemented in the form of instructions and performed by the processor 110.
- the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. You can.
- Each of the memory 120 and the storage device 160 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium.
- the memory 120 may be one of read only memory (ROM) and random access memory (RAM), and the storage device 160 may be flash memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).
- the multi-wavelength skin analysis device 100 may include a transceiver 130 that communicates through a wireless network. Additionally, the device 100 may further include an input interface device 140, an output interface device 150, a storage device 160, etc. Each component included in the multi-wavelength skin analysis device 100 is connected by a bus 170 and can communicate with each other.
- the multi-wavelength skin analysis device 100 is described as an example, but it is not limited thereto.
- a plurality of user terminals may include components according to FIG. 6 .
- Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination.
- Program instructions recorded on a computer-readable medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the computer software art.
- Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc.
- Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.
- the above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.
- the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Dermatology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Nursing (AREA)
Abstract
Description
Claims (5)
- 다파장 피부 분석 장치에 있어서,카메라 및 다파장 광원부를 이용하여 사용자의 피부 상태를 측정하는 피부 상태 측정부;상기 다파장 광원부를 통해 획득된 다파장 영상을 통해 상기 사용자의 피부 분석 정보를 획득하는 다목적 피부 분석 정보 획득부;측정된 상기 피부 상태에 대응하는 추천 화장품에 대한 정보를 제공하는 솔루션 제공부를 포함하고,상기 다목적 피부 분석 정보 획득부는,상기 사용자의 피부의 멜라닌 상태를 결정하는 멜라닌 분포 확인부, 다크서클 원인을 결정하는 다크서클 원인 판단부 및 주름 생성층 구분에 따라 주름 원인을 판단하는 주름 원인 판단부를 포함하는, 다파장 피부 분석 장치.
- 청구항 1에서,상기 멜라닌 분포 확인부는,제1 파장을 가진 제1 광원을 이용하여 제1 파장 영상을 획득하고,상기 제1 파장보다 짧은 파장인 제2 파장을 가진 제2 광원을 이용하여 제2 파장 영상을 획득하고,상기 제1 파장 영상에 기반하여 제1 멜라닌 영역 이미지를 추출하고,상기 제2 파장 영상에 기반하여 제2 멜라닌 영역 이미지를 추출하고,상기 제1 멜라닌 영역 이미지 및 상기 제2 멜라닌 영역 이미지를 상기 사용자의 피부 이미지에 결합하고, 상기 결합을 통해 멜라닌 분포 영상을 획득하는, 다파장 피부 분석 장치.
- 청구항 1에서,상기 멜라닌 분포 확인부는,상기 다파장 광원 중 제일 긴 파장인 제3 파장을 가진 제3 광원을 이용하여 제3 파장 영상을 획득하고,상기 다파장 광원 중 제일 짧은 파장인 제4 파장을 가진 제4 광원을 이용하여 제4 파장 영상을 획득하고,상기 제3 파장 영상 및 상기 제4 파장 영상에 기반하여 차분 영상을 생성하고,생성된 상기 차분 영상에 기반하여 멜라닌 영역이 강조된 분포 영상을 획득하는, 다파장 피부 분석 장치.
- 청구항 1에서,상기 다크서클 원인 판단부는,상기 카메라를 통해 획득된 상기 사용자의 피부 이미지에서 상기 사용자의 다크서클 영역을 검출하고,검출된 상기 다크서클 영역에서 멜라닌 성분이 미리 설정된 제1 성분량보다 초과 검출된 경우에는 사용자의 다크서클의 원인을 색소 침착으로 인한 것으로 결정하고,검출된 상기 다크서클 영역에서 헤모글로빈 성분이 미리 설정된 제2 성분량보다 초과 검출된 경우에는 사용자의 다크서클의 원인을 혈관 확장으로 인한 것으로 결정하는, 다파장 피부 분석 장치.
- 청구항 1에서,주름 원인 판단부는,상기 다파장 중 제5 파장을 가진 제5 광원에 기반한 제1 주름 영상을 획득하고,상기 다파장 중 상기 제5 파장보다 긴 파장인 제6 파장을 가진 제6 광원에 기반한 제2 주름 영상를 획득하고,상기 제1 주름 영상 및 상기 제2 주름 영상에 기반하여 상기 사용자의 주름 생성층에 따른 주름 구분 및 상기 주름 구분에 대응하는 주요 주름 생성 원인을 결정하고,상기 제1 주름 영상은 표피 주름 영상이고, 상기 제2 주름 정보는 진피 주름 영상인, 다파장 피부 분석 장치.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202380050641.5A CN119365120A (zh) | 2022-06-28 | 2023-06-27 | 利用多重波长获取皮肤分信息的方法及装置 |
| US18/878,952 US20250380899A1 (en) | 2022-06-28 | 2023-06-27 | Method and device for acquiring skin analysis information using multiple wavelengths |
| EP23831868.7A EP4548833A4 (en) | 2022-06-28 | 2023-06-27 | METHOD AND DEVICE FOR ACQUIRING SKIN ANALYSIS INFORMATION USING MULTIPLE WAVELENGTHS |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020220079124A KR102450422B1 (ko) | 2022-06-28 | 2022-06-28 | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 |
| KR10-2022-0079124 | 2022-06-28 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024005509A1 true WO2024005509A1 (ko) | 2024-01-04 |
Family
ID=83597323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2023/008955 Ceased WO2024005509A1 (ko) | 2022-06-28 | 2023-06-27 | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20250380899A1 (ko) |
| EP (1) | EP4548833A4 (ko) |
| KR (1) | KR102450422B1 (ko) |
| CN (1) | CN119365120A (ko) |
| WO (1) | WO2024005509A1 (ko) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102450422B1 (ko) * | 2022-06-28 | 2022-10-06 | 주식회사 룰루랩 | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140112046A (ko) * | 2011-12-26 | 2014-09-22 | 샤넬 파르퓜 보트 | 피부 부위 상의 피부 징후를 검출하고 정량화하는 방법과 장치 |
| KR20150080280A (ko) * | 2013-12-31 | 2015-07-09 | (주)아모레퍼시픽 | 피부 진단 및 피부 미용 정보 제공 방법 및 시스템 |
| KR20200142938A (ko) * | 2019-06-14 | 2020-12-23 | 주식회사 룰루랩 | 사용자 맞춤형 피부 진단 시스템 및 방법 |
| KR20210069495A (ko) * | 2019-12-03 | 2021-06-11 | 삼성전자주식회사 | 전자 장치 및 그의 제어 방법 |
| KR20220009735A (ko) * | 2020-07-16 | 2022-01-25 | (주) 코코리색채연구소 | 멜라닌 지수 및 헤모글로빈 지수를 기초로 한 화장품 추천 방법 및 그 디바이스 |
| KR102450422B1 (ko) * | 2022-06-28 | 2022-10-06 | 주식회사 룰루랩 | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010093503A2 (en) * | 2007-01-05 | 2010-08-19 | Myskin, Inc. | Skin analysis methods |
| JP6051558B2 (ja) * | 2012-03-28 | 2016-12-27 | ソニー株式会社 | 撮像装置と撮像方法、プログラム、撮像システム、および付属装置 |
| RU2657377C2 (ru) * | 2016-11-11 | 2018-06-13 | Самсунг Электроникс Ко., Лтд. | Интеллектуальная насадка на смартфон для определения чистоты, влажности и фотовозраста кожи |
-
2022
- 2022-06-28 KR KR1020220079124A patent/KR102450422B1/ko active Active
-
2023
- 2023-06-27 CN CN202380050641.5A patent/CN119365120A/zh active Pending
- 2023-06-27 EP EP23831868.7A patent/EP4548833A4/en active Pending
- 2023-06-27 WO PCT/KR2023/008955 patent/WO2024005509A1/ko not_active Ceased
- 2023-06-27 US US18/878,952 patent/US20250380899A1/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140112046A (ko) * | 2011-12-26 | 2014-09-22 | 샤넬 파르퓜 보트 | 피부 부위 상의 피부 징후를 검출하고 정량화하는 방법과 장치 |
| KR20150080280A (ko) * | 2013-12-31 | 2015-07-09 | (주)아모레퍼시픽 | 피부 진단 및 피부 미용 정보 제공 방법 및 시스템 |
| KR20200142938A (ko) * | 2019-06-14 | 2020-12-23 | 주식회사 룰루랩 | 사용자 맞춤형 피부 진단 시스템 및 방법 |
| KR20210069495A (ko) * | 2019-12-03 | 2021-06-11 | 삼성전자주식회사 | 전자 장치 및 그의 제어 방법 |
| KR20220009735A (ko) * | 2020-07-16 | 2022-01-25 | (주) 코코리색채연구소 | 멜라닌 지수 및 헤모글로빈 지수를 기초로 한 화장품 추천 방법 및 그 디바이스 |
| KR102450422B1 (ko) * | 2022-06-28 | 2022-10-06 | 주식회사 룰루랩 | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4548833A4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119365120A (zh) | 2025-01-24 |
| EP4548833A1 (en) | 2025-05-07 |
| KR102450422B1 (ko) | 2022-10-06 |
| EP4548833A4 (en) | 2026-04-15 |
| US20250380899A1 (en) | 2025-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Appiahene et al. | Detection of iron deficiency anemia by medical images: a comparative study of machine learning algorithms | |
| Ghosal et al. | sHEMO: Smartphone spectroscopy for blood hemoglobin level monitoring in smart anemia-care | |
| US8705815B2 (en) | Systems and methods for automatic skin-based identification of people using digital images | |
| US8260010B2 (en) | Systems and methods for analyzing skin conditions of people using digital images | |
| WO2016099099A1 (en) | Image capturing device and sensing protection device | |
| Hasan et al. | Smartphone-based human hemoglobin level measurement analyzing pixel intensity of a fingertip video on different color spaces | |
| CN107005642B (zh) | 图像捕获设备与感测保护设备 | |
| US20230096501A1 (en) | Computer-readable recording medium storing calculation program, calculation method, and information processing device | |
| CN109805944A (zh) | 一种儿童共情能力分析系统 | |
| Flament et al. | Developing an Artificial Intelligence (AI)‐based descriptor of facial appearance that fits with the assessments of makeup experts | |
| JPWO2020095739A1 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
| WO2024005509A1 (ko) | 다파장을 이용하여 피부 분석 정보를 획득하는 방법 및 장치 | |
| Park et al. | Development and application of artificial intelligence‐based facial skin image diagnosis system: Changes in facial skin characteristics with ageing in Korean women | |
| KR102648659B1 (ko) | 광학 접근법을 통해 재구성한 광반사 특성 재현 영상을 이용하여 피부 분석 모델을 최적화하기 위한 방법 및 장치 | |
| Eguizabal et al. | Direct identification of breast cancer pathologies using blind separation of label-free localized reflectance measurements | |
| Guarin et al. | Automatic facial landmark localization in clinical populations-improving model performance with a small dataset | |
| Flament et al. | Objective and automatic grading system of facial signs from smartphones’ pictures in South African men: validation versus dermatologists and characterization of changes with age | |
| Viveha et al. | Point of care noninvasive screening tool for early detection of anemia using smartphone | |
| CN113807320B (zh) | 一种基于多光谱成像技术的人体肤色识别方法及系统 | |
| Islam et al. | PolypNet: An attention based shallow deep learning model for colorectal polyp image classification | |
| CN113762010B (zh) | 图像处理方法、装置、设备和存储介质 | |
| Lehner et al. | Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination | |
| Yoshida et al. | Noise reduction from chromophore images and reliability improvement by successive minimization of intermixture in the modified Lambert-Beer law | |
| US20250087016A1 (en) | Adaptable Camera-based Contactless SpO2 Detection | |
| KR102465728B1 (ko) | 다크서클을 검출하여 다크서클의 정도를 정량화하는 방법 및 장치 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23831868 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18878952 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202380050641.5 Country of ref document: CN |
|
| WWP | Wipo information: published in national office |
Ref document number: 202380050641.5 Country of ref document: CN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2023831868 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2023831868 Country of ref document: EP Effective date: 20250128 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2023831868 Country of ref document: EP |
|
| WWP | Wipo information: published in national office |
Ref document number: 18878952 Country of ref document: US |

