WO2021215749A1 - Procédé et dispositif de fourniture d'informations capillaires, et procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci - Google Patents

Procédé et dispositif de fourniture d'informations capillaires, et procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci Download PDF

Info

Publication number
WO2021215749A1
WO2021215749A1 PCT/KR2021/004802 KR2021004802W WO2021215749A1 WO 2021215749 A1 WO2021215749 A1 WO 2021215749A1 KR 2021004802 W KR2021004802 W KR 2021004802W WO 2021215749 A1 WO2021215749 A1 WO 2021215749A1
Authority
WO
WIPO (PCT)
Prior art keywords
hair
root
type
hair root
image
Prior art date
Application number
PCT/KR2021/004802
Other languages
English (en)
Korean (ko)
Inventor
김융언
박인혁
김형규
Original Assignee
(주)에임즈
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from KR1020200048104A external-priority patent/KR102329641B1/ko
Priority claimed from KR1020200136590A external-priority patent/KR20220052532A/ko
Application filed by (주)에임즈 filed Critical (주)에임즈
Publication of WO2021215749A1 publication Critical patent/WO2021215749A1/fr

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
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • the present invention relates to a method and apparatus for providing hair information, and more specifically, a method capable of collecting and analyzing information about the number and density of hair as well as information on hair roots by analyzing a camera image and providing it to a user in real time and devices.
  • hair loss is divided into male pattern hair loss and female pattern hair loss, which progress slowly due to genetic causes, and alopecia areata due to abnormalities in the autoimmune system, telogen hair loss due to stress, side effects of drugs, and the like.
  • the part of the hair that grows in the hair follicle inside the scalp is called a hair root.
  • the ratio of multiple hair roots growing from one follicle to two or three hair follicles reaches about 95%, whereas in Asians, it is known that the ratio of multiple hair roots is less than 50%.
  • the hair is not only abundant compared to the number of hair follicles, but also the rest of the hair continues to grow even if one hair is lost.
  • the present invention was devised against this background, and it is an object of the present invention to enable a user to quickly and accurately check his/her hair condition without visiting a hospital by analyzing a hair image with artificial intelligence.
  • the purpose is to provide users with more diverse information about the hair condition by checking the type and number of hair roots through hair root analysis and analyzing the rate of hair loss, etc.
  • the purpose is to provide a fun factor to reduce the user's stress even a little during the hair loss treatment process.
  • a first aspect of the present invention comprises the steps of: acquiring a hair image; classifying the type of hair root into a single hair root or n-fold (n is an integer greater than or equal to 2) hair root by analyzing the hair image; It provides a method of providing hair information, including calculating the number of each type of hair root.
  • a hair image in the step of classifying the type of hair root, a hair image may be input to an input terminal of a pre-trained AI-based hair root analysis model.
  • the end points of each hair are extracted from the hair image, and then the distance between the end points is calculated, and the distance between the end points is adjacent within a set value.
  • n is an integer greater than or equal to 2
  • the corresponding hair bundle can be classified as an n-fold hair root.
  • the method for providing hair information according to the first aspect of the present invention may further include calculating at least one of the number of hairs and the density of hairs by using the number of each type of hair root.
  • a second aspect of the present invention provides a computer-readable recording medium in which a program for implementing the method for providing hair information is recorded.
  • a third aspect of the present invention is a hair root analyzer that analyzes a hair image to classify the type of hair root into a single hair root or n-of-n (n is an integer of 2 or more) hair root and calculates the number of each type; a hair density analyzer for calculating at least one of the number of hairs and the density of hairs by using the number of each type of hair root;
  • a hair information providing device including a communication unit that communicates with an external device through a communication network.
  • the hair root analysis unit includes a pre-trained artificial intelligence-based hair root analysis model, and inputs a hair image to the input terminal of the hair root analysis model to classify the type of hair root.
  • the hair root analysis unit extracts the end points of each hair from the hair image, and then calculates the distance between each end point, and the number of adjacent hairs with a distance between the end points within a set value If there are n (n is an integer greater than or equal to 2), the corresponding hair bundle can be classified as an n-fold hair root.
  • the hair information providing apparatus may include a visualization processing unit that visually displays the type of hair root on the hair image by using the analysis result of the hair root analysis unit.
  • the hair information providing apparatus may include a hair loss progress analysis unit for calculating the fluctuation range for each type of hair root.
  • the hair information providing device is a game in which at least one item from among the number of hairs, the density of the hair, the increase/decrease of the number or density of hairs, the number of multiple hair roots, and the increase/decrease width of multiple hair roots, is competed with another person. It may include a game execution unit that provides an interface.
  • a fourth aspect of the present invention is a hair root analyzer that analyzes a hair image to classify the type of hair root into a single hair root or n-of-n (n is an integer greater than or equal to 2) hair root and calculates the number of each type, and the number of each type of hair root using a hair information providing device having a hair density analyzer that calculates at least one of the number of hairs and the hair density;
  • a hair information providing system comprising a server having a database for storing hair condition analysis results received from a plurality of the hair information providing devices for each user, and a game support unit supporting a game in which users compete for the number of multiple hair roots. do.
  • the server includes a statistical analysis unit for statistically processing the hair analysis results received from a plurality of the hair information providing devices, and a hair loss progress analysis unit for calculating the fluctuation range of each type of hair root for each user. It may include at least one of
  • a fifth aspect of the present invention provides a method of generating a hair root analysis model, which includes performing learning by inputting a number of labeled hair images to an input stage of an artificial intelligence model architecture.
  • the user by analyzing the hair image in real time using artificial intelligence, the user can quickly and accurately check the condition of his/her hair without visiting a hospital.
  • the user can more accurately check the condition of their hair.
  • FIG. 1 is a schematic configuration diagram of a hair information providing system according to an embodiment of the present invention.
  • FIG. 2 is a block diagram of an apparatus for providing hair information according to an embodiment of the present invention.
  • 3 is a functional block diagram of the hair condition analysis unit
  • FIG. 4 is a block diagram of artificial intelligence for analyzing hair roots
  • 5 is a diagram illustrating the architecture of a deep learning analysis model
  • FIG. 6 is a flowchart showing a method for generating a hair root analysis model
  • FIG. 7 is a diagram illustrating hair root type labeling
  • FIG. 8 is a diagram illustrating an image pre-processing process
  • FIG. 9 is a diagram illustrating a visualization image of the number of hair roots
  • FIG. 10 is a view showing another embodiment of a method for classifying hair roots
  • 11 is a diagram illustrating a screen for visualizing hair density
  • FIG. 12 is a block diagram of a server according to an embodiment of the present invention.
  • FIG. 13 is a functional block diagram of the hair condition analysis unit of the server
  • FIG. 14 is a flowchart illustrating a hair analysis method according to an embodiment of the present invention.
  • 15 is a flowchart illustrating a game method using hair information
  • a part includes or includes any component, it means that other components may be further included or provided without excluding other components unless otherwise stated.
  • one element when one element is connected, combined, or communicated with another element, it is not only directly connected, combined, or communicated with another element, but also indirectly connected with another element in between. , combining, or communicating.
  • one component when one component is directly connected or directly coupled to another component, it means that another element is not interposed therebetween.
  • the accompanying drawings in the present specification are merely illustrative for easy understanding of the gist of the present invention, it is clarified in advance that the scope of the present invention is not limited thereto.
  • the hair information providing system provides a hair information providing device 200 through a camera 100 , a hair information providing device 200 , and a communication network 300 . ) and may include a server 400 that communicates with it.
  • the camera 100 is for photographing hair and is preferably a high-magnification camera capable of confirming the number of hair roots and hairs.
  • the camera 100 may be a hair-only camera, or a camera mounted on a smartphone or the like.
  • the camera 100 may include wired and/or wireless communication means for transmitting the captured image to the hair information providing device 200 .
  • the hair information providing device 200 is a device that analyzes the number of hair roots, the number of hairs, the density of hair, etc. based on the hair image received from the camera 100 and provides it to the user.
  • the hair information providing device 200 may be a portable device such as a smart phone, a tablet, a handheld PC, a PDA, or a PMP personally used, or a desktop computer or a notebook computer.
  • the hair information providing device 200 may be a computer device installed in a hair loss treatment hospital or a portable device of a doctor or nurse.
  • the hair information providing device 200 includes a processor 210 , a memory 220 , a hair condition analysis unit 230 , a statistical analysis unit 240 , and a game execution unit 250 . ), an input unit 260 , a display 270 , a communication unit 280 , a bus 202 , and the like.
  • the processor 210 executes a computer program stored in the memory 220 to perform a predetermined operation.
  • the memory 220 may store a computer program for the operation of the hair information providing device 200 , various parameters, data, and the like.
  • the memory 220 may include a non-volatile memory such as a flash memory and a volatile memory such as a RAM.
  • the memory 220 may include a mass storage device such as HDD, ODD, or SDD.
  • Some or all of the hair condition analysis unit 230 , the statistical analysis unit 240 , and the game execution unit 250 may be provided in the form of a computer program stored in the memory 220 and executed by the processor 210 . Also, it may be provided in the form of hardware such as an Application Specific Integrated Circuit (ASIC), or may be provided in an integrated form of hardware and software.
  • ASIC Application Specific Integrated Circuit
  • the input unit 260 is an input device for a user of the hair information providing device 200 and may include at least one of a keyboard, a button, a touch pad, a touch screen, and a mouse.
  • the display 270 may output the operation state of the hair information providing device 200 or the analysis result of the hair condition analysis unit 230 , the analysis result of the statistical analysis unit 240 , the execution screen of the game execution unit 250 , and the like.
  • the communication unit 280 may include short-range wireless communication means such as Wi-Fi and Bluetooth for communicating with the camera 100 and wired or wireless communication means for communicating with the server 400 via the communication network 300 . .
  • the bus 202 is a data or electrical signal transmission path between each component of the hair information providing device 200, and may be provided in the form of a circuit pattern or a cable.
  • the hair condition analysis unit 230 as shown in the functional block diagram of FIG. 3 , the hair root analysis unit 232 , the visualization processing unit 234 , the hair density analysis unit 236 , and the hair loss progress analysis unit 238 . and the like.
  • the hair root analysis unit 232 analyzes the hair image captured by the camera 100 to classify the type of hair root and calculate the number.
  • 'single hair root' means a case in which one hair grows in one hair follicle
  • 'n hair root' is one It means that n hairs (n is an integer greater than or equal to 2) grow in the hair follicles of
  • a method of classifying the type of hair root in the hair root analysis unit 232 includes a method of utilizing the artificial intelligence for hair root analysis 500 and a method of using an image analysis technology such as OpenCV.
  • the hair root analysis artificial intelligence 500 includes a model generator 510 , a hair root analysis model 520 , an image preprocessor 530 , and an analysis result output unit 540 . ) and the like. Some or all of these functions may be provided in the form of a computer program stored in the memory 220 and executed by the processor 210, may be provided in the form of hardware, or may be provided in the form of a combination of hardware and software. may be provided.
  • At least one of the model generating unit 510 and the hair root analysis model 520 may be installed only in the server 400 .
  • the model generator 510 may generate the hair root analysis model 520 by, for example, learning a deep learning-based model architecture to which arbitrary weights are set.
  • the deep learning-based model architecture has one or more hidden layers between the input layer and the output layer as illustrated in FIG. By updating the weight ([W]1,,,,,[W]n) given between nodes (neurons) of the layer to an optimal value, the accuracy of the output value can be improved.
  • the hair root analysis model 520 does not necessarily have to be a deep learning model, and may be designed based on other types of machine learning models.
  • the model generation unit 510 includes a learning preparation unit 512 and a learning execution unit 514 , and may generate a hair root analysis model by the method illustrated in the flowchart of FIG. 6 .
  • the learning preparation unit 512 prepares data for learning. To this end, the learning preparation unit 512 performs a process of directly collecting a plurality of images of hair including hair roots through a web search, or receiving or receiving input from an administrator.
  • the learning preparation unit 512 may additionally perform a data amplification process of generating a plurality of modified images for learning from one hair image by applying various filtering elements to the collected hair images.
  • the learning preparation unit 512 analyzes the collected hair image to extract a hair root region, and performs a predetermined labeling on the extracted hair root region as shown in the right photo of FIG. 7 .
  • the labeling is to identifiably display the type of the root of the extracted hair root region.
  • the hair root region is displayed in a rectangle, single hair roots are displayed in green, double hair roots are displayed in red, and triple hair roots are displayed in blue. did.
  • the shape or color of the mark for labeling may vary.
  • the learning preparation unit 512 may perform an image preprocessing process in order to extract the features of the hair root type.
  • preprocessing such as contrast enhancement, noise removal, blur processing, and sharpness enhancement may be performed on the original image.
  • this image preprocessing process may be performed before labeling or may be omitted if necessary.
  • the learning execution unit 514 inputs the labeled training hair image to the input terminal of the artificial intelligence model architecture, calculates an output value (eg, hair root type, number of each type), and executes the back propagation algorithm. The operation of updating the weight based on the output value is repeated to generate the hair root analysis model 520 . (ST14, ST15)
  • the hair root analysis model 500 generated by this process performs an artificial intelligence algorithm to classify the types of hair roots included in the input image when an actual user inputs an actual hair image to check their hair condition, while the number of each type plays a role in calculating
  • the image preprocessor 530 may serve to extract a region of interest (ROI) from the hair image received from the camera 100 while scaling the image size to a set size. However, when the magnification and/or size of the hair image acquired by the camera 100 is constant, the image preprocessor 530 may be omitted.
  • ROI region of interest
  • the analysis result output unit 540 may output the analysis result of the hair root analysis model 520 to the display 270 under the control of the processor 210 or transmit it to the server 280 through the communication unit 280 .
  • the analysis result output unit 540 may output, for example, a hair root type classification screen as shown in the right photo of FIG. 7 through the display 270 .
  • a simplified hair pattern is extracted from the hair image captured by the camera 100 .
  • a known image analysis technique it is possible to extract such a simplified hair pattern from the hair image.
  • the endpoints of each pattern are extracted from the simplified hair pattern, and the distance between the endpoints is calculated using the coordinates of each endpoint.
  • Calculation of the coordinates and distance of each end point can be calculated using information such as the magnification of the hair image and the pixels of the image sensor. (See Fig. 10(b), Fig. 10(c))
  • hair whose calculated distance is less than or equal to a set value (eg, 1 mm) is determined as multiple hair roots.
  • the hair bundle is classified as a double root root. classify In other words, if the distance between the end points is within the set value and the number of adjacent hairs is n (n is an integer greater than or equal to 2), the corresponding hair bundle is classified as an n-fold hair root.
  • the visualization processing unit 234 of the hair condition analysis unit 230 visualizes and outputs the hair root type analyzed through the hair root analysis artificial intelligence 500 or OpenCV image analysis so that the user can intuitively recognize it. plays a role
  • the hair density analyzer 236 calculates the number of hairs and the hair density in the corresponding hair image by using the analysis result of the hair root analyzer 232 .
  • the analysis result of the hair root analysis unit is 20 single hair roots, 5 double hair roots, and 3 triple hair roots, it is easy to find that the total number of hairs in the hair image is 39 (20 + 2*5 + 3*3). Able to know. In addition, when the number of hairs is calculated, the hair density of the corresponding region can be easily calculated.
  • the hair density analyzer 236 may visualize the hair density of the photographed area in various colors and then output it through the display 270 .
  • the hair loss progress analysis unit 238 compares the analysis results of the hair root analysis unit 232 and/or the hair density analysis unit 236 with past results to analyze the user's hair loss progress.
  • the hair loss trend and/or hair loss rate can be more accurately determined compared to a method of simply comparing only the number of hairs by calculating variation information for each type of hair root.
  • the single hair root remains the same, but it can be seen that the double hair root is lost and converted to a single hair root.
  • the number of multiple hair roots is increased, it can be seen that a new hair root that has been hidden from a single or double hair root has grown.
  • the hair loss progress analysis unit 238 may determine the degree of hair loss and output the images of the front, middle, crown, back, etc. of the user's head in comparison with the known Ludwig Scale or Savin scale.
  • the statistical analysis unit 240 of the hair information providing apparatus 200 stores the result value of the hair condition analysis unit 230 and calculates statistics in various ways. do.
  • Statistical information may be provided in the form of a time series graph so that the user can easily check the hair loss trend.
  • the information provided from the statistical analysis unit 240 includes the number of single hair roots, the number of double hair roots, the number of triple hair roots, the number of hairs, the density of hair, the change trend of single hair roots, the change trend of multiple hair roots, and the progress of hair loss by imaging area. It may include information about the degree, etc.
  • the statistical analysis unit 240 may be installed only in the server 400 rather than the hair information providing device 200 .
  • the game execution unit 250 is to provide a fun element to the user, and provides a game interface that can compete with other users in various ways.
  • the type of the game is not particularly limited, and the game can be played in various ways, for example, a contest for the number of hairs, a contest for the number of multiple hair roots, a contest for the rate of change of the number of hairs, a contest for the rate of change of multiple hair roots, and the like.
  • the server 400 includes a processor 410 , a memory 420 , a hair condition analysis unit 430 , a statistical analysis unit 440 , a game support unit 450 , and a communication unit 460 . ), an input/output unit 470 , a database 480 , a bus 402 , and the like.
  • the processor 410 executes a computer program stored in the memory 420 to perform a predetermined operation.
  • the memory 420 may store a computer program for the operation of the server 400 , various parameters, data, and the like.
  • the memory 420 may include a non-volatile memory such as a flash memory and a volatile memory such as a RAM.
  • the memory 420 may include a mass storage device such as HDD, ODD, or SDD.
  • Some or all of the hair condition analysis unit 430 , the statistical analysis unit 440 , and the game support unit 450 may be provided in the form of a computer program stored in the memory 420 and executed by the processor 410 .
  • ASIC, etc. may be provided in the form of hardware, or may be provided in an integrated form of hardware and software.
  • the communication unit 460 may include a wired or wireless communication means for communicating with the hair information providing device 200 .
  • the input/output unit 470 may include an input means for an administrator and an output means such as a display.
  • the database 480 stores information such as identification information such as ID of a user possessing the hair information providing device 200, hair condition information for each user, statistical information for each user, and game performance history for each user.
  • the bus 402 is a transmission path of data or electrical signals between each component of the server 400 and may be provided in the form of a circuit pattern or a cable.
  • the hair condition analysis unit 430 includes a hair root analysis unit 432 , a visualization processing unit 434 , a hair density analysis unit 436 , and a hair loss progress rate determination unit 438 , each of which The functions of the hair root analysis unit 232 , the visualization processing unit 234 , the hair density analysis unit 236 , and the hair loss progress rate determination unit 238 of the hair information providing device 200 are the same, and thus a description thereof will be omitted.
  • Some or all of the hair root analysis unit 432 , the visualization processing unit 434 , the hair density analysis unit 436 , and the hair loss progress rate determination unit 438 are not installed in the server 400 , but are installed only in the hair information providing device 200 . may be
  • a user can use his/her smart phone as the hair information providing device 200 by downloading a dedicated application for applying an embodiment of the present invention, installing it on his/her smartphone, and executing it.
  • the hair root analysis unit 232 of the hair information providing device 200 includes the hair root analysis model 520 using artificial intelligence, a pre-processing operation such as scaling the photographed image to a set size is performed, If the size of the image is within the set range, pre-processing is omitted. (ST22)
  • the hair root analysis model 520 executes the learned algorithm to output the type of each hair root included in the hair image and the number of each type.
  • the hair density analyzer 236 may calculate the number and density of hairs in the photographed area using the output. (ST24)
  • the hair loss progress analysis unit 238 compares information such as the number of each type of hair root, the hair density, and the number of hairs with the analysis results of the past to calculate a change rate, and determines the hair loss progress state based on this.
  • the calculated information is stored in the hair information providing device 200 or transmitted to the server 400 and stored in the database 480 , and is utilized for statistical processing in the statistical analysis units 240 and 440 . (ST25, ST26)
  • the hair root analysis unit 232 analyzes the type of hair root using the hair root analysis model 520 using artificial intelligence, but as illustrated in FIG. 10 , the distance between the endpoints of the hair pattern As described above, it is also possible to determine the type of hair root by calculating .
  • the match-up game may be a one-on-one method, may be a method in which multiple players compete for ranking, or may be a one-to-one or multi-person competition by designating the age or gender of the game opponent.
  • Contest items for example, the number of hair, hair density, increase/decrease in the number/density of hair, the number of double hair roots, the number of triple hair roots, the increase/decrease width of double hair roots, the increase/decrease width of triple hair roots, all items can be selected. . (ST31)
  • the game support unit 450 of the server 400 when there is a request for a game designating the opponent from the user, inquires about the participation intention to the designated opponent's hair information providing device 200, and if the opponent approves, game matching with the game applicant's device 200 Request hair imaging and analysis with notice.
  • the game support unit 450 of the server 400 receives a game request of a multiple participation method from the user's device 200, it selects a plurality of people according to a set criterion from among unspecified people waiting after a game application, or the user After selecting a plurality of people according to a set criterion among people of a specified age group and/or gender, a game is matched, and a hair photographing and analysis is requested along with a game matching notification to each device 200 . (ST32, ST33)
  • Users who have received such a request use their respective cameras 200 to photograph hair in an arbitrary area or a designated area on the game screen, and use the hair condition analysis unit ( 230) to analyze it. At this time, it is possible to calculate the number of each hair root type, the number of hairs, the hair density, and the like.
  • the captured image may be transmitted from the respective device 200 to the server 400 to request analysis.
  • the load is concentrated on the server 400 in this way, it may take too much time to determine the ranking if there are many game participants. Therefore, it is much preferable in terms of the speed of the game to perform hair analysis on the user's device 200 as there are more participants. something to do. (ST34)
  • the game execution unit 250 of each device 200 transmits the analysis result to the server 400 , and the server 400 determines the ranking for each item in comparison with the analysis result received from the device 200 of each participant. and transmits the result to each device 200 .
  • the rate of change of each item may be calculated using the past data for each participant stored in the database 480 , and the ranking of the rate of change for each item may be calculated and transmitted to each device 200 . (ST35, ST36)
  • the hair information providing method and the game method according to the embodiment of the present invention described above may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable recording medium.
  • the computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.
  • the program instructions recorded on the recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art related to computer software.
  • Computer-readable recording media include magnetic media such as hard disks, SSDs, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and optical disks. It may include at least one of a magneto-optical medium, a ROM, a RAM, a flash memory, and the like.
  • program instructions may include high-level language codes that can be executed by a computer using an interpreter as well as machine language codes such as those generated by a compiler.
  • visualization processing unit 236 hair density analysis unit 238: hair loss progress analysis unit
  • server 410 processor 420: memory
  • hair condition analysis unit 440 statistical analysis unit 450: game support unit
  • learning execution unit 520 hair root analysis model 530: image preprocessing unit

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Dentistry (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé et un dispositif de fourniture d'informations capillaires, et un procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci. Un procédé d'analyse de l'état capillaire selon la présente invention comprend les étapes consistant à : acquérir une image des cheveux ; analyser l'image des cheveux de façon à classer le type de racine de cheveux en tant que racine de cheveux unique ou une racine de cheveux n fois (n est un nombre entier supérieur ou égal à 2) ; et le calcul du nombre de racines de cheveux par type. Selon la présente invention, l'image des cheveux est analysée en temps réel en utilisant une intelligence artificielle, de telle sorte qu'un utilisateur peut vérifier rapidement et avec précision l'état capillaire de l'utilisateur sans se rendre à une consultation hospitalière. De plus, on fournit des informations concernant le nombre et la densité des cheveux, le type de racine de cheveux, le nombre de racines de cheveux multiples, un taux de progression de perte de cheveux, un graphique de série chronologique et analogues, de telle sorte que l'utilisateur peut vérifier plus précisément l'état capillaire de l'utilisateur.
PCT/KR2021/004802 2020-04-21 2021-04-16 Procédé et dispositif de fourniture d'informations capillaires, et procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci WO2021215749A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
KR10-2020-0048104 2020-04-21
KR1020200048104A KR102329641B1 (ko) 2020-04-21 2020-04-21 모발 상태를 분석하는 방법 및 이를 이용한 모발 정보 제공 장치 및 시스템
KR1020200136590A KR20220052532A (ko) 2020-10-21 2020-10-21 모근 검출기를 이용한 모발 정보 제공 방법 및 이를 위한 장치 및 시스템
KR10-2020-0136590 2020-10-21

Publications (1)

Publication Number Publication Date
WO2021215749A1 true WO2021215749A1 (fr) 2021-10-28

Family

ID=78269710

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/004802 WO2021215749A1 (fr) 2020-04-21 2021-04-16 Procédé et dispositif de fourniture d'informations capillaires, et procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci

Country Status (1)

Country Link
WO (1) WO2021215749A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024192560A1 (fr) * 2023-03-17 2024-09-26 Ho Yin Wong Système et procédé de détermination d'épaisseur de cheveux sur une personne

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007260038A (ja) * 2006-03-28 2007-10-11 Taisho Pharmaceut Co Ltd 毛髪数の計測方法および発毛剤の効果の評価方法
KR20090030341A (ko) * 2006-08-25 2009-03-24 레스토레이션 로보틱스, 인코포레이티드 모낭 단위 분류 방법 및 시스템, 종단점 결정 방법과, 화상처리기
KR101030853B1 (ko) * 2006-08-25 2011-04-22 레스토레이션 로보틱스, 인코포레이티드 모낭 단위 카운트 방법, 시스템, 화상 처리기 및 모낭 단위를 카운트하고 분류하는 방법
KR20120110479A (ko) * 2011-03-29 2012-10-10 강진수 탈모진행정도의 측정 방법
US20190209077A1 (en) * 2018-01-05 2019-07-11 L'oreal Grooming instrument configured to monitor hair loss/growth

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007260038A (ja) * 2006-03-28 2007-10-11 Taisho Pharmaceut Co Ltd 毛髪数の計測方法および発毛剤の効果の評価方法
KR20090030341A (ko) * 2006-08-25 2009-03-24 레스토레이션 로보틱스, 인코포레이티드 모낭 단위 분류 방법 및 시스템, 종단점 결정 방법과, 화상처리기
KR101030853B1 (ko) * 2006-08-25 2011-04-22 레스토레이션 로보틱스, 인코포레이티드 모낭 단위 카운트 방법, 시스템, 화상 처리기 및 모낭 단위를 카운트하고 분류하는 방법
KR20120110479A (ko) * 2011-03-29 2012-10-10 강진수 탈모진행정도의 측정 방법
US20190209077A1 (en) * 2018-01-05 2019-07-11 L'oreal Grooming instrument configured to monitor hair loss/growth

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024192560A1 (fr) * 2023-03-17 2024-09-26 Ho Yin Wong Système et procédé de détermination d'épaisseur de cheveux sur une personne

Similar Documents

Publication Publication Date Title
CN109948459B (zh) 一种基于深度学习的足球动作评估方法与系统
WO2021025461A1 (fr) Système de diagnostic à base d'image échographique pour lésion d'artère coronaire utilisant un apprentissage automatique et procédé de diagnostic
WO2019132168A1 (fr) Système d'apprentissage de données d'images chirurgicales
WO2018048000A1 (fr) Dispositif et procédé d'interprétation d'imagerie tridimensionnelle basés sur caméra unique, et support lisible par ordinateur enregistré avec un programme pour une interprétation d'imagerie tridimensionnelle
WO2021215749A1 (fr) Procédé et dispositif de fourniture d'informations capillaires, et procédé de génération de modèle d'analyse de racine de cheveux pour ceux-ci
KR102202490B1 (ko) 3차원 신체 모델 측정 장치 및 방법
WO2021242050A1 (fr) Procédé de traitement d'image buccale, dispositif de diagnostic buccal pour effectuer une opération en fonction de ce dernier et support de mémoire lisible par ordinateur dans lequel est stocké un programme pour la mise en œuvre du procédé
WO2020226455A1 (fr) Dispositif de prédiction de neuropathie optique à l'aide d'une image de fond d'œil et procédé de fourniture d'un résultat de prédiction de neuropathie optique
WO2021010777A1 (fr) Appareil et procédé d'analyse précise de la gravité de l'arthrite
WO2016105102A1 (fr) Dispositif et procédé pour évaluer la possibilité d'apparition de trouble musculo-squelettique
WO2020071086A1 (fr) Dispositif de traitement d'informations, procédé de commande, et programme
JP2002236904A (ja) データ処理装置および方法、記録媒体、並びにプログラム
WO2019164273A1 (fr) Méthode et dispositif de prédiction de temps de chirurgie sur la base d'une image chirurgicale
WO2017043945A1 (fr) Procédé et appareil de reconnaissance d'expressions faciales détaillées
KR102329641B1 (ko) 모발 상태를 분석하는 방법 및 이를 이용한 모발 정보 제공 장치 및 시스템
JP6019517B2 (ja) 眼球運動解析システム、眼球運動診断装置および眼球運動解析システムの作動方法
CN115553779A (zh) 一种情绪识别方法、装置、电子设备及存储介质
WO2022119347A1 (fr) Procédé, appareil et support d'enregistrement pour analyser un tissu de plaque d'athérome par apprentissage profond basé sur une image échographique
CN115813343A (zh) 儿童行为异常评估方法和系统
WO2022034955A1 (fr) Appareil pour détecter un ulcère cornéen sur la base d'un traitement d'image et procédé associé
WO2021141186A1 (fr) Système et procédé d'apprentissage de réadaptation cognitive de types multiples
WO2018048227A1 (fr) Dispositif, procédé et programme de production d'une image de type à réaction multidimensionnelle, et procédé et programme de reproduction d'une image de type à réaction multidimensionnelle
EP4026479A1 (fr) Dispositif de traitement d'image médicale, système d'endoscope, procédé de traitement d'image médicale et programme
WO2020159276A1 (fr) Appareil d'analyse chirurgicale et système, procédé et programme pour analyser et reconnaître une image chirurgicale
WO2019168372A1 (fr) Appareil de traitement d'images médicales et son procédé de fonctionnement

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: 21791895

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 27.03.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21791895

Country of ref document: EP

Kind code of ref document: A1