CN117617899A - Face skin detection method and detection device - Google Patents
Face skin detection method and detection device Download PDFInfo
- Publication number
- CN117617899A CN117617899A CN202210998003.3A CN202210998003A CN117617899A CN 117617899 A CN117617899 A CN 117617899A CN 202210998003 A CN202210998003 A CN 202210998003A CN 117617899 A CN117617899 A CN 117617899A
- Authority
- CN
- China
- Prior art keywords
- image
- image acquisition
- acquisition component
- face
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 60
- 230000005808 skin problem Effects 0.000 claims abstract description 68
- 230000001815 facial effect Effects 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 16
- 239000002537 cosmetic Substances 0.000 claims description 27
- 206010000496 acne Diseases 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 9
- 208000002874 Acne Vulgaris Diseases 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 210000001061 forehead Anatomy 0.000 claims description 6
- 239000004519 grease Substances 0.000 claims description 6
- 239000011148 porous material Substances 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 6
- 230000036541 health Effects 0.000 abstract description 6
- 230000003321 amplification Effects 0.000 abstract 1
- 238000003199 nucleic acid amplification method Methods 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 7
- 230000036559 skin health Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
Abstract
The invention discloses a face skin detection method and a detection device, wherein the method comprises the following steps: controlling a first image acquisition component to acquire a full-face image; identifying skin problems according to the full-face image and identifying areas; and prompting to acquire a local image of the identification area where the skin problem is located by using the second image acquisition component, and acquiring the severity and/or score of the identification area in the corresponding dimension of the skin problem based on the acquired local image. According to the invention, the area where the skin problem is located is rapidly identified and identified by collecting the full-face image, and then the local fine image collection of the amplification factor is carried out on the area where the skin problem is located by the second image collection assembly, so that the severity and/or score of the identified area in the corresponding dimension of the skin problem is obtained, and the user can know the health condition of the facial skin more accurately and comprehensively.
Description
Technical Field
The invention relates to the technical field of skin detection, in particular to a face skin detection method and a face skin detection device.
Background
With the improvement of the current living standard, the public is more and more concerned about the appearance and the instrument of the public, and the cosmetic mirror is popular as a popular consumer product, and especially female consumers can use the cosmetic mirror almost every day. The mirror has the main functions of finishing instruments and assisting in makeup. With the development of technology, consumers have more and more diversified and intelligent requirements on mirror functions.
The second image acquisition component configured by the prior cosmetic mirror on the market is basically handheld and can only perform local detection, and a user can select one position to detect in the forehead, cheek, nose wing and chin freely, and because the whole face health is not clear, the user can randomly select an area to perform image acquisition during image acquisition, or select an area possibly having a problem on the skin according to the feeling of the user to perform image acquisition, on one hand, the image acquisition time is prolonged, on the other hand, a skin image actually having a problem can not be acquired, and finally the analyzed face skin data can not reflect the real health state of the face skin, so that the skin problem can not be treated in time.
Disclosure of Invention
The main purpose of the invention is to provide a face skin detection method and a detection device, which overcome the defects existing in the prior art, firstly, the region where the skin problem is located is rapidly identified and the region identification is carried out by collecting the full-face image, then, the local fine image collection of the magnification factor of the region where the skin problem is located is carried out by a second image collection component (such as a skin test pen), and the severity and/or fraction of the identified region in the corresponding dimension of the skin problem is obtained, so that the user can know the skin health condition of the face more accurately and comprehensively.
The invention adopts the following technical scheme:
in one aspect, a facial skin detection method includes:
controlling a first image acquisition component to acquire a full-face image;
identifying skin problems according to the full-face image and identifying areas;
and prompting to acquire a local image of the identification area where the skin problem is located by using the second image acquisition component, and acquiring the severity and/or score of the identification area in the corresponding dimension of the skin problem based on the acquired local image.
Preferably, the controlling the first image acquisition component to acquire the full-face image specifically includes:
when the whole face is detected to be in the image pickup area of the first image acquisition component, controlling to start white light to take full face to acquire full face image pickup.
Preferably, the method for identifying skin problems and identifying areas according to the full-face image specifically comprises the following steps:
and identifying skin problems in the full-face image by using the trained convolutional neural network model, positioning image coordinates of the skin problems, and identifying corresponding position areas of the full-face image.
Preferably, the prompting of using the second image acquisition component to acquire the local image of the identification area where the skin problem is located specifically includes:
prompting the use of a second image acquisition component to acquire preset partial images of the identification area where each skin problem is located under natural light, UV light or polarized light; the preset sheet is larger than 1 sheet.
Preferably, the prompting uses the second image acquisition component to acquire the preset partial images of the identification area where each skin problem is located under natural light, UV light or polarized light, and specifically includes:
s501, prompting a user to collect an image of an identification area where a certain skin problem is located by using a second image collection component under natural light, UV light or polarized light, judging whether the photographed image is clear or not, and repeating the step S501 if the photographed image is not clear; if clear, go to step S502;
s502, prompting a user to shoot a next image of the identification area under the same light source or different light sources; and repeats step S501;
s503, until the number of clear images in the area reaches a preset value;
s504, repeating S501-S503 until all the identification areas with skin problems acquire the preset partial images.
Preferably, before controlling the first image acquisition component to acquire the full-face image, the method further comprises:
detecting the opening state of the second image acquisition component, and controlling to enter the step of acquiring the full-face image by the first image acquisition component if the second image acquisition component is not opened; and if the method is started, prompting the second image acquisition component to acquire partial images of the divided face areas, and acquiring the severity and/or score of each face area in the corresponding dimension of the skin problem based on the acquired partial images.
Preferably, the prompting of using the second image acquisition component to acquire the local image for each divided face area specifically includes:
prompting the use of a second image acquisition component to acquire preset partial images of each divided face area under natural light, UV light or polarized light; the preset sheet is larger than 1 sheet.
Preferably, the prompting uses the second image acquisition component to acquire the preset partial images of each divided face area under natural light, UV light or polarized light, and specifically includes:
s801, prompting a user to collect images of a certain divided face area by using a second image collection assembly under natural light, UV light or polarized light, judging whether the photographed images are clear or not, and repeating the step S801 if the photographed images are not clear; if clear, go to step S802;
s802, prompting a user to shoot a next image of the face area under the same light source or different light sources; and repeats step S801;
s803, until the number of clear images in the area reaches a preset value;
s804, repeating S801-S803 until all the divided face areas acquire a preset partial image.
Preferably, the face area includes: forehead, left cheek, right cheek, nose and chin.
Preferably, the skin problem comprises: at least one of texture, pores, acne, sensitivity, stain, blackhead or grease; each skin problem corresponds to a dimension.
Preferably, the severity comprises: severe, moderate or mild.
Preferably, the score is obtained based on severity and corresponding confidence, as follows:
wherein x represents the confidence; f (x) represents a score.
In another aspect, a facial skin detection device includes a first image acquisition assembly, a cosmetic mirror, and a second image acquisition assembly; the cosmetic mirror and the first image acquisition component and the second image acquisition component respectively perform data interaction; the first image acquisition component and the makeup mirror are arranged separately, or the first image acquisition component is arranged on the makeup mirror; the cosmetic mirror is used for executing the steps of the facial skin detection method.
In yet another aspect, a facial skin detection apparatus includes a first image acquisition assembly, a cosmetic mirror, a second image acquisition assembly, and an external terminal device; the cosmetic mirror, the first image acquisition assembly, the second image acquisition assembly and the external terminal equipment respectively conduct data interaction; the first image acquisition component and the makeup mirror are arranged separately, or the first image acquisition component is arranged on the makeup mirror; the external terminal device is used for executing the steps of the facial skin detection method.
Compared with the prior art, the invention has the following beneficial effects:
(1) Firstly, a whole face image is collected to quickly identify and mark a weak area of facial skin health, namely an area where skin problems are located, so that a user can primarily and macroscopically know the whole face; the local fine image acquisition of the magnification factor of the area where the identified skin problem is located is carried out through a second image acquisition component (such as a skin test pen) to obtain the severity and/or score of the identified area in the corresponding dimension of the skin problem, so that the user can know the health condition of the facial skin more accurately and comprehensively;
(2) According to the invention, whether the second image acquisition assembly is started or not can be automatically searched for a WIFI hotspot and the like of the second image acquisition assembly, if not, full-face image acquisition and analysis can be firstly carried out, and then a user is guided to start the second image acquisition assembly to carry out local image acquisition and analysis on the area with the skin problem; if the second image acquisition component is started, the user can be prompted to perform full-face image detection first, and if the user does not close the second image acquisition component, the user does not want to perform full-face image acquisition and detection, the user can directly perform local image acquisition and detection on a user selection area, or the user is guided to perform image acquisition and detection on forehead, left cheek, right cheek, nose and chin areas in sequence, and the multi-azimuth requirement of the user is met.
The foregoing description is only an overview of the present invention, and is intended to provide a more clear understanding of the technical means of the present invention, so that it may be carried out in accordance with the teachings of the present specification, and to provide a more complete understanding of the above and other objects, features and advantages of the present invention, as exemplified by the following detailed description.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of the specific embodiments of the present invention when taken in conjunction with the accompanying drawings.
Drawings
Fig. 1 is a flow chart of a face skin detection method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a skin problem identified according to a full-face image according to a first embodiment of the present invention;
FIG. 3 is a detailed detection flow chart of the second image capturing component according to the first embodiment of the present invention when not turned on;
FIG. 4 is a detailed detection flow chart of the second image acquisition assembly according to the first embodiment of the present invention when turned on;
fig. 5 is a block diagram of a facial skin detection device according to a second embodiment of the present invention;
fig. 6 is a front view of a facial skin detection device according to a second embodiment of the present invention;
fig. 7 is a cross-sectional view of a facial skin detection device according to a second embodiment of the present invention;
fig. 8 is a second cross-sectional view of a facial skin detection device according to a second embodiment of the present invention;
fig. 9 is a block diagram showing the structure of a facial skin detection apparatus according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention; it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments, and that all other embodiments obtained by persons of ordinary skill in the art without making creative efforts based on the embodiments in the present invention are within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the description of the present invention, it should be noted that the positional or positional relationship indicated by the terms such as "upper", "lower", "inner", "outer", "top/bottom", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "provided," "engaged/connected," "connected," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, may be a detachable connection, or may be an integral connection, may be a mechanical connection, may be an electrical connection, may be a direct connection, may be an indirect connection via an intermediary, may be a communication between two elements, and for one of ordinary skill in the art, the specific meaning of the terms in this disclosure may be understood in a specific case.
In the description of the present invention, unless explicitly stated and defined otherwise, the step identifiers S101, S102, S103, etc. are used for convenience of description, and do not represent an execution sequence, and the corresponding execution sequence may be adjusted.
Example 1
Referring to fig. 1, in one aspect, a facial skin detection method includes:
s101, controlling a first image acquisition component to acquire a full-face image;
s102, identifying skin problems according to the full-face image and identifying areas;
s103, prompting to acquire a local image of the identification area where the skin problem is located by using the second image acquisition component, and acquiring the severity and/or score of the identification area in the corresponding dimension of the skin problem based on the acquired local image.
In this embodiment, the facial skin detection method may be implemented through a control motherboard installed in the cosmetic mirror, where the control motherboard includes an MCU controller and the like, and is connected to the first image acquisition component and the second image acquisition component to perform data interaction. In another embodiment, the facial skin detection method may be implemented in an external terminal, where the external terminal includes an actuator and the like, and is connected to the first image acquisition component and the second image acquisition component for data interaction. In other embodiments, the method may further include controlling the acquisition of the full-face image, prompting the acquisition of the partial image, and the like to be implemented in the cosmetic mirror, identifying the skin problem according to the full-face image, and implementing the identification in the external terminal device, and acquiring the severity and/or score of the identification area in the corresponding dimension of the skin problem based on the acquired partial image, where the second image acquisition component or the external terminal device is implemented, and the devices are connected to each other to perform data interaction. The specific implementation mode can be laid out according to the requirement, and the invention is not limited.
Firstly, a facial skin health weak area, namely an area where a skin problem is located, is quickly identified by acquiring a full-face image, and area identification is carried out, so that a user can primarily and macroscopically know the whole face; and then, carrying out local fine image acquisition of the magnification factor on the area where the identified skin problem is located through the second image acquisition component to obtain the severity and/or score of the identified area on the corresponding dimension of the skin problem, so that the user can know the health condition of the facial skin more accurately and comprehensively.
The method for controlling the first image acquisition component to acquire the full-face image specifically comprises the following steps:
when the whole face is detected to be in the image pickup area of the first image acquisition component, controlling to start white light to take full face to acquire full face image pickup.
Identifying skin problems and carrying out region identification according to the full-face image, and specifically comprising the following steps:
and identifying skin problems in the full-face image by using the trained convolutional neural network model, positioning image coordinates of the skin problems, and identifying corresponding position areas of the full-face image.
Specifically, the first image acquisition component is controlled to start the camera, whether the whole face of the user is in the camera shooting area is firstly judged, and if not, the user is prompted to move correspondingly by voice; judging the brightness of the ambient light, and if the environment is darker, starting a white LED lamp group of the makeup lamp around the makeup mirror body; finally, taking a white light photograph of the whole face, identifying skin problems based on a convolutional neural network model of a training number (the convolutional neural network model is a feasible network model designed in advance, loading a large number of face training data sets into the network model, then carrying out automatic training to obtain a good identification rate), finally identifying the coordinates of the skin problems (texture, pores, acne, sensitivity, color spots, blackheads and grease, and the like) in a limited area of the face, and positioning the coordinates of the texture, pores, acne, sensitivity, color spots, blackheads and grease, and the like, and identifying the coordinates at corresponding positions on the whole face image.
Referring to fig. 2, a circle is used to mark the area where the skin problem is located on the full-face image, and the area is displayed on the interface of the cosmetic mirror or the external terminal device APP, and the user is prompted whether to detect locally immediately or not through voice or interface.
The full-face image detection is mainly used for helping a user to quickly find out a place with weak facial skin health, and the whole face is subjected to preliminary macroscopic detection to find out and mark the area with skin problems.
When the local image is acquired, the local second image acquisition component is adopted to aim at the identification areas, cameras with the magnification of tens of times are adopted under the light sources of white light, polarized light, UV light and the like, and the images are automatically photographed according to the image definition, so that the targeted image acquisition is carried out on all the identification areas.
In this embodiment, the second image capturing component is a skin test pen.
Since the severity and/or score of the subsequent calculation of the facial region in the corresponding dimension of the skin problem depends on whether the partial image is clear, if the image taken by the user is not clear, the subsequent steps may not be completed or the result may deviate.
Specifically, the prompting uses the second image acquisition component to acquire the preset partial images of the identification area where each skin problem is located under natural light, UV light or polarized light, and specifically includes:
s501, prompting a user to collect an image of an identification area where a certain skin problem is located by using a second image collection component under natural light, UV light or polarized light, judging whether the photographed image is clear or not, and repeating the step S501 if the photographed image is not clear; if clear, go to step S502;
s502, prompting a user to shoot a next image of the identification area under the same light source or different light sources; and repeats step S501;
s503, until the number of clear images in the area reaches a preset value;
s504, repeating S501-S503 until all the identification areas with skin problems acquire the preset partial images.
For the determination of sharpness, algorithms for image recognition and image comparison, which are common in the prior art, may be used. Specifically, the image shot by the second image acquisition component can be compared with the pre-image information in real time to judge, and when the definition score is reached, the image is judged to be clear, and the image is saved. The definition may also be determined by an image recognition algorithm, such as a deep neural network algorithm, and when a clear image is recognized, the image may be saved. The embodiment is not limited.
The skin problems include: at least one of texture, pores, acne, sensitivity, stain, blackhead or grease; each skin problem corresponds to a dimension.
The severity includes: severe, moderate or mild.
The score is obtained based on the severity and the corresponding confidence, and is specifically as follows:
wherein x represents the confidence; f (x) represents a score.
And carrying out data operation on the acquired image by using a preset algorithm, calculating the severity and/or score of the skin problem in the corresponding dimension, thus more accurately learning the health condition of the skin, and taking corresponding skin care measures. Specifically, the category of the severity and the corresponding confidence level may be obtained according to the existing image processing method, which is not described in detail in this embodiment.
Referring to fig. 3 and 4, before controlling the first image acquisition component to acquire the full-face image, the method further includes:
detecting the opening state of the second image acquisition component, and controlling to enter the step of acquiring the full-face image by the first image acquisition component if the second image acquisition component is not opened; and if the method is started, prompting the second image acquisition component to acquire partial images of the divided face areas, and acquiring the severity and/or score of each face area in the corresponding dimension of the skin problem based on the acquired partial images.
In this embodiment, the face area includes: forehead, left cheek, right cheek, nose and chin.
Prompting to acquire partial images of the divided face areas by using a second image acquisition component, and specifically comprising:
prompting the use of a second image acquisition component to acquire preset partial images of each divided face area under natural light, UV light or polarized light; the preset sheet is larger than 1 sheet.
Further, prompting to use the second image acquisition component to acquire preset partial images of each divided face area under natural light, UV light or polarized light, and specifically comprising:
s801, prompting a user to collect images of a certain divided face area by using a second image collection assembly under natural light, UV light or polarized light, judging whether the photographed images are clear or not, and repeating the step S801 if the photographed images are not clear; if clear, go to step S802;
s802, prompting a user to shoot a next image of the face area under the same light source or different light sources; and repeats step S801;
s803, until the number of clear images in the area reaches a preset value;
s804, repeating S801-S803 until all the divided face areas acquire a preset partial image.
According to the invention, whether the second image acquisition assembly is started or not can be automatically searched for a WIFI hotspot and the like of the second image acquisition assembly, if not, full-face image acquisition and analysis can be firstly carried out, and then a user is guided to start the second image acquisition assembly to carry out local image acquisition and analysis on the area with the skin problem; if the second image acquisition component is started, the user can be prompted to perform full-face image detection first, and if the user does not close the second image acquisition component, the user does not want to perform full-face image acquisition and detection, the user can directly perform local image acquisition and detection on a user selection area, or the user is guided to perform image acquisition and detection on forehead, left cheek, right cheek, nose and chin areas in sequence, and the multi-azimuth requirement of the user is met.
Example 2
As shown in figures 5 to 8 of the drawings,
a facial skin detection device includes a first image acquisition assembly 30, a cosmetic mirror 10, and a second image acquisition assembly 20; the cosmetic mirror 10 and the first image acquisition component 30 and the second image acquisition component 20 respectively perform data interaction; the first image acquisition component 30 and the cosmetic mirror 10 are separately arranged, or the first image acquisition component 30 is arranged on the cosmetic mirror 10.
The first image capturing assembly 30 of the present embodiment includes a main camera 301 disposed above the cosmetic mirror 10. The second image acquisition assembly 20 is placed in the pen holder 201. The pen holder 201 is disposed beside the cosmetic mirror 10 and is integrally designed with the cosmetic mirror 10.
Specifically, the cosmetic mirror 10 further includes a mirror body 101, a rotating assembly 102, a support 103, and a base 104. The mirror body 101 is connected to the base 104 through the support 103. The rotating assembly 102 drives the mirror body 101 to turn over, and the rotating assembly 102 comprises a rotating shaft 1021.
Further, the front surface of the mirror body 101 is composed of a touch screen 1011, a display screen 1012, a control main board 1013, a light compensating lamp assembly 1014, and the like, wherein the main camera 301 is located in the middle of the upper end of the mirror body 101. The inner side of the touch screen 1011 is hollowed-out with black silk screen corresponding to the silk screen position, so that a user can conveniently and directly operate various functions on the mirror surface. The control main board 1013 stores a software program for realizing the facial skin detection method as described above, and the software program can be executed on the control main board 1013 and display the execution result on the display screen 1012.
The specific implementation manner of this embodiment is as follows:
A. firstly, starting the cosmetic mirror, starting an intermediate display screen, entering an APP main interface, automatically searching whether a skin test pen WIFI hotspot exists or not, and displaying on the APP interface;
B. if yes, referring to fig. 4, performing local skin detection according to the flow, then performing full face detection, and then outputting an overall test report;
C. if not, referring to fig. 3, immediately starting the main camera, firstly judging whether the whole face of the user is in the shooting area, and if not, prompting the user to do corresponding movement by voice; judging the brightness of the ambient light, and if the environment is darker, starting a white LED lamp group of the makeup lamp around the mirror body; finally, taking a white light photograph of the whole face, identifying skin problems in a limited area of the face based on target detection of a convolutional neural network in a depth algorithm, positioning image coordinates of detected skin conditions, and identifying corresponding position areas on the face;
D. the interface prompts the user whether to detect locally immediately;
E. purposefully guiding a user, adopting a local skin test pen to align the identification area, adopting a camera with tens of times of magnification under the light sources of white light, polarized light, UV light and the like, automatically photographing all severe areas by a system according to image definition, carrying out targeted image acquisition on all the severe areas, carrying out data operation by the system by using an own algorithm after acquiring the images, and calculating the key dimensions of facial skin: texture, pores, acne, sensitivity, blemishes, blackheads, grease, etc., are determined, and their weight, middle and light are determined, so that skin health is more accurately known, and solutions are more accurately recommended.
Example 3
The present embodiment differs from embodiment 2 in that a software program implementing the face skin detection method as described above is stored in an external terminal device, and the software program can be executed on the external terminal device and the execution result is displayed on the display screen of the external terminal device.
Specifically, referring to fig. 9, a facial skin detection apparatus includes a first image acquisition component 901, a cosmetic mirror 902, a second image acquisition component 903, and an external terminal device 904; the cosmetic mirror 902 and the first image acquisition component 901, the second image acquisition component 903 and the external terminal device 904 respectively perform data interaction; the first image acquisition component 901 and the makeup mirror 902 are separately arranged, or the first image acquisition component 901 is arranged on the makeup mirror 902.
In this embodiment, the second image acquisition component 903 includes a skin test pen.
The above description is only of the preferred embodiments of the present invention; the scope of the invention is not limited in this respect. Any person skilled in the art, within the technical scope of the present disclosure, may apply to the present invention, and the technical solution and the improvement thereof are all covered by the protection scope of the present invention.
Claims (14)
1. A face skin detection method, comprising:
controlling a first image acquisition component to acquire a full-face image;
identifying skin problems according to the full-face image and identifying areas;
and prompting to acquire a local image of the identification area where the skin problem is located by using the second image acquisition component, and acquiring the severity and/or score of the identification area in the corresponding dimension of the skin problem based on the acquired local image.
2. The facial skin detection method according to claim 1, wherein controlling the first image acquisition component to acquire the full-face image comprises:
when the whole face is detected to be in the image pickup area of the first image acquisition component, controlling to start white light to take full face to acquire full face image pickup.
3. The face skin detection method according to claim 1, wherein the skin problem is identified and the region is identified based on the full-face image, specifically comprising:
and identifying skin problems in the full-face image by using the trained convolutional neural network model, positioning image coordinates of the skin problems, and identifying corresponding position areas of the full-face image.
4. The facial skin detection method according to claim 1, wherein prompting the use of the second image acquisition component to acquire a partial image of the identified region where the skin problem is located, comprises:
prompting the use of a second image acquisition component to acquire preset partial images of the identification area where each skin problem is located under natural light, UV light or polarized light; the preset sheet is larger than 1 sheet.
5. The method for detecting facial skin according to claim 4, wherein the prompting uses the second image acquisition component to acquire the preset partial images of the identification area where each skin problem is located under natural light, UV light or polarized light, respectively, specifically comprising:
s501, prompting a user to collect an image of an identification area where a certain skin problem is located by using a second image collection component under natural light, UV light or polarized light, judging whether the photographed image is clear or not, and repeating the step S501 if the photographed image is not clear; if clear, go to step S502;
s502, prompting a user to shoot a next image of the identification area under the same light source or different light sources; and repeats step S501;
s503, until the number of clear images in the area reaches a preset value;
s504, repeating S501-S503 until all the identification areas with skin problems acquire the preset partial images.
6. The facial skin detection method according to claim 1, further comprising, prior to controlling said first image acquisition component to acquire said full-face image:
detecting the opening state of the second image acquisition component, and controlling to enter the step of acquiring the full-face image by the first image acquisition component if the second image acquisition component is not opened; and if the method is started, prompting the second image acquisition component to acquire partial images of the divided face areas, and acquiring the severity and/or score of each face area in the corresponding dimension of the skin problem based on the acquired partial images.
7. The facial skin detection method according to claim 6, wherein prompting the use of the second image acquisition component to acquire a partial image for each divided facial region, comprises:
prompting the use of a second image acquisition component to acquire preset partial images of each divided face area under natural light, UV light or polarized light; the preset sheet is larger than 1 sheet.
8. The facial skin detection method according to claim 7, wherein prompting to use the second image acquisition component to acquire the preset partial images for the divided facial regions respectively under natural light, UV light or polarized light, comprises:
s801, prompting a user to collect images of a certain divided face area by using a second image collection assembly under natural light, UV light or polarized light, judging whether the photographed images are clear or not, and repeating the step S801 if the photographed images are not clear; if clear, go to step S802;
s802, prompting a user to shoot a next image of the face area under the same light source or different light sources; and repeats step S801;
s803, until the number of clear images in the area reaches a preset value;
s804, repeating S801-S803 until all the divided face areas acquire a preset partial image.
9. The face skin detection method of claim 6, wherein the face region comprises: forehead, left cheek, right cheek, nose and chin.
10. The facial skin detection method according to claim 1, wherein said skin problem comprises: at least one of texture, pores, acne, sensitivity, stain, blackhead or grease; each skin problem corresponds to a dimension.
11. The facial skin detection method according to claim 1, wherein said severity comprises: severe, moderate or mild.
12. The facial skin detection method according to claim 11, wherein said score is obtained based on severity and corresponding confidence, in particular as follows:
wherein x represents the confidence; f (x) represents a score.
13. The facial skin detection device is characterized by comprising a first image acquisition component, a cosmetic mirror and a second image acquisition component; the cosmetic mirror and the first image acquisition component and the second image acquisition component respectively perform data interaction; the first image acquisition component and the makeup mirror are arranged separately, or the first image acquisition component is arranged on the makeup mirror; the cosmetic mirror is used for performing the steps of the facial skin detection method as claimed in any one of claims 1 to 12.
14. The facial skin detection device is characterized by comprising a first image acquisition component, a cosmetic mirror, a second image acquisition component and an external terminal device; the cosmetic mirror, the first image acquisition assembly, the second image acquisition assembly and the external terminal equipment respectively conduct data interaction; the first image acquisition component and the makeup mirror are arranged separately, or the first image acquisition component is arranged on the makeup mirror; the external terminal device is configured to perform the steps of the facial skin detection method according to any one of claims 1 to 12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210998003.3A CN117617899A (en) | 2022-08-19 | 2022-08-19 | Face skin detection method and detection device |
| PCT/CN2023/108738 WO2024037287A1 (en) | 2022-08-19 | 2023-07-21 | Facial skin evaluation method and evaluation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210998003.3A CN117617899A (en) | 2022-08-19 | 2022-08-19 | Face skin detection method and detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117617899A true CN117617899A (en) | 2024-03-01 |
Family
ID=89940663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210998003.3A Pending CN117617899A (en) | 2022-08-19 | 2022-08-19 | Face skin detection method and detection device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117617899A (en) |
| WO (1) | WO2024037287A1 (en) |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064438A (en) * | 2017-06-09 | 2018-12-21 | 丽宝大数据股份有限公司 | skin condition detection method, electronic device and skin condition detection system |
| CN108399364A (en) * | 2018-01-29 | 2018-08-14 | 杭州美界科技有限公司 | A kind of face state appraisal procedure of major-minor camera setting |
| CN109064465A (en) * | 2018-08-13 | 2018-12-21 | 上海试美网络科技有限公司 | It is a kind of that labeling method is merged with the skin characteristic of natural light based on UV light |
| CN110378304B (en) * | 2019-07-24 | 2021-11-02 | 厦门美图之家科技有限公司 | Skin state detection method, device, equipment and storage medium |
| EP3772326A1 (en) * | 2019-08-06 | 2021-02-10 | Dermavision Solutions, Sl | A dermatoscopy device and a method for checking skin lesions |
| WO2021107677A1 (en) * | 2019-11-29 | 2021-06-03 | 문명일 | Facial skin diagnosis device and facial skin diagnosis method using same |
| KR20210075673A (en) * | 2019-12-13 | 2021-06-23 | 삼성전자주식회사 | Electronic device for measuring a skin state of a user and method of operating the same |
| CN111543943A (en) * | 2020-04-08 | 2020-08-18 | 深圳市视泰奇科技有限公司 | Face detection method |
| CN212346505U (en) * | 2020-05-26 | 2021-01-15 | 成都端丽医学科技有限公司 | Five-spectrum skin detector with 3D model reconstruction function |
| KR102458615B1 (en) * | 2020-12-03 | 2022-10-28 | 주식회사 베이바이오텍 | Skin condition measuring apparatus, skin condition measring system and method thereof |
| KR102413404B1 (en) * | 2021-01-12 | 2022-06-27 | 주식회사 룰루랩 | skin condition analyzing and skin disease diagnosis device |
| CN113159227A (en) * | 2021-05-18 | 2021-07-23 | 中国医学科学院皮肤病医院(中国医学科学院皮肤病研究所) | Acne image recognition method, system and device based on neural network |
| KR102314167B1 (en) * | 2021-06-25 | 2021-10-18 | 주식회사 우분트디자인 | Method of curating beauty care products by analyzing user's facial contour and skin type |
-
2022
- 2022-08-19 CN CN202210998003.3A patent/CN117617899A/en active Pending
-
2023
- 2023-07-21 WO PCT/CN2023/108738 patent/WO2024037287A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024037287A9 (en) | 2024-04-11 |
| WO2024037287A1 (en) | 2024-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10617301B2 (en) | Information processing device and information processing method | |
| US20220237811A1 (en) | Method for Testing Skin Texture, Method for Classifying Skin Texture and Device for Testing Skin Texture | |
| CN106056064B (en) | A kind of face identification method and face identification device | |
| US11579904B2 (en) | Learning data collection device, learning data collection system, and learning data collection method | |
| CN110235169B (en) | Cosmetic evaluation system and operation method thereof | |
| US20140275948A1 (en) | Information terminal device | |
| JP6799525B2 (en) | Biological information analyzer and hand skin analysis method | |
| CN111597938B (en) | Living body detection and model training method and device | |
| CN109948476B (en) | Human face skin detection system based on computer vision and implementation method thereof | |
| KR20110094037A (en) | Video infrared retinal image scanner | |
| CN103839054A (en) | Multi-functional mobile intelligent terminal sensor supporting iris recognition | |
| CN109427075A (en) | Biological information analytical equipment and its eye shadow analysis method | |
| CN102479322A (en) | System, apparatus and method for analyzing facial defect by facial image with angle | |
| CN109427078A (en) | Biological information analytical equipment and its lip adornment analysis method | |
| RU2556417C2 (en) | Detecting body movements using digital colour rear projection | |
| GB2598016A (en) | Biometric authentication apparatus and biometric authentication method | |
| KR20220068330A (en) | User personalized recommendation method based on skin diagnosis and appatratus thereof | |
| JP2009000410A (en) | Image processor and image processing method | |
| CN111767756A (en) | Method for automatically detecting facial flaws | |
| CN113143193A (en) | Intelligent vision testing method, device and system | |
| CN112668539A (en) | Biological characteristic acquisition and identification system and method, terminal equipment and storage medium | |
| CN117617899A (en) | Face skin detection method and detection device | |
| CN207586946U (en) | Alternative light source intelligent starting and anti-fake active biological characteristic shape of face identification device | |
| JP2017023474A (en) | Skin pore analysis apparatus, skin pore analysis method and program for use in device | |
| CN111210438A (en) | Mirror |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |