CN114399811A - Adjusting method, adjusting device, intelligent fitting mirror system and medium - Google Patents
Adjusting method, adjusting device, intelligent fitting mirror system and medium Download PDFInfo
- Publication number
- CN114399811A CN114399811A CN202111551990.4A CN202111551990A CN114399811A CN 114399811 A CN114399811 A CN 114399811A CN 202111551990 A CN202111551990 A CN 202111551990A CN 114399811 A CN114399811 A CN 114399811A
- Authority
- CN
- China
- Prior art keywords
- target object
- mirror surface
- adjusting
- acquiring
- human body
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B15/00—Special procedures for taking photographs; Apparatus therefor
- G03B15/02—Illuminating scene
- G03B15/03—Combinations of cameras with lighting apparatus; Flash units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention provides an adjusting method, an adjusting device, an intelligent fitting mirror system and a medium. The adjusting method is used for adjusting an intelligent fitting mirror system, the intelligent fitting mirror system comprises a camera, a mirror surface, a motor and a light supplementing lamp, and the adjusting method comprises the following steps: acquiring an image of a target object shot by the camera and extracting human key points in the image; acquiring a face area and a human body real proportion of the target object based on the human body key points; performing skin color recognition based on the facial region of the target object; adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification; acquiring an optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object; adjusting the mirror surface to the optimal mirror surface angle using the motor. The method can improve the fitting look and feel and the fitting experience of the target object.
Description
Technical Field
The invention relates to an adjusting method, in particular to an intelligent fitting mirror adjusting method, an adjusting device, an intelligent fitting mirror system and a medium.
Background
In the current sale process of off-line physical stores, in order to provide real fitting effect, the traditional fitting mirror is usually required to be used for displaying the fitting effect. The body proportion and the face skin color of the target client are different, so that the angle of the fitting mirror needs to be adjusted manually, but the manual adjustment process has the problems of low efficiency and difficulty in selecting the optimal mirror face angle, so that the whole fitting experience is influenced.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide an adjusting method, an adjusting device, an intelligent fitting mirror system and a medium, which are used to solve the problems of low efficiency of manual adjusting process, difficulty in selecting an optimal mirror angle and unreasonable color light ratio in the prior art.
In order to achieve the above and other related objects, a first aspect of the present invention provides an adjusting method for adjusting an intelligent fitting mirror system, where the intelligent fitting mirror system includes a camera, a mirror surface, a motor and a fill-in light, where the motor is configured to drive the mirror surface to rotate, and the adjusting method includes: acquiring an image of a target object shot by the camera and extracting human key points in the image; acquiring a face area and a human body real proportion of the target object based on the human body key points; performing skin color recognition based on the facial region of the target object; adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification; acquiring an optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object; adjusting the mirror surface to the optimal mirror surface angle using the motor.
In an embodiment of the first aspect, the method for obtaining the real proportions of the face region and the human body of the target object based on the human body key points includes: acquiring pixel coordinates of the human body key points; acquiring the on-picture sizes of the upper body and the lower body of the target object based on the pixel coordinates; acquiring a human body true scale of the target object based on-image sizes of an upper body and a lower body of the target object.
In an embodiment of the first aspect, the method for obtaining the on-diagram sizes of the upper body and the lower body of the target object based on the pixel coordinates includes: acquiring the on-picture size of the upper body of the target object based on the pixel coordinates of the head vertex and the waist midpoint; and acquiring the on-picture size of the lower half of the target object based on the pixel coordinates of the waist center point and the two heel center points.
In an embodiment of the first aspect, the method further includes: acquiring the current dressing information of the target object according to the image; and acquiring and displaying a recommended dressing product based on the current dressing information of the human body.
In an embodiment of the first aspect, a method for performing skin color identification based on a facial region of the target object includes: acquiring color distribution information of a face region of the target object; acquiring a dominant color of a face region of the target object based on the color distribution information.
In an embodiment of the first aspect, the method for obtaining the facial region of the target object based on the human body key points further includes: the face region of the target object is acquired based on the key point positions of the nose, the eyes, and the ears.
A second aspect of the present invention provides an adjusting device, configured to adjust an intelligent fitting mirror system, where the intelligent fitting mirror system includes a camera, a mirror surface, a motor, and a light supplement lamp, where the motor is configured to drive the mirror surface to rotate, and the adjusting device includes: the image acquisition module is used for acquiring an image of a target object shot by the camera; the key point extraction module is used for extracting human body key points in the image; the key point processing module is used for acquiring the face area and the real human body proportion of the target object based on the human body key points; a skin color identification module for performing skin color identification based on the face region of the target object; the color light adjusting module is used for adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification; the angle acquisition module is used for acquiring the optimal mirror surface angle of the mirror surface relative to the target object based on the human body real proportion and the target display proportion of the target object; and the mirror surface adjusting module is used for adjusting the mirror surface to the optimal mirror surface angle by utilizing the motor.
A third aspect of the present invention provides an intelligent fitting mirror system, which includes a camera, a mirror surface, a motor, a light supplement lamp, and a controller, wherein: the motor is used for driving the mirror surface to rotate; the controller is in communication connection with the camera, the mirror surface, the motor and the light supplement lamp, and is used for adjusting the mirror surface by adopting the adjusting method of any one of the first aspect.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the adjustment method of any one of the first aspects.
As described above, the adjusting method, the adjusting device, the intelligent fitting mirror system and the medium of the present invention have the following advantageous effects:
the adjusting method comprises the steps of obtaining an image of a target object shot by the camera and extracting key points of a human body in the image; acquiring a face area and a human body real proportion of the target object based on the human body key points; performing skin color recognition based on the facial region of the target object; adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification; acquiring an optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object; adjusting the mirror surface to the optimal mirror surface angle using the motor. The adjusting method can obtain the optimal mirror surface angle and different skin color recognition results corresponding to different human body real proportions according to different human body real proportions and different human body facial skin colors, the light supplementing lamp is adjusted by adjusting the mirror surface to the optimal mirror surface angle and according to the skin color recognition results, the fitting look of a target object can be improved, in addition, the adjusting efficiency can be improved by automatically adjusting the fitting mirror, and the whole fitting experience is further improved.
Drawings
Fig. 1A is a schematic structural diagram of an intelligent fitting mirror system according to an embodiment of the present invention.
FIG. 1B is a flow chart illustrating an exemplary embodiment of a tuning method of the present invention.
Fig. 2 is a flowchart illustrating a method for obtaining a real ratio of the facial region and the human body of the target object based on the human body key points according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating an implementation method for obtaining the on-diagram dimensions of the upper body and the lower body of the target object based on the pixel coordinates according to an embodiment of the present invention.
FIG. 4 is a flow chart of an embodiment of the tuning method of the present invention.
Fig. 5 is a flowchart illustrating a method for skin color identification based on the facial region of the target object according to an embodiment of the present invention.
FIG. 6 is a flow chart of an embodiment of the tuning method of the present invention.
FIG. 7 is a flow chart of an embodiment of the tuning method of the present invention.
Fig. 8 is a schematic diagram of an optical path of the adjusting method according to an embodiment of the invention.
Fig. 9 is a schematic structural diagram of an adjusting device according to an embodiment of the invention.
Description of the element reference numerals
900 adjusting device
910 image acquisition module
920 key point extraction module
930 key point processing module
940 skin color identification module
950 color light adjusting module
960 angle acquisition module
970 mirror adjusting module
S11-S16 steps
S21-S23 steps
S31-S32 steps
S41-S42 steps
S51-S52 steps
S61-S62 steps
S71-S78 steps
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
In the existing adjusting method, the fitting look and feel of a target group are improved by manually adjusting fitting mirrors and manually supplementing light according to the body and skin color characteristics and facial skin color characteristics of different target clients, but the problems of low efficiency, difficulty in selecting an optimal mirror surface angle and unreasonable color light proportion exist in the manual process, so that the whole fitting experience is influenced.
In order to solve the above problems, the present invention provides an adjusting method for adjusting an intelligent fitting mirror system, where the intelligent fitting mirror system includes a camera, a mirror surface, a motor and a light supplement lamp, where the motor is used to drive the mirror surface to rotate, and the adjusting method includes: acquiring an image of a target object shot by the camera and extracting human key points in the image; acquiring a face area and a human body real proportion of the target object based on the human body key points; performing skin color recognition based on the facial region of the target object; adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification; acquiring an optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object; adjusting the mirror surface to the optimal mirror surface angle using the motor. According to the method, the optimal mirror surface angle and different skin color recognition results corresponding to different human body real proportions can be obtained according to different human body real proportions and different human body facial skin colors, the fitting look of the target object can be improved by adjusting the mirror surface to the optimal mirror surface angle and adjusting the light supplementing lamp according to the skin color recognition results, in addition, the adjustment efficiency can be improved by automatically adjusting the fitting mirror, and further the whole fitting experience is improved.
In an embodiment of the present invention, the adjusting method is used for adjusting an intelligent fitting mirror system. For example, referring to fig. 1A, the intelligent fitting mirror system includes a camera, a mirror surface, a motor, and a fill-in light, wherein the motor is used for driving the mirror surface to rotate. Referring to fig. 1B, the adjusting method includes:
and S11, acquiring the image of the target object shot by the camera and extracting the key points of the human body in the image. Wherein the human body key points may include: nose, neck, right shoulder, right elbow, right wrist, left shoulder, left elbow, left wrist, lumbar, right hip, right knee, right ankle, left hip, left knee, left ankle, right eye, left eye, right ear, left ear, crown of head, left thumb, left pinky, left heel, right thumb, right pinky, and right heel. Optionally, in this embodiment, the human body key points in the image may be extracted through a Mask-R-CNN algorithm, and the training samples of the Mask-R-CNN algorithm may be a large number of multi-posture human body images.
And S12, acquiring the face area and the real human body proportion of the target object based on the human body key points. Wherein the face region may be determined by a nose, eyes, ears among the key points of the human body. Optionally, in this embodiment, the pixel coordinates of the human body key points may be obtained first, then the on-image sizes of the upper half and the lower half of the human body are obtained based on the pixel coordinates of the human body key points, and finally the real human body proportion is obtained by combining with an actual distance measurement function of a camera.
S13, performing skin color recognition based on the face area of the target object. Optionally, the present embodiment may obtain the main color of the facial region through a statistical algorithm to complete the skin color identification.
And S14, adjusting the color light proportion of the light supplement lamp according to the result of the skin color identification. The color light ratio can be a ratio of white light to yellow light.
And S15, acquiring the optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object. The target display proportion may be a human body proportion displayed by the target object in a mirror surface, and the selection range of the optimal mirror surface angle may be a mirror surface angle range corresponding to the target display proportion near a human body golden ratio of 0.618.
And S16, adjusting the mirror surface to the optimal mirror surface angle by using the motor.
Note that the above reference numerals S11 to S16 are used only to identify different steps, and are not used to limit the execution order of the steps. In practical application, the execution sequence of these steps can be adjusted according to specific requirements. For example, steps S13 and S14 may be performed first, and steps S12 and S15 may be performed second, or steps S12 and S15 may be performed first, and steps S13 and S14 may be performed second, which is not limited in the present invention.
As can be seen from the above description, in the adjusting method of this embodiment, the key points of the human body are extracted to obtain the face area and the real human body ratio of the target object, then the skin color is identified based on the face area, the optimal mirror surface angle of the target object is obtained based on the real human body ratio and the target display ratio, and finally the color ratio of the fill light is adjusted according to the skin color identification result and the mirror surface is adjusted to the optimal mirror surface angle by the motor. The adjusting method can obtain the optimal mirror surface angle and different skin color recognition results corresponding to different human body real proportions according to different human body real proportions and different human body facial skin colors, the fitting look of the target object can be improved by adjusting the mirror surface to the optimal mirror surface angle and adjusting the light supplementing lamp according to the skin color recognition results, in addition, the adjusting efficiency is improved by automatically adjusting the fitting mirror, and the whole fitting experience is further improved.
Referring to fig. 2, in an embodiment of the present invention, a method for obtaining a face region and a real human scale of the target object based on the human key points includes:
and S21, acquiring the pixel coordinates of the human key points.
S22, acquiring the on-image sizes of the upper and lower bodies of the target object based on the pixel coordinates. Alternatively, the distance between the head vertex and the waist midpoint in the human body key points may be obtained as the upper body on-image size of the target object, and the distance between the waist midpoint and the two heel center points in the human body key points may be obtained as the lower body on-image size of the target object.
And S23, acquiring the real human body proportion of the target object based on the on-picture sizes of the upper half body and the lower half body of the target object. Optionally, the present embodiment may obtain the real human body ratio of the target object by combining the upper-half body size and the lower-half body size of the target object through the distance measurement and the actual object length functions in the binocular depth camera.
As can be seen from the above description, the method for acquiring the facial region and the human true proportion of the target object based on the human key points according to the embodiment can improve the accuracy of the acquired human true proportion by acquiring the pixel coordinates of the human key points, then acquiring the on-image sizes of the upper body and the lower body of the target object based on the pixel coordinates, and finally acquiring the human true proportion of the target object based on the on-image sizes of the upper body and the lower body of the target object.
Referring to fig. 3, in an embodiment of the present invention, the method for obtaining the on-image sizes of the upper body and the lower body of the target object based on the pixel coordinates includes:
and S31, acquiring the on-map size of the upper body of the target object based on the pixel coordinates of the head vertex and the waist midpoint.
And S32, acquiring the on-picture size of the lower half of the target object based on the pixel coordinates of the waist center point and the heel center points.
Referring to fig. 4, in an embodiment of the present invention, the adjusting method further includes:
and S41, acquiring the current dressing information of the target object according to the image. Wherein the current dressing information may include clothing and apparel information.
And S42, acquiring and displaying a recommended dressing product based on the current dressing information of the human body. Optionally, the present embodiment may display the recommended dressing product through a liquid crystal highlighting module behind the fitting mirror.
As can be seen from the above description, the adjusting method according to this embodiment can provide associated clothing products by obtaining the current clothing information of the target object according to the image, and obtaining and displaying recommended clothing products based on the current clothing information of the human body, so as to improve the fitting experience of the target object.
Referring to fig. 5, in an embodiment of the present invention, a method for performing skin color identification based on a facial region of a target object includes:
s51, acquiring color distribution information of the face region of the target object. Alternatively, the present embodiment may acquire the color distribution information of the face region of the target object by a statistical algorithm.
S52, a dominant color of the face region of the target object is acquired based on the color distribution information. Alternatively, the present embodiment may select a color having a color distribution ratio of more than eighty percent as the primary color of the face area of the target object.
As can be seen from the above description, the implementation method for identifying skin color based on the face area of the target object according to this embodiment can improve the accuracy of the result of identifying skin color of the face area by first obtaining the color distribution information of the face area of the target object and then obtaining the dominant color of the face area of the target object based on the color distribution information.
Referring to fig. 6, in an embodiment of the present invention, the adjusting method further includes:
s61, acquiring current dressing information and personal information of the target object, wherein the personal information comprises gender and/or age group;
and S62, acquiring and displaying the recommended dressing product based on the current dressing information and the personal information of the target object.
As can be seen from the above description, the adjusting method according to this embodiment can improve the accuracy of the recommended associated goods and implement personalized goods recommendation by acquiring the current dressing information and the personal information of the target object, and acquiring and displaying the recommended dressing product based on the current dressing information and the personal information of the target object.
Referring to fig. 7, in an embodiment of the present invention, the adjusting method includes:
and S71, acquiring the image of the target object shot by the camera and extracting the key points of the human body in the image. Optionally, in this embodiment, skeleton points, which are key points of the human body of the image, may be extracted from the image through Mask-R-CNN, OpenPose, and OmniPose algorithms.
And S72, acquiring the face area and the real human body proportion of the target object based on the human body key points. Alternatively, the embodiment may obtain the marked pixel distances of the upper body and the lower body by first selecting the head vertex and the waist midpoint as the upper body distance punctuation points, and selecting the waist midpoint and the center points of the two heels as the lower body distance punctuation points, and then obtaining the actual heights of the upper body and the lower body and obtaining the ratio of the upper body and the lower body by combining the functions of distance measurement in the camera and the actual length of the object. The face region may be determined according to the positions of key points of the nose, eyes and ears.
S73, performing skin color recognition based on the face area of the target object. Alternatively, the present embodiment may count the color distribution of the face area of the target object by an AI algorithm, and take the color of which the percentage is more than eighty percent as the face color of the fitting person.
And S74, adjusting the color light proportion of the light supplement lamp according to the result of the skin color identification. The color light ratio can be a ratio of white light to yellow light.
And S75, acquiring the optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object. Alternatively, referring to fig. 8, in a schematic diagram of an optical path,
for the real human body scale, the target display scale may be a body scale expected to be observed by the target object
Wherein
Based on the optical path diagram shown in FIG. 8, the optimal mirror angle θ in this embodiment is
Wherein θ is the optimal mirror angle. The target display scale
The golden ratio of the human body can be set to be about 0.618 according to the scene requirements, and the invention is not limited to this. L1 represents the on-picture size of the upper body of the target object, and L2 represents the on-picture size of the lower body of the target object.
And S76, adjusting the mirror surface to the optimal mirror surface angle by using the motor.
S77, acquiring the current dressing information and the personal information of the target object, wherein the personal information comprises gender and/or age group. Alternatively, the present embodiment may obtain the current dressing information and the personal information of the target object through an AI recognition algorithm.
And S78, acquiring and displaying the recommended dressing product based on the current dressing information and the personal information of the target object. Optionally, in this embodiment, the associated product may be recommended by a recommendation algorithm, and displayed by the liquid crystal highlight module behind the mirror surface.
According to the above description, the adjusting method in this embodiment includes the processes of acquiring key points of a human body, an optimal mirror surface angle, dressing information of a current target object, and personal information, and adjusting the mirror surface to the optimal mirror surface angle, adjusting a light supplement lamp, and pushing related products. In addition, the mirror surface is adjusted to
The target object can observe the expected body proportion through the fitting mirror, and the fitting effect is further improved.
In an embodiment of the present invention, an intelligent fitting mirror system is provided, which includes a camera, a mirror surface, a motor, a light supplement lamp, and a controller, wherein: the motor is used for driving the mirror surface to rotate; the controller is in communication connection with the camera, the mirror surface, the motor and the light supplement lamp, and is used for adjusting the mirror surface by using the adjusting method shown in fig. 1B or fig. 7.
In an embodiment of the present invention, with reference to fig. 9, in this embodiment, the adjusting device 900 is configured to adjust an intelligent fitting mirror system, where the intelligent fitting mirror system includes a camera, a mirror surface, a motor, and a light supplement lamp, where the motor is configured to drive the mirror surface to rotate, and the adjusting device 900 includes:
an image obtaining module 910, configured to obtain an image of a target object captured by the camera;
a key point extracting module 920, configured to extract a human key point in the image;
a key point processing module 930, configured to obtain a facial region and a human true scale of the target object based on the human key point;
a skin color identification module 940 for performing skin color identification based on the facial region of the target object;
the color light adjusting module 950 is configured to adjust a color light ratio of the light supplement lamp according to a result of skin color identification;
an angle obtaining module 960, configured to obtain an optimal mirror angle of the mirror with respect to the target object based on the human body true scale and the target display scale of the target object;
a mirror adjusting module 970, configured to adjust the mirror to the optimal mirror angle by using the motor.
It should be noted that, the corresponding modules in the adjusting apparatus 900 correspond to the steps S11 through S16 in the adjusting method shown in fig. 1B one by one, and are not described herein for saving the description.
According to the above description, the adjusting device can obtain the optimal mirror surface angle corresponding to different human body real proportions and different skin color recognition results according to different human body real proportions and different human body facial skin colors, and the fitting look and feel of the target object can be improved by adjusting the mirror surface to the optimal mirror surface angle and adjusting the light supplement lamp according to the skin color recognition results. In addition, the adjustment efficiency can be improved through the automatically-adjusted fitting mirror, so that the overall fitting experience is improved.
Based on the above description of the adjustment method, the present invention also provides a computer-readable storage medium having stored thereon a computer program. Which computer program, when being executed by a processor, carries out the adaptation method shown in fig. 1B or fig. 7.
The protection scope of the control method of the present invention is not limited to the execution sequence of the steps illustrated in this embodiment, and all the solutions implemented by the steps addition, subtraction, and step replacement in the prior art according to the principle of the present invention are included in the protection scope of the present invention.
In summary, the adjusting method, the adjusting device, the intelligent fitting mirror system and the medium of the invention improve fitting look and fitting experience of the target object. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (9)
1. An adjusting method is characterized by being used for adjusting an intelligent fitting mirror system, wherein the intelligent fitting mirror system comprises a camera, a mirror surface, a motor and a light supplementing lamp, the motor is used for driving the mirror surface to rotate, and the adjusting method comprises the following steps:
acquiring an image of a target object shot by the camera and extracting human key points in the image;
acquiring a face area and a human body real proportion of the target object based on the human body key points;
performing skin color recognition based on the facial region of the target object;
adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification;
acquiring an optimal mirror surface angle of the mirror surface relative to the target object based on the human body real scale and the target display scale of the target object;
adjusting the mirror surface to the optimal mirror surface angle using the motor.
2. The adjusting method according to claim 1, wherein the implementation method for obtaining the real proportion of the face area and the human body of the target object based on the human body key points comprises the following steps:
acquiring pixel coordinates of the human body key points;
acquiring the on-picture sizes of the upper body and the lower body of the target object based on the pixel coordinates;
acquiring a human body true scale of the target object based on-image sizes of an upper body and a lower body of the target object.
3. The adjustment method according to claim 2, wherein the implementation method for acquiring the on-image sizes of the upper body and the lower body of the target object based on the pixel coordinates comprises:
acquiring the on-picture size of the upper body of the target object based on the pixel coordinates of the head vertex and the waist midpoint;
and acquiring the on-picture size of the lower half of the target object based on the pixel coordinates of the waist center point and the two heel center points.
4. The adjustment method according to claim 1, further comprising:
acquiring the current dressing information of the target object according to the image;
and acquiring and displaying a recommended dressing product based on the current dressing information of the human body.
5. The adjustment method according to claim 1, wherein the implementation of skin tone recognition based on the target object's facial region comprises:
acquiring color distribution information of a face region of the target object;
acquiring a dominant color of a face region of the target object based on the color distribution information.
6. The adjustment method according to claim 1, wherein the implementation method for obtaining the face region of the target object based on the human keypoints further comprises:
the face region of the target object is acquired based on the key point positions of the nose, the eyes, and the ears.
7. The utility model provides an adjusting device, its characterized in that for adjusting an intelligent fitting mirror system, intelligent fitting mirror system includes camera, mirror surface, motor and light filling lamp, wherein, the motor is used for driving the mirror surface rotates, adjusting device includes:
the image acquisition module is used for acquiring an image of a target object shot by the camera;
the key point extraction module is used for extracting human body key points in the image;
the key point processing module is used for acquiring the face area and the real human body proportion of the target object based on the human body key points;
a skin color identification module for performing skin color identification based on the face region of the target object;
the color light adjusting module is used for adjusting the color light proportion of the light supplementing lamp according to the result of skin color identification;
the angle acquisition module is used for acquiring the optimal mirror surface angle of the mirror surface relative to the target object based on the human body real proportion and the target display proportion of the target object;
and the mirror surface adjusting module is used for adjusting the mirror surface to the optimal mirror surface angle by utilizing the motor.
8. The utility model provides an intelligence fitting mirror system, its characterized in that, intelligence fitting mirror system includes camera, mirror surface, motor, light filling lamp and controller, wherein:
the motor is used for driving the mirror surface to rotate;
the controller is in communication connection with the camera, the mirror surface, the motor and the supplementary lighting lamp and is used for adjusting the mirror surface by adopting the adjusting method of any one of claims 1 to 6.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the adaptation method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111551990.4A CN114399811A (en) | 2021-12-17 | 2021-12-17 | Adjusting method, adjusting device, intelligent fitting mirror system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111551990.4A CN114399811A (en) | 2021-12-17 | 2021-12-17 | Adjusting method, adjusting device, intelligent fitting mirror system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114399811A true CN114399811A (en) | 2022-04-26 |
Family
ID=81227098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111551990.4A Pending CN114399811A (en) | 2021-12-17 | 2021-12-17 | Adjusting method, adjusting device, intelligent fitting mirror system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399811A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351540A (en) * | 2023-09-27 | 2024-01-05 | 东莞莱姆森科技建材有限公司 | Bathroom mirror integrated with LED and head action recognition |
-
2021
- 2021-12-17 CN CN202111551990.4A patent/CN114399811A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351540A (en) * | 2023-09-27 | 2024-01-05 | 东莞莱姆森科技建材有限公司 | Bathroom mirror integrated with LED and head action recognition |
| CN117351540B (en) * | 2023-09-27 | 2024-04-02 | 东莞莱姆森科技建材有限公司 | Bathroom mirror integrated with LED and head action recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11450075B2 (en) | Virtually trying cloths on realistic body model of user | |
| CN105678232B (en) | A kind of face picture feature extraction and control methods based on deep learning | |
| US9779512B2 (en) | Automatic generation of virtual materials from real-world materials | |
| CN105354876B (en) | A kind of real-time volume fitting method based on mobile terminal | |
| CN109377557B (en) | Real-time three-dimensional face reconstruction method based on single-frame face image | |
| CN102622613B (en) | Hair style design method based on eyes location and face recognition | |
| CN108537126B (en) | Face image processing method | |
| CN106920277A (en) | Simulation beauty and shaping effect visualizes the method and system of online scope of freedom carving | |
| CN106952221B (en) | Three-dimensional Beijing opera facial makeup automatic making-up method | |
| CN105913416A (en) | Method for automatically segmenting three-dimensional human face model area | |
| CN110363867A (en) | Virtual dress up system, method, equipment and medium | |
| CN103456010A (en) | Human face cartoon generation method based on feature point localization | |
| CN111325846B (en) | Expression base determination method, avatar driving method, device and medium | |
| CN111435433B (en) | Information processing device, information processing method, and storage medium | |
| CN109801380A (en) | A kind of method, apparatus of virtual fitting, storage medium and computer equipment | |
| US11069089B2 (en) | Information processing apparatus, information processing method, and computer program product | |
| JP2010507854A (en) | Method and apparatus for virtual simulation of video image sequence | |
| CN107077751A (en) | The virtual try-in method of contact lenses, device and the computer program for implementing this method | |
| KR101720016B1 (en) | A clothing fitting system with a mirror display by using salient points and the method thereof | |
| CN108629248A (en) | A kind of method and apparatus for realizing augmented reality | |
| CN108805090A (en) | A kind of virtual examination cosmetic method based on Plane Gridding Model | |
| CN109426767A (en) | Informer describes guidance device and its method | |
| CN104157001A (en) | Method and device for drawing head caricature | |
| CN108305321B (en) | Three-dimensional human hand 3D skeleton model real-time reconstruction method and device based on binocular color imaging system | |
| WO2020104990A1 (en) | Virtually trying cloths & accessories on body model |
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 |