CN109165700B - Extrusion control method, device and system for beauty liquid - Google Patents
Extrusion control method, device and system for beauty liquid Download PDFInfo
- Publication number
- CN109165700B CN109165700B CN201811216797.3A CN201811216797A CN109165700B CN 109165700 B CN109165700 B CN 109165700B CN 201811216797 A CN201811216797 A CN 201811216797A CN 109165700 B CN109165700 B CN 109165700B
- Authority
- CN
- China
- Prior art keywords
- initial image
- extrusion
- feature
- server
- cosmetic
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The application relates to a method, a device and a system for controlling extrusion of a cosmetic liquid. The method comprises the following steps: acquiring an initial image containing a specific part of a human body sent by a cosmetic device; inputting the processed initial image into a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information; sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data. By adopting the method, the technical effect of intelligently controlling the amount of the discharged cosmetic liquid can be realized, the diversified skin care requirements of users can be met, the users do not need to manually extrude various different cosmetic liquids, and the use convenience of the users is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a system, a computer device, and a storage medium for controlling squeezing of a cosmetic liquid.
Background
With the continuous development of society, people pay more and more attention to their own images, and on the other hand, with the progress of science and technology, more and more scientific and technical products can be applied to the purpose of managing or improving their own images; for example, some beauty equipment can automatically extrude a fixed amount of skin care liquid, and the technical effect of finishing the skin care liquid by one key is achieved.
Specifically, the extrusion amount of the cosmetic liquid can be preset by the cosmetic device, and when a user presses a key on the cosmetic device, the cosmetic liquid with the corresponding extrusion amount is extruded, namely, the extrusion amount of the cosmetic liquid is fixed every time and does not meet the personalized requirements of the user; in addition, the variety of the beauty lotion can be various, and if a user needs various beauty lotions at the same time, the user needs to press the corresponding key of the beauty equipment for many times, so that the steps are complicated, and the convenience of the user is not improved.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a system, a computer device and a storage medium for controlling squeezing of a cosmetic liquid, which can intelligently control the amount of the cosmetic liquid.
A method of controlling the extrusion of a cosmetic liquid, the method comprising:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information;
acquiring corresponding feature extrusion data according to the classification information;
sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the amount of the extruded cosmetic liquid according to the characteristic extrusion data.
In one embodiment, the acquiring the corresponding feature extrusion data according to the classification information includes:
generating a skin detection result according to the classification information;
and acquiring corresponding feature extrusion data according to the skin detection result.
A method of controlling the extrusion of a cosmetic liquid, the method comprising:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data.
In one embodiment, the specific part of the human body comprises human skin; the acquisition of an initial image containing a specific part of a human body comprises the following steps:
an initial image containing human skin is acquired by a camera.
In one embodiment, the cosmetic device is preset with a first mapping relation between feature extrusion data and a rotation stroke, and the control of the type and the quantity of the extruded cosmetic liquid according to the feature extrusion data comprises the following steps:
finding the corresponding rotation stroke according to the feature extrusion data and the first mapping relation;
and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
A device for controlling the extrusion of a cosmetic liquid, the method comprising:
the device comprises an initial image acquisition module, a display module and a display module, wherein the initial image acquisition module is used for acquiring an initial image which is sent by the beauty equipment and contains a specific part of a human body;
the classification information acquisition module is used for inputting the processed initial image into a preset trained machine learning model to acquire classification information;
the first feature extrusion data acquisition module is used for acquiring corresponding feature extrusion data according to the classification information;
the feature extrusion data sending module is used for sending the feature extrusion data to the beauty equipment; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
In one embodiment, the feature extrusion data acquisition module comprises:
the skin detection result generation submodule is used for generating a skin detection result according to the classification information;
and the feature extrusion data acquisition submodule is used for acquiring corresponding feature extrusion data according to the skin detection result.
An extrusion control device for a cosmetic liquid, the method comprising:
the initial image acquisition module is used for acquiring an initial image containing a specific part of a human body;
the second feature extrusion data acquisition module is used for sending the initial image to a server and acquiring feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
and the control module is used for controlling the type and the quantity of the extruded beauty fluid according to the characteristic extrusion data.
In one embodiment, the specific part of the human body comprises human skin; the initial image acquisition module comprises:
and the initial image acquisition submodule is used for acquiring an initial image containing human skin through the camera.
In one embodiment, the cosmetic device is preset with a first mapping of feature expression data to rotational stroke, and the control module comprises:
the rotation stroke searching submodule is used for searching a corresponding rotation stroke according to the feature extrusion data and the first mapping relation;
and the control submodule is used for controlling the extrusion motor to extrude the quantity of the one or more cosmetic liquids according to the rotation stroke.
The extrusion control system of the beauty fluid comprises a beauty device and a server, wherein the server is preset with a trained machine learning model; the system comprises:
the beauty equipment acquires an initial image containing a specific part of a human body;
the beauty equipment sends the initial image to a server;
the server inputs the processed initial image into the trained machine learning model to obtain classification information;
the server acquires corresponding feature extrusion data according to the classification information;
the server sends the feature extrusion data to the beauty equipment;
the cosmetic device controls the kind and amount of the extruded cosmetic liquid according to the feature extrusion data.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information;
acquiring corresponding feature extrusion data according to the classification information;
sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information;
acquiring corresponding feature extrusion data according to the classification information;
sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data.
The extrusion control method, the device, the system, the computer equipment and the storage medium of the beauty fluid acquire the initial image containing the specific part of the human body; sending the initial image to a server to obtain feature extrusion data output by the server; the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment; controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data; the technical effect of intelligently controlling the liquid outlet quantity of the cosmetic liquid can be realized, the diversified skin care requirements of users can be met, the users do not need to manually extrude various different cosmetic liquids, and the use convenience of the users is improved.
Drawings
Fig. 1 is a diagram of an application environment of a method for controlling extrusion of a cosmetic liquid according to an embodiment;
fig. 2 is a schematic flow chart of a method for controlling the extrusion of a cosmetic liquid according to an embodiment;
fig. 3 is a schematic flow chart of a method for controlling the extrusion of a cosmetic liquid according to an embodiment;
fig. 4 is a schematic flow chart of a cosmetic liquid extrusion control system according to an embodiment;
fig. 5 is a block diagram showing the structure of an extrusion control device for cosmetic liquid according to an embodiment;
fig. 6 is a block diagram showing the structure of an extrusion control device for cosmetic liquid according to an embodiment;
FIG. 7 is an internal block diagram of a computer device of an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The cosmetic liquid extrusion control method provided by the application can be applied to the application environment shown in fig. 1. Wherein the cosmetic device 102 communicates with the server 104 over a network. The server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a method for controlling extrusion of a cosmetic liquid is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
step S201, acquiring an initial image which is sent by a beauty device and contains a specific part of a human body;
in this embodiment, the server may include a PC (Personal Computer) server, a mainframe, a mini-machine, and a cloud server, and the type and number of the servers are not specifically limited in the embodiment of the present invention.
In a specific implementation, the server is connected to one or more beauty devices, and the server and the beauty devices may be connected in a wired or wireless manner, where the wired manner means that the server and the beauty devices are connected through a wired communication network formed by communication cables, and the wireless manner means that the server and the beauty devices are connected through a communication network such as the internet, an LTE (Long Term Evolution) network, and the like, and the specific connection manner of the server and the beauty devices is not limited in this embodiment.
It should be noted that the cosmetic device may be a device for storing and dispensing one or more cosmetic liquids, and in particular, the cosmetic device may include at least one dispensing motor and at least one liquid reservoir for storing a cosmetic liquid; namely, the beauty equipment can extrude a plurality of beauty liquids with preset quantity at the same time; for example, the cosmetic device may extrude 1mL of "hand cream" and 3mL of "eye cream" simultaneously.
Accordingly, the cosmetic device may be provided with one or more extrusion mechanisms, such as a nozzle mechanism, a pressing mechanism, etc., which is not limited by the present embodiment. Additionally, the cosmetic device may also include other electronic components that may be used to receive or transmit information; if control information is sent to the extrusion motor, controlling the quantity of the extruded beauty fluid; specifically, the electronic component may include a processor, a memory, a network connector, and the like, which is not limited in this embodiment.
In this embodiment, after the beauty equipment acquires an initial image containing a specific part of a human body through a camera, the beauty equipment can send the initial image to a server; the server may receive the initial image containing the specific part of the human body.
The specific part of the human body may include a human organ, such as human skin, etc., and it should be noted that the initial image may be an image including a part of the specific part of the human body; for example, the initial image may be an image including human face skin.
Step S202, inputting the processed initial image into a preset trained machine learning model to obtain classification information;
in specific implementation, the server may preset a trained machine learning model, and it should be noted that the machine learning model may be divided into a supervised learning model and an unsupervised learning model according to available data types; supervised learning models mainly include models for classification and for regression.
For example, the supervised learning model may include a Linear Classifier model (Linear Classifier), a Support Vector Machine (Support Vector Machine), a Naive Bayes model Classifier (Naive Bayes Classifier), a K-nearest neighbor model (K-nearest neighbor), a Decision Tree model (Decision Tree), a Linear Regression model (Linear Regression), and a Regression Tree model (Regression Tree);
the unsupervised learning model mainly comprises the following steps: data clustering models (K-means), data dimension reduction models (Principal Component Analysis). The method of the present embodiment may be applied to a supervised learning model.
Further, the machine learning model may be trained in the following manner, to obtain a trained machine learning model:
1. acquiring a sample image containing a specific part of a human body;
2. extracting a connected domain image in the sample image;
3. acquiring characteristic shape parameters of the connected domain image;
4. when the characteristic shape parameters meet preset conditions, determining the connected domain image as a human body characteristic image corresponding to a specific part of a human body;
5. and inputting the human body characteristic image into a machine learning model for training to obtain the trained machine learning model.
Specifically, after the server acquires the sample image of the specific part of the human body, the connected domain image of the sample image may be extracted, specifically, the sample image is subjected to grayscale conversion to obtain a grayscale image corresponding to the sample image, the grayscale image is binarized to obtain a binarized image, and finally, one or more connected domain images of the binarized image are further extracted.
After obtaining the connected domain image, the server may obtain a characteristic shape parameter of the connected domain image, where the characteristic shape parameter refers to a relevant parameter such as a shape, a size, or a proportion of the connected domain image.
For example, the characteristic shape parameter may include a connected domain area parameter, an inertia rate parameter, a convexity parameter, a roundness parameter, and the like, and may further include a ratio of two connected domain area parameters, which is not limited in this embodiment.
After the server obtains the characteristic shape parameters, whether the characteristic shape parameters meet preset conditions or not can be judged, when the characteristic shape parameters meet the preset conditions, the connected domain image corresponding to the characteristic shape parameters is determined to be a human body characteristic image, and it needs to be explained that the human body characteristic image is a processed initial image.
After the human body characteristic image is obtained, inputting the human body characteristic image into the machine learning model, and training the machine learning model; the human body characteristic image is used as a sample image, and the sample image is adopted to train the machine learning model to obtain the trained machine learning model.
The above manner of obtaining the human body feature image is only an example of the embodiment of the present invention, and the human body feature image of the sample image may also be obtained through the other manners; in another embodiment, a sample image of an RGB color mode may be converted into an image of an HSV color mode; then extracting at least one edge area image in the image of the HSV color mode; screening the edge area image to obtain a human body characteristic image; inputting the human body characteristic image into a machine learning model for training to obtain a trained machine learning model;
specifically, the step of extracting at least one edge region image in the image of the HSV color mode may include: filtering and binarizing the image in the HSV color mode to obtain a binary image; performing first filtering operation on the binary image to obtain a first filtering image; and carrying out edge detection on the first filtering image to obtain at least one edge area image.
Based on the above two ways of obtaining the human body feature image, those skilled in the art may also derive or associate other ways of obtaining the human body feature image similar to or the same as the concept of the present embodiment, and the present embodiment does not limit the ways of obtaining the human body feature image too much.
It should be noted that the sample image may be image data different from the initial image, which is mainly used for training the machine learning model, but the sample image may also include an image of a specific part of a human body.
After the trained machine learning model is obtained, the server can preset the trained machine learning model in a database on the server, when the initial image is received, the server can process the initial image to obtain a human body characteristic image, the server can call a program interface corresponding to the trained machine learning model, and the human body characteristic image is input into the trained machine learning model to obtain classification information; namely, the processed initial image is the human body characteristic image.
Step S203, acquiring corresponding feature extrusion data according to the classification information;
after the processed initial image is input to the trained machine learning model, the server may obtain the output classification information.
Further, acquiring corresponding feature extrusion data according to the classification information; it should be noted that the characteristic extrusion data may include extrusion amount data and/or cosmetic liquid type data; the extrusion amount data refers to the volume or weight of the cosmetic liquid; the cosmetic liquid type data refers to identification information of different types of cosmetic liquid.
In a specific application, the server may obtain a corresponding skin detection result according to the classification information, and obtain the extrusion amount data and/or the cosmetic liquid type data according to the skin detection result.
Step S204, sending the feature extrusion data to the beauty equipment; wherein the cosmetic device is used for controlling the type and the amount of the extruded cosmetic liquid according to the characteristic extrusion data.
Further, after the server acquires the feature extrusion data, the feature extrusion data is sent to the beauty equipment; namely, the extrusion amount data and/or the cosmetic liquid kind data are transmitted to the cosmetic apparatus.
According to the extrusion control method of the beauty fluid provided by the embodiment, an initial image containing a specific part of a human body and sent by the beauty equipment is obtained; inputting the processed initial image into a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information; sending the feature extrusion data to the cosmetic device; wherein the beauty device is used for controlling the type and the quantity of the extruded beauty liquid according to the characteristic extrusion data; the technical effect of intelligently controlling the liquid outlet quantity of the beauty fluid can be realized, the diversified skin care requirements of users are met, the users do not need to manually extrude various different beauty fluids, the using steps are simplified, and the using convenience of the users is improved.
In another embodiment, the step S203 includes: generating a skin detection result according to the classification information; and acquiring corresponding feature extrusion data according to the skin detection result.
Specifically, the server may have a plurality of mapping tables preset therein, for example, a certain mapping table may include a first mapping relationship between the classification information and the skin detection result; another mapping table may include a second mapping relationship between skin test results and feature extrusion data.
When the classification information is obtained, the server can query the first mapping relation to obtain a corresponding skin detection result, wherein the skin detection result can be a skin report of the user and record the skin condition of the user; and querying the second mapping relation according to the skin detection result to obtain corresponding feature extrusion data.
For example, when the human body feature image is a pore feature image, the classification information may include first type information, second type information, third type information, and the like.
The first type of information may refer to information that the number of pores is 20; the second category may refer to information that the number of pores is 50; the third category may refer to information that the number of pores is 80, and the classification information may be related information set by a person skilled in the art according to practical situations, which is not limited by the embodiment.
When the classification information is the third type information, namely the information with the number of pores of 80; according to the first mapping relationship between the classification information and the skin detection result, it is found that the skin detection result corresponding to the third type of information is "more in number", and then the server may find that the feature extrusion data is: "essence: 1mL "," emulsion cream: 3 mL' can accurately determine the liquid discharge quantity of various beauty liquids according to the skin of the user.
In one embodiment, as shown in fig. 3, a method for controlling the extrusion of a cosmetic liquid is provided, which is illustrated by applying the method to the cosmetic apparatus 102 in fig. 1, and comprises the following steps:
step S301, acquiring an initial image containing a specific part of a human body;
in this embodiment, the beauty device mainly includes a control component and a beauty liquid squeezing component, the control component mainly includes a processor, a memory, and the like, the control component also includes a single computer, this embodiment is not limited thereto, the beauty liquid squeezing component may include a squeezing motor, a liquid storage, and the like, and an operating system of the beauty device may include Android (Android), IOS, Windows Phone, Windows, and the like;
specifically, the beauty treatment apparatus may acquire an initial image containing a specific part of a human body; the specific part of the human body may include a human organ, such as human skin, etc., and it should be noted that the initial image may be an image including a part of the specific part of the human body; for example, the initial image may be an image containing human face skin.
Step S302, the initial image is sent to a server, and feature extrusion data output by the server are obtained; the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
in specific application, after the initial image is collected by the beauty equipment, the initial image is sent to the server, after the initial image is received by the server, the server processes the initial image, the processed initial image (namely, a human body characteristic image) is input into the trained machine learning model, classification information is obtained, corresponding characteristic extrusion data is obtained according to the first mapping relation and the second mapping relation, and the characteristic extrusion data is sent to the beauty equipment.
And step S303, controlling the type and the quantity of the extruded beauty fluid according to the characteristic extrusion data.
In this embodiment, the cosmetic apparatus may further control the kind and amount of the extruded cosmetic liquid according to the feature extrusion data; it should be noted that the beauty treatment equipment comprises one or more extrusion motors and also comprises one or more liquid reservoirs corresponding to the extrusion motors, wherein the liquid reservoirs are respectively used for storing different kinds of beauty treatment liquids.
After the feature extrusion data are received by the beauty equipment, extracting extrusion amount data and/or beauty fluid type data in the feature extrusion data; the extrusion motor is controlled according to the characteristic extrusion data, so as to control the amount of one or more cosmetic liquids.
For example, when the feature extrusion data is: "essence: 1mL "," emulsion cream: 3 mL', extracting extrusion amount data of 1mL and 3mL, and cosmetic liquid type data of essence and emulsion cream in the feature extrusion data, and controlling an extrusion motor to extrude the cosmetic liquid according to the extrusion amount data and the cosmetic liquid type data.
According to the extrusion control method of the cosmetic liquid provided by the embodiment, the initial image containing the specific part of the human body is collected; sending the initial image to a server to obtain feature extrusion data output by the server; the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment; controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data; the technical effect of intelligently controlling the liquid outlet quantity of the cosmetic liquid can be realized, the diversified skin care requirements of users can be met, the users do not need to manually extrude various different cosmetic liquids, and the use convenience of the users is improved.
In another embodiment, the human specific part comprises human skin; the step S301 includes: an initial image containing human skin is acquired by a camera.
Specifically, the beauty treatment device may include a camera, and the beauty treatment device may control the camera to acquire an initial image containing a specific part of a human body; the specific part of the human body may include a human organ, such as human skin, etc., i.e., the initial image may be an image of the specific part of the human body including a part; for example, the initial image may be an image containing human face skin.
In another embodiment, the cosmetic device is preset with a first mapping relationship between feature extrusion data and rotational stroke, and the step S303 includes:
finding the corresponding rotation stroke according to the feature extrusion data and the first mapping relation; controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
It should be noted that the cosmetic apparatus may be preset with a first mapping relationship between feature extrusion data and a rotation stroke of the extrusion motors, that is, each extrusion motor may extrude a corresponding cosmetic liquid, and specifically, the cosmetic apparatus may control extrusion amounts of different types of cosmetic liquids by controlling the rotation stroke of one or more extrusion motors; the output of cosmetic liquid that can customize improves the intelligent degree of equipment.
In one embodiment, as shown in fig. 4, a cosmetic liquid squeezing control system is provided, which includes a cosmetic device and a server, where the server is preset with a trained machine learning model; the system may perform the following steps:
step S401, the beauty equipment collects an initial image containing a specific part of a human body;
in this embodiment, the beauty equipment may include a camera, and the beauty equipment may control the camera to acquire an initial image including a specific part of a human body; the specific part of the human body can comprise a human organ, such as human skin, and the like, and for example, the beauty device can control the camera to acquire an image containing human face skin.
Step S402, the beauty equipment sends the initial image to a server;
further, after the initial image is acquired, the beauty equipment transmits the initial image to a server through a network.
Step S403, the server inputs the processed initial image into the trained machine learning model to obtain classification information;
in a specific implementation, the server may preset a trained machine learning model, and after the initial image is subjected to image processing, the initial image (i.e., a human body feature image) subjected to image processing is used as an input of the model.
And after the human body characteristic image is obtained, inputting the processed initial image into a trained machine learning model, and outputting the classification information of the processed initial image.
After obtaining the trained machine learning model, the server may preset the trained machine learning model in a database thereof, and when receiving the initial image, process the initial image, and the server may call a program interface corresponding to the trained machine learning model, and input the processed initial image (i.e., the human body feature image) to the trained machine learning model to obtain the classification information.
Step S404, the server acquires corresponding feature extrusion data according to the classification information;
in practical applications, after the processed initial image is input to the trained machine learning model, the server may obtain the output classification information.
Further, acquiring corresponding feature extrusion data according to the classification information; it should be noted that the characteristic extrusion data may include extrusion amount data and/or cosmetic liquid type data; the extrusion amount data refers to the volume or weight of the cosmetic liquid; the cosmetic liquid type data refers to identification information of different types of cosmetic liquid.
In a specific application, the server may obtain a corresponding skin detection result according to the classification information, and obtain the extrusion amount data and/or the cosmetic liquid type data according to the skin detection result.
Step S405, the server sends the feature extrusion data to the beauty equipment;
in this embodiment, after the server obtains the feature extraction data, the feature extraction data is sent to the beauty equipment through a network.
And step S406, the beauty device controls the type and the quantity of the squeezed beauty liquid according to the characteristic squeezing data.
Further applied to the embodiment, the beauty device can also control the type and the quantity of the squeezed beauty liquid according to the characteristic squeezing data; the beauty device comprises one or more extrusion motors and one or more liquid reservoirs corresponding to the extrusion motors, wherein the liquid reservoirs are respectively used for storing different kinds of beauty liquid.
After the feature extrusion data are received by the beauty equipment, extracting extrusion amount data and/or beauty fluid type data in the feature extrusion data; the extrusion motor is controlled according to the characteristic extrusion data, so that the quantity of one or more cosmetic liquids extruded is controlled.
According to the extrusion control system of the beauty fluid provided by the embodiment, the beauty device acquires an initial image containing a specific part of a human body; the beauty equipment sends the initial image to a server; the server inputs the processed initial image into the trained machine learning model to obtain classification information; the server acquires corresponding feature extrusion data according to the classification information; the server sends the feature extrusion data to the beauty equipment; the cosmetic device controls the kind and amount of the extruded cosmetic liquid according to the feature extrusion data. The technical effect of intelligently controlling the liquid outlet quantity of the cosmetic liquid can be realized, the diversified skin care requirements of users can be met, the users do not need to manually extrude various different cosmetic liquids, and the use convenience of the users is improved.
It should be understood that although the various steps in the flow diagrams of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a cosmetic liquid extrusion control device including: an initial image obtaining module 501, a classification information obtaining module 502, a first feature extrusion data obtaining module 503, and a feature extrusion data sending module 504, wherein:
an initial image obtaining module 501, configured to obtain an initial image that includes a specific part of a human body and is sent by a beauty device;
a classification information obtaining module 502, configured to input the processed initial image to a preset trained machine learning model, and obtain classification information;
a first feature extrusion data obtaining module 503, configured to obtain corresponding feature extrusion data according to the classification information;
a feature extrusion data sending module 504, configured to send the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
In one embodiment, the feature extrusion data acquisition module 504 includes:
the skin detection result generation submodule is used for generating a skin detection result according to the classification information;
and the characteristic extrusion data acquisition submodule is used for acquiring corresponding characteristic extrusion data according to the skin detection result.
In one embodiment, as shown in fig. 6, there is provided a cosmetic liquid extrusion control device including: an initial image acquisition module 601, a second feature extrusion data obtaining module 602, and a control module 603, wherein:
an initial image acquisition module 601, configured to acquire an initial image including a specific part of a human body;
a second feature extrusion data obtaining module 602, configured to send the initial image to a server, and obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
and a control module 603 for controlling the type and amount of the extruded cosmetic liquid according to the feature extrusion data.
In one embodiment, the specific part of the human body comprises human skin; the initial image acquisition module comprises:
and the initial image acquisition sub-module 601 is used for acquiring an initial image containing human skin through the camera.
In one embodiment, the cosmetic device is preset with a first mapping relationship between feature extrusion data and rotational stroke, and the control module 603 comprises:
the rotation stroke searching submodule is used for searching a corresponding rotation stroke according to the feature extrusion data and the first mapping relation;
and the control submodule is used for controlling the extrusion motor to extrude the quantity of the one or more cosmetic liquids according to the rotation stroke.
For specific limitations of the device for controlling the extrusion of the cosmetic liquid, reference may be made to the above limitations of the method for controlling the extrusion of the cosmetic liquid, which are not described herein again. All or part of each module in the cosmetic liquid extrusion control device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The device for controlling the extrusion of the cosmetic liquid can be used for executing the method for controlling the extrusion of the cosmetic liquid provided by any embodiment, and has corresponding functions and beneficial effects.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external beauty treatment device through network connection. The computer program is executed by a processor to implement a cosmetic liquid extrusion control method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information;
acquiring corresponding feature extrusion data according to the classification information;
sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: generating a skin detection result according to the classification information; and acquiring corresponding feature extrusion data according to the skin detection result.
In one embodiment, another computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: an initial image containing human skin is acquired by a camera.
In one embodiment, the processor when executing the computer program further performs the steps of: searching a corresponding rotation stroke according to the feature extrusion data and the first mapping relation; controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information;
acquiring corresponding feature extrusion data according to the classification information;
sending the feature extrusion data to the cosmetic device; wherein the cosmetic device is used for controlling the type and the quantity of the extruded cosmetic liquid according to the characteristic extrusion data.
In one embodiment, the computer program when executed by the processor further performs the steps of: generating a skin detection result according to the classification information; and acquiring corresponding feature extrusion data according to the skin detection result.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; acquiring corresponding feature extrusion data according to the classification information and sending the feature extrusion data to the beauty equipment;
controlling the type and quantity of the extruded beauty fluid according to the characteristic extrusion data.
In one embodiment, the computer program when executed by the processor further performs the steps of: an initial image containing human skin is acquired by a camera.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching a corresponding rotation stroke according to the feature extrusion data and the first mapping relation; controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (9)
1. A method for controlling the extrusion of a cosmetic liquid, applied to a server, comprising:
acquiring an initial image containing a specific part of a human body sent by a cosmetic device;
inputting the processed initial image into a preset trained machine learning model to obtain classification information; when the processed initial image is a pore characteristic image, the classification information comprises first type information, second type information and third type information;
inquiring a first mapping relation according to the classification information to obtain a corresponding skin detection result;
inquiring a second mapping relation according to the skin detection result to obtain corresponding feature extrusion data;
sending the feature extrusion data to the beauty equipment, wherein the beauty equipment is used for finding out a corresponding rotation stroke according to the feature extrusion data and the first mapping relation; and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
2. A method for controlling the extrusion of a cosmetic liquid, comprising:
acquiring an initial image containing a specific part of a human body;
sending the initial image to a server to obtain feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; when the processed initial image is a pore characteristic image, the classification information comprises first type information, second type information and third type information; inquiring a first mapping relation according to the classification information to obtain a corresponding skin detection result, inquiring a second mapping relation according to the skin detection result to obtain corresponding feature extrusion data, and sending the feature extrusion data to the beauty equipment;
the cosmetic equipment finds out a corresponding rotation stroke according to the feature extrusion data and the first mapping relation; and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
3. The method of claim 2, wherein the human specific part comprises human skin; the acquisition of an initial image containing a specific part of a human body comprises the following steps:
an initial image containing human skin is acquired by a camera.
4. A method according to claim 2 or 3, wherein the cosmetic device is preset with a first mapping of feature extrusion data to rotational stroke.
5. An extrusion control device of a cosmetic liquid, comprising:
the device comprises an initial image acquisition module, a display module and a display module, wherein the initial image acquisition module is used for acquiring an initial image which is sent by the beauty equipment and contains a specific part of a human body;
the classification information acquisition module is used for inputting the processed initial image into a preset trained machine learning model to acquire classification information; when the processed initial image is a pore characteristic image, the classification information comprises first type information, second type information and third type information;
the first feature extrusion data acquisition module is used for inquiring a first mapping relation according to the classification information and acquiring a corresponding skin detection result; inquiring a second mapping relation according to the skin detection result to obtain corresponding feature extrusion data;
the feature extrusion data sending module is used for sending the feature extrusion data to the beauty equipment, and the beauty equipment is used for finding the corresponding rotation stroke according to the feature extrusion data and the first mapping relation; and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
6. An extrusion control device for a cosmetic liquid, comprising:
the initial image acquisition module is used for acquiring an initial image containing a specific part of a human body;
the second feature extrusion data acquisition module is used for sending the initial image to a server and acquiring feature extrusion data output by the server;
the server is used for inputting the processed initial image to a preset trained machine learning model to obtain classification information; when the processed initial image is a pore characteristic image, the classification information comprises first type information, second type information and third type information; inquiring a first mapping relation according to the classification information to obtain a corresponding skin detection result, inquiring a second mapping relation according to the skin detection result to obtain corresponding feature extrusion data, and sending the feature extrusion data to the beauty equipment;
the control module is used for finding the corresponding rotation travel according to the feature extrusion data and the first mapping relation; and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
7. The extrusion control system of the beauty fluid is characterized by comprising beauty equipment and a server, wherein the server is preset with a trained machine learning model; the system comprises:
the beauty equipment acquires an initial image containing a specific part of a human body;
the beauty equipment sends the initial image to a server;
the server inputs the processed initial image into the trained machine learning model to obtain classification information; when the processed initial image is a pore characteristic image, the classification information comprises first type information, second type information and third type information;
the server inquires a first mapping relation according to the classification information to obtain a corresponding skin detection result; inquiring a second mapping relation according to the skin detection result to obtain corresponding feature extrusion data; the server sends the feature extrusion data to the beauty equipment;
the cosmetic equipment finds out a corresponding rotation stroke according to the feature extrusion data and the first mapping relation; and controlling the quantity of the one or more cosmetic liquids extruded by the extruding motor according to the rotating stroke.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method for controlling the extrusion of a cosmetic liquid according to any one of claims 1 to 4.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the method for controlling the extrusion of a cosmetic liquid according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811216797.3A CN109165700B (en) | 2018-10-18 | 2018-10-18 | Extrusion control method, device and system for beauty liquid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811216797.3A CN109165700B (en) | 2018-10-18 | 2018-10-18 | Extrusion control method, device and system for beauty liquid |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109165700A CN109165700A (en) | 2019-01-08 |
| CN109165700B true CN109165700B (en) | 2022-09-06 |
Family
ID=64878381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811216797.3A Active CN109165700B (en) | 2018-10-18 | 2018-10-18 | Extrusion control method, device and system for beauty liquid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165700B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1338263A2 (en) * | 2002-02-23 | 2003-08-27 | Hwajin Cosmetics Co., Ltd. | Total skin management system and method using the same |
| CN106469302A (en) * | 2016-09-07 | 2017-03-01 | 成都知识视觉科技有限公司 | A kind of face skin quality detection method based on artificial neural network |
| CN108198043A (en) * | 2018-01-29 | 2018-06-22 | 杭州美界科技有限公司 | A kind of facial skin care product recommended based on user recommend method |
| CN108211102A (en) * | 2018-01-02 | 2018-06-29 | 汕头高新区梦禾生物科技研究所有限公司 | A kind of face full-automatic water-supplying method and its instrument |
| CN108323203A (en) * | 2017-07-17 | 2018-07-24 | 深圳和而泰智能控制股份有限公司 | A kind of method, apparatus and intelligent terminal quantitatively detecting face skin quality parameter |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001292832A (en) * | 2000-04-13 | 2001-10-23 | Shiseido Co Ltd | Method for classifying makeup color image and makeup color image map |
| CN101833293B (en) * | 2010-06-01 | 2011-11-02 | 华东师范大学 | Precision control method and device for adding micro-liquid |
| RU2017128027A (en) * | 2015-06-15 | 2019-02-08 | Хаим АМИР | SYSTEMS AND METHODS FOR ADAPTIVE SKIN TREATMENT |
| AT517819B1 (en) * | 2015-09-15 | 2017-08-15 | Avl List Gmbh | Flushable device for measuring flow processes of fluids |
| CN107025629B (en) * | 2017-04-27 | 2021-03-26 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
| CN107563976B (en) * | 2017-08-24 | 2020-03-27 | Oppo广东移动通信有限公司 | Beauty parameter obtaining method and device, readable storage medium and computer equipment |
| CN107492067B (en) * | 2017-09-07 | 2019-06-07 | 维沃移动通信有限公司 | A kind of image beautification method and mobile terminal |
-
2018
- 2018-10-18 CN CN201811216797.3A patent/CN109165700B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1338263A2 (en) * | 2002-02-23 | 2003-08-27 | Hwajin Cosmetics Co., Ltd. | Total skin management system and method using the same |
| CN106469302A (en) * | 2016-09-07 | 2017-03-01 | 成都知识视觉科技有限公司 | A kind of face skin quality detection method based on artificial neural network |
| CN108323203A (en) * | 2017-07-17 | 2018-07-24 | 深圳和而泰智能控制股份有限公司 | A kind of method, apparatus and intelligent terminal quantitatively detecting face skin quality parameter |
| CN108211102A (en) * | 2018-01-02 | 2018-06-29 | 汕头高新区梦禾生物科技研究所有限公司 | A kind of face full-automatic water-supplying method and its instrument |
| CN108198043A (en) * | 2018-01-29 | 2018-06-22 | 杭州美界科技有限公司 | A kind of facial skin care product recommended based on user recommend method |
Non-Patent Citations (1)
| Title |
|---|
| 便携式人脸肤质检测与评价系统的设计与实现;张景源;《中国优秀硕士学位论文全文数据库-信息科技辑》;20180115(第（2018）年01期);I138-1550页第3.1.1节第1段、第4.4节第1、3段、表3-1、图4-18、4-19 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109165700A (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10936919B2 (en) | Method and apparatus for detecting human face | |
| CN108268885B (en) | Feature point detection method, device, and computer-readable storage medium | |
| KR102619221B1 (en) | Machine-implemented facial health and beauty aids | |
| CN110020582B (en) | Face emotion recognition method, device, equipment and medium based on deep learning | |
| CN109325468B (en) | Image processing method and device, computer equipment and storage medium | |
| US10990858B2 (en) | Machine-implemented facial health and beauty assistant | |
| CN110827236B (en) | Brain tissue layering method, device and computer equipment based on neural network | |
| CN108766545A (en) | Online interrogation section office distribution method, device, computer equipment and storage medium | |
| CN104346503A (en) | Human face image based emotional health monitoring method and mobile phone | |
| CN109117760A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| CN109559193A (en) | Product method for pushing, device, computer equipment and the medium of intelligent recognition | |
| JP6569183B2 (en) | Information processing apparatus, method, and program | |
| CN108784651A (en) | The commending system of U.S. industry product and service based on artificial intelligence | |
| WO2020125217A1 (en) | Expression recognition method and apparatus and recommendation method and apparatus | |
| CN109165700B (en) | Extrusion control method, device and system for beauty liquid | |
| CN110720906B (en) | Brain image processing method, computer device, and readable storage medium | |
| CN110163151B (en) | Training method and device of face model, computer equipment and storage medium | |
| CN110780956A (en) | Intelligent remote assistance method and device, computer equipment and storage medium | |
| CN115860067B (en) | Method, device, computer equipment and storage medium for generating countermeasure network training | |
| Siregar et al. | Human face recognition using eigenface in cloud computing environment | |
| CN108764289B (en) | Method and system for classifying UI (user interface) abnormal pictures based on convolutional neural network | |
| CN113657479B (en) | Novel multi-scale depth-width combined pathological picture classification method, system and medium | |
| EP3425637A3 (en) | Electronic system and method for classifying a physiological state | |
| CN113344040A (en) | Image classification method and device, computer equipment and storage medium | |
| CN111429991A (en) | Medicine prediction method and device, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |