CN111797775A - Recommended methods, devices and smart mirrors for image design - Google Patents

Abstract

The present invention provides an image design recommendation method, equipment and smart mirror, the method includes acquiring an image of a target object and illumination intensity of a target scene; extracting face feature data of the target object from the image of the target object; The face feature data and the light intensity are input into a pre-built grooming recommendation model for image design matching, and at least one image design scheme matching the face feature data under the light intensity is output. According to the illumination intensity of the scene corresponding to the destination to be reached by the target object, an image design scheme matching the facial feature data of the target object is obtained, which ensures that the target object can be designed according to the generated auxiliary image design scheme. achieve the desired effect. By adopting the technical scheme of the present invention, the reliability of the generated auxiliary image design scheme can be improved.

Description

Recommended methods, devices and smart mirrors for image design

technical field

The invention relates to the technical field of smart devices, and in particular, to a method, device and smart mirror for image design recommendation.

Background technique

With the continuous improvement of people's living standards, people pay more and more attention to their own image. Having a good image can leave a good and deep impression on people, and at the same time, it can also make one's life easier and more autonomous. , image design has gradually become an indispensable part of people's life aesthetics.

In the prior art, products such as smart mirrors can be used to assist in the design of the user's image. Usually, the facial features of the facial skin smoothness and facial features can be extracted, and a preset algorithm can be used to compare the current user's face for matching. Generate auxiliary image design scheme.

However, the results presented by the same facial features in different environments may be different, so that when the user designs according to the generated auxiliary image design scheme, the user's expected effect may not be achieved. The auxiliary image design scheme is less reliable.

SUMMARY OF THE INVENTION

In view of this, the purpose of the present invention is to provide an image design recommendation method, device and smart mirror, so as to solve the problem of poor reliability of the auxiliary image design scheme generated in the prior art.

Based on the above purpose, the present invention provides a method for recommending image design, including:

Obtain the image of the target object and the illumination intensity of the target scene; wherein, the target scene is the scene corresponding to the destination to be reached by the target object;

Extract the facial feature data of the target object from the image of the target object;

Inputting the face feature data and the light intensity into a pre-built grooming recommendation model for image design matching, and outputting at least one image design scheme that matches the face feature data under the light intensity.

Further, in the above-mentioned image design recommendation method, the illumination intensity of the target scene is collected by a light sensor, and/or determined according to a preset association relationship between the scene and the illumination intensity.

Further, in the above-mentioned method for recommending image design, the outputting at least one image design scheme that matches the face feature data under the illumination intensity includes:

If there are multiple image design schemes, calculate the score value of each image design scheme according to the weight of each image design scheme;

According to the order of the score value from high to low, sort each image design scheme, and obtain and output the sorted image design scheme.

Further, the above-mentioned recommended method for image design also includes:

Adjust the weight value of the target image design scheme selected by the target object.

Further, the above-mentioned recommended method for image design also includes:

receiving the evaluation information of the target image design scheme;

According to the evaluation information, the weight value of the target image design scheme is adjusted.

Further, in the above-mentioned method for recommending image design, the image design scheme includes: a grooming modelling design scheme and/or a dress matching design scheme;

Wherein, the dress collocation design scheme is designed according to the principle of main and auxiliary collocation of contrasting colors and adjacent colors.

Further, the above-mentioned recommended method for image design also includes:

Obtain the meteorological data of the target area; the target area is the area where the target object is located and/or the area where the target is reached;

generating maintenance suggestion information according to the meteorological data;

The maintenance recommendation information is output.

Further, in the above-mentioned image design recommendation method, the face feature data includes at least one of skin tone, face shape, eye distance, nose bridge ratio, eyebrow thickness, lip thickness, beard residue distribution and hairstyle.

The present invention also provides a recommended device for image design, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements any of the above-mentioned programs when the processor executes the program. Recommended methods for image design.

The present invention also provides a smart mirror, which is provided with the recommended device with the image design as described above.

As can be seen from the above, the image design recommendation method, device and smart mirror provided by the present invention obtain the facial feature data of the target object and the illumination intensity of the target scene, and combine the facial feature data of the target object with the target The illumination intensity of the scene is input into the pre-built grooming recommendation model for image design matching, and at least one image design scheme matching the facial feature data under the illumination intensity is output, which realizes the illumination intensity of the scene corresponding to the destination to be reached by the target object. , to obtain an image design scheme that matches the facial feature data of the target object, which ensures that the target object can achieve the expected effect when it is designed according to the generated auxiliary image design scheme. By adopting the technical scheme of the present invention, the reliability of the generated auxiliary image design scheme can be improved.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

Fig. 1 is the flow chart of the recommended method embodiment of the image design of the present invention;

2 is a schematic structural diagram of an embodiment of a recommended device for image design of the present invention;

FIG. 3 is a schematic structural diagram of an embodiment of a recommended device for image design of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of the present invention shall have the usual meanings understood by those with ordinary skill in the art to which the present disclosure belongs. As used in this disclosure, "first," "second," and similar terms do not denote any order, quantity, or importance, but are merely used to distinguish the various components. "Comprises" or "comprising" and similar words mean that the elements or things appearing before the word encompass the elements or things recited after the word and their equivalents, but do not exclude other elements or things. Words like "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right", etc. are only used to represent the relative positional relationship, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

FIG. 1 is a flowchart of an embodiment of a method for recommending image design according to the present invention. As shown in FIG. 1 , the method for recommending image design in this embodiment may specifically include the following steps:

100. Obtain the image of the target object and the illumination intensity of the target scene;

Under normal circumstances, the results of the facial features of the same person in different environments may vary. For example, under different light and different light intensities, the skin color may change to a certain extent. Therefore, in this embodiment, The image of the target object and the illumination intensity of the target scene can be acquired, wherein the target scene is the destination to be reached by the target object.

Specifically, this embodiment is mainly applied to a smart mirror, but can also be used in a smart terminal with a smart mirror function. Both smart mirrors and such smart terminals are provided with at least a display for displaying images and a camera for capturing images of users. In this step, when the target object activates the smart mirror, the smart mirror will acquire the image of the target object through the camera.

The illumination intensity of the target scene is collected by a light sensor, and/or determined according to a preset association relationship between the scene and the illumination intensity. Specifically, the illumination intensity of the target scene may be acquired according to the specific location of the target scene. For example, if the target scene is an office, the target object can use the light sensor to collect the light intensity of the office and then enter it into the smart mirror, or send it to the smart mirror through the cloud, or save it in the cloud, which is not specifically limited in this embodiment. If the target scene is a scene that the target object occasionally goes to, such as a restaurant, the target object cannot know the light intensity of the hotel. Therefore, in this embodiment, the light intensity of each scene can be sampled in advance in order to establish a scene The relationship between the light intensity and the light intensity. In this way, after the target scene is determined to be the hotel, the light intensity of the hotel can be obtained from the preset correlation relationship between the scene and the light intensity. In the association relationship, the light intensity of the hotel does not exist, and the light intensity of the hotel of the same type as the hotel can be determined from the preset association relationship between the scene and the light intensity as the light intensity of the hotel, or the target object The light intensity of the current scene is used as the light intensity of the restaurant.

It should be noted that, in this embodiment, the reason why the illumination intensity of the target scene is obtained is because the target object often arrives at the destination from home during image care, and the target user needs to leave a good and profound impression on the destination. Impression, therefore, the light intensity of the destination is more important to the image of the target object than the light intensity of the home. Therefore, when generating the image design plan, the light intensity of the destination is often used as a reference.

101. Extract face feature data of the target object from an image of the target object;

A preset image feature extraction method can be used to extract the face feature data of the target object from the image of the target object; wherein, the face feature data of the target object can include skin tone, face shape, eye distance, nose bridge ratio, eyebrow thickness , at least one of lip thickness, beard distribution and hairstyle.

102. Input the facial feature data of the target object and the light intensity of the target object into a pre-built grooming recommendation model for image design matching, and output at least one image design scheme that matches the facial feature data under the light intensity;

In a specific implementation process, the upper body feature images of representative people of different age levels in various regions can be collected, and the portrait model trained by using the deep learning method can automatically extract the different skin tones, facial features (face shape) in the portrait. , eye distance, nose bridge ratio, eyebrow thickness, lip thickness, beard stubble distribution) and other face feature data under different light intensities, as well as the men's upper body clothing data of common matching colors and classic dress styles for men's tops.

Collect classic and trendy male hair style, beard shape, clothing color matching information, and build a grooming recommendation model based on these contents: First, through manual annotation, take a part of the above face feature data, and match with the recommended grooming style and dress matching; Then through deep learning training, the model has a high recommendation accuracy rate, and at the same time, the unlabeled image data is used for testing and optimization; at the same time, the grooming recommendation model will also set some rules: for example, for color matching, there are adjacent colors and contrasting colors. etc. rules.

In this embodiment, after obtaining the facial feature data of the target object and the light intensity of the target scene, the facial feature data of the target object and the light intensity of the target object can be input into a pre-built grooming recommendation model for image design matching, and output At least one image design scheme that matches the facial feature data under the light intensity, so that the target object selects the target image design scheme, and takes care of its own image according to the selected target image design scheme. Among them, the beauty styling design scheme and/or the dress matching design scheme; wherein, the beauty styling design scheme includes shaving, combing hair, and the like. The dress collocation design scheme is designed according to the principle of the main and auxiliary collocation of contrasting colors and adjacent colors. That is to say, the main and auxiliary collocation rules of contrasting colors and adjacent colors are used. Two colors that are adjacent to each other are similar colors. For example, orange and pink are also called warm colors, and blue and purple are also called cool colors; the two colors are in the color wheel. Contrasting colors, such as red, green, yellow and blue, are generally used to create jumping color contrasts or to use contrasting colors for festivals. Black, white and gray are universal auxiliary colors. The golden rule of color is 60:30:10. The main color is 60%, the auxiliary color is 30%, and the auxiliary color is 10%. For example, men's tops, blazers can be used 60%, shirts 30%, bow ties 10%.

It should be noted that, in practical applications, the smart mirrors on the market are usually only designed for the image of the female group, while the male group is different from the female group in terms of facial smoothness, facial features and beards. The smart mirror pass cannot reach the pain points of the male group in a targeted manner, and the recommended image design scheme is often feminine, and the recommendation is difficult to be close to daily life. Therefore, in this embodiment, it is preferable to apply the image design recommendation method to in the male group.

In the image design recommendation method of this embodiment, the facial feature data of the target object and the illumination intensity of the target scene are acquired, and the facial feature data of the target object and the illumination intensity of the target scene are input into a pre-built grooming recommendation model for image development. Design matching, at least one image design scheme that matches the facial feature data under the output light intensity, realizes the illumination intensity of the scene corresponding to the destination to be reached by the target object, and obtains the target object. The image design scheme ensures that when the target object is designed according to the generated auxiliary image design scheme, the expected effect can be achieved. By adopting the technical scheme of the present invention, the reliability of the generated auxiliary image design scheme can be improved.

In a specific implementation process, in order to facilitate the target object to quickly select the desired target image design scheme, in this embodiment, if there are multiple image design schemes, according to the weight of each image design scheme, calculate the image design scheme of each image design scheme. The score value; and according to the order of the score value from high to low, sort each image design scheme, and obtain and output the sorted image design scheme. In addition, the output quantity can also be set, so that the output quantity can be selected according to the order from high to low. For example, the output quantity is preferably 3.

In practical applications, the weight value of the target image design scheme for the selection of the target object can also be adjusted according to the selection of the target object, so as to determine the preferences of the target object, thereby accurately recommending. In addition, for the target object, after it is arranged according to the selected target image design plan, other people may evaluate the image of the target object, for example, "the young man is really spirited", "the hairstyle is a bit unsuitable", etc. Therefore, The target object can enter the evaluation heard, so that the smart mirror is receiving evaluation information of the target image design scheme; according to the evaluation information, the weight value of the target image design scheme is adjusted. For example, if the evaluation information is "the real spirit of the young man", the weight of the target image design scheme can be increased, and the "hair style is a little unsuitable" can reduce the weight of the target image design scheme, so that the image design scheme can be pushed more accurately.

In a specific implementation process, the image design recommendation method of this embodiment can also obtain meteorological data of the target area; generate maintenance advice information according to the meteorological data; output maintenance advice information, so that the target object is taking care of itself It can also be taken care of in combination with maintenance advice information. The target area is the area where the target object is located and/or the area where the target is reached. Meteorological data includes temperature, UV rays, air pollution, and more.

In practical applications, the image design scheme obtained by the image design recommendation method in this embodiment may only have a better image in theory, but the user may not be able to implement the selected target image design scheme due to various factors. Therefore, in order to solve the above technical problems, the present invention also provides the following technical solutions.

Specifically, the target object can use the camera of the smart mirror to take pictures of the clothes purchased by himself, so that his clothes can be entered into the resource library as resources. After an image design plan, the target object cannot take care of himself according to the image design plan.

In practical applications, if the image design scheme obtained from the resource library of the target object does not meet the needs of the target object, it is also possible to generate links corresponding to other image design schemes based on resources other than the resource library of the target object, so that after the user clicks the link, Make an online purchase.

It should be noted that, the method in this embodiment of the present invention may be executed by a single device, such as a computer or a server. The method in this embodiment can also be applied in a distributed scenario, and is completed by the cooperation of multiple devices. In such a distributed scenario, one device among the multiple devices may only execute one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the method.

FIG. 2 is a schematic structural diagram of an embodiment of an image design recommendation apparatus according to the present invention. As shown in FIG. 2 , the image design recommendation apparatus of this embodiment includes an acquisition module 20 , an extraction module 21 and a matching module 22 .

The acquisition module 20 is used to acquire the image of the target object and the illumination intensity of the target scene; wherein, the target scene is a scene corresponding to the destination to be reached by the target object; the illumination intensity of the target scene is collected by using a light sensor, and/or, It is determined according to the relationship between the preset scene and the light intensity.

The extraction module 21 is used to extract the facial feature data of the target object from the image of the target object; wherein, the facial feature data includes skin tone, face shape, eye distance, nose bridge ratio, eyebrow thickness, lip thickness, stubble distribution and At least one of the hairstyles.

The matching module 22 is used for inputting the face feature data and the light intensity into the pre-built grooming recommendation model for image design matching, and outputting at least one image design scheme matching the face feature data under the light intensity. Among them, grooming styling design scheme and/or dress collocation design scheme;

Among them, the dress collocation design scheme is designed according to the principle of the main and auxiliary collocation of contrasting colors and adjacent colors.

Further, in the above-mentioned embodiment, the matching module 22 is specifically used to calculate the score value of each image design solution according to the weight of each image design solution if there are multiple image design solutions; In the lower order, sort each image design scheme, and obtain and output the sorted image design scheme.

In practical applications, the matching module 22 is further configured to adjust the weight value of the target image design scheme selected by the target object.

Further, the matching module 22 is also used to receive the evaluation information of the target image design scheme;

According to the evaluation information, adjust the weight value of the standard image design scheme.

In a specific implementation process, the acquisition module 20 is also used to acquire the meteorological data of the target area; the target area is the area where the target object is located and/or the area where the target is reached;

The matching module 22 is further configured to generate maintenance suggestion information according to the meteorological data, and output the maintenance suggestion information.

The apparatuses in the foregoing embodiments are used to implement the corresponding methods in the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

FIG. 3 is a schematic structural diagram of an embodiment of a recommended device according to the image design of the present invention. As shown in FIG. 3 , the passing device in this embodiment may include: a processor 1010 and a memory 1020 . Those skilled in the art may know that the recommended device for image design may further include an input/output interface 1030 , a communication interface 1040 and a bus 1050 . The processor 1010 , the memory 1020 , the input/output interface 1030 and the communication interface 1040 realize the communication connection among each other within the device through the bus 1050 .

The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute related program to implement the technical solutions provided by the embodiments of this specification.

The memory 1020 may be implemented in the form of a ROM (Read Only Memory, read only memory), a RAM (Random Access Memory, random access memory), a static storage device, a dynamic storage device, and the like. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and invoked by the processor 1010 for execution.

The input/output interface 1030 is used to connect the input/output module to realize information input and output. The input/output/module can be configured in the device as a component (not shown in the figure), or can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, and the like.

The communication interface 1040 is used to connect a communication module (not shown in the figure), so as to realize the communication interaction between the device and other devices. The communication module may implement communication through wired means (eg, USB, network cable, etc.), or may implement communication through wireless means (eg, mobile network, WIFI, Bluetooth, etc.).

Bus 1050 includes a path to transfer information between the various components of the device (eg, processor 1010, memory 1020, input/output interface 1030, and communication interface 1040).

It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include necessary components for normal operation. other components. In addition, those skilled in the art can understand that, the above-mentioned device may only include components necessary to implement the solutions of the embodiments of the present specification, rather than all the components shown in the figures.

The present invention also provides a smart mirror, which is provided with the recommended device for the image design of the above embodiment.

The present invention also provides a storage medium, which is characterized in that the storage medium stores computer instructions, and the computer instructions are used to make the computer execute the image design method of the above embodiment.

The computer readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology for information storage. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the spirit of the present invention, the above embodiments or There may also be combinations between technical features in different embodiments, steps may be carried out in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.

Additionally, well known power/ground connections to integrated circuit (IC) chips and other components may or may not be shown in the figures provided in order to simplify illustration and discussion, and in order not to obscure the present invention. . Furthermore, devices may be shown in block diagram form in order to avoid obscuring the present invention, and this also takes into account the fact that the details regarding the implementation of these block diagram devices are highly dependent on the platform on which the invention will be implemented (i.e. , these details should be fully within the understanding of those skilled in the art). Where specific details (eg, circuits) are set forth to describe exemplary embodiments of the invention, it will be apparent to those skilled in the art that these specific details may be used without or with changes The present invention is carried out below. Accordingly, these descriptions are to be considered illustrative rather than restrictive.

Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations to these embodiments will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (eg, dynamic RAM (DRAM)) may use the discussed embodiments.

Embodiments of the present invention are intended to cover all such alternatives, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A method for recommending a character design, comprising:

acquiring an image of a target object and the illumination intensity of a target scene; the target scene is a scene corresponding to a destination to which the target object is to reach;

extracting face feature data of the target object from the image of the target object;

inputting the face feature data and the illumination intensity into a pre-constructed face-to-face recommendation model for image design matching, and outputting at least one image design scheme matched with the face feature data under the illumination intensity.

2. The visual design recommendation method according to claim 1, wherein the illumination intensity of the target scene is collected by a light sensor and/or determined according to a preset scene-to-illumination intensity correlation.

3. The avatar design recommendation method of claim 1, wherein said outputting at least one avatar design matching said face feature data at said illumination intensity comprises:

if the number of the image design schemes is multiple, calculating the score value of each image design scheme according to the weight of each image design scheme;

and sequencing each image design scheme according to the sequence of the score values from high to low to obtain and output the sequenced image design schemes.

4. The visual design recommendation method of claim 3, further comprising:

adjusting a weight value of the selected target avatar design of the target object.

5. The visual design recommendation method of claim 4, further comprising:

receiving evaluation information of the target image design scheme;

and adjusting the weight value of the design scheme of the object shape according to the evaluation information.

6. The character design recommendation method of claim 1, wherein the character design solution comprises: a face-care modeling design scheme and/or a dressing matching design scheme;

wherein, the dress collocation design scheme is designed according to the main and auxiliary collocation principles of contrast colors and adjacent colors.

7. The visual design recommendation method of claim 1, further comprising:

acquiring meteorological data of a target area; the target area is the area where the target object is located and/or the area where the target reaches;

generating maintenance suggestion information according to the meteorological data;

and outputting the maintenance suggestion information.

8. An image design recommendation method according to any one of claims 1-7, wherein the face feature data includes at least one of skin tone, face shape, eye distance, nose bridge ratio, eyebrow thickness, lip thickness, beard distribution and hairstyle.

9. A character design recommendation apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the character design recommendation method of any one of claims 1 to 8.

10. A smart mirror, characterized in that it is provided with a recommendation device designed according to the image of claim 9.

Images