CN105354792A - A virtual glasses try-on method and mobile terminal - Google Patents

Abstract

The embodiment of the invention provides a virtual glasses try-on method, which comprises the following steps: acquiring an image input by a user; carrying out face detection on the image; under the condition that a human face is detected, determining an angle value and a face shape of the human face and central points of two eyes of the human face; determining a target model picture corresponding to the angle value and the face shape; acquiring a glasses style selected by a user; determining a glasses picture corresponding to the glasses style according to the angle value; scaling the glasses picture according to a proportional relation between a second distance in the target model picture and a first distance between center points of two eyes in the human face, wherein the second distance is the distance between the center points of the two eyes of the model in the target model picture; and overlapping the glasses picture after the zooming processing with the face. By the embodiment of the invention, a user can more directly observe the wearing effect of the glasses, and the user experience is improved.

Description

A virtual glasses try-on method and mobile terminal

technical field

The embodiment of the present invention relates to the technical field of combining computer vision and virtual wear, and in particular to a virtual glasses try-on method and a mobile terminal.

Background technique

With the rapid development of mobile Internet technology, mobile terminals (such as mobile phones, tablet computers, etc.) have become an indispensable part of life. Compared with shopping in traditional brick-and-mortar stores, online shopping has the advantages of being free from time and location constraints, complete varieties, and low prices. It is difficult to choose the product you want in this way.

In life, glasses are very popular as one of the many consumption categories of online shopping. However, in the process of selecting glasses on the Internet, the effect of the glasses is only observed from the existing model pictures. In this way, the display of the wearing effect of the glasses is not intuitive, so that it is difficult for the user to feel the feeling of trying them on during the online shopping process. Therefore, , reducing the user experience.

Contents of the invention

Embodiments of the present invention provide a virtual glasses try-on method and a mobile terminal, in order to allow users to more intuitively understand the wearing effect selected by the user, and at the same time improve user experience.

The first aspect of the embodiment of the present invention provides a virtual glasses try-on method, including:

Get the image entered by the user;

Perform face detection on the image;

In the case of detecting a human face, determine the angle value of the human face, the face shape and the center point of the two eyes of the human face;

Determining a target model picture corresponding to the angle value and the face shape;

Obtain the glasses style selected by the user;

determining the glasses picture corresponding to the glasses style according to the angle value;

According to the proportional relationship between the second distance in the target model picture and the first distance between the center points of the two eyes in the face, the glasses picture is scaled, wherein the second distance is the The distance between the center points of the eyes of the model in the target model image;

and superimposing the zoomed glasses picture with the human face.

With reference to the first aspect of the embodiments of the present invention, in the first possible implementation manner of the first aspect, when a human face is detected, determining the angle value of the human face, the shape of the face, and the angle of the human face The center point of the two eyes and the first distance between the center points of the two eyes comprise:

In the case of detecting a plurality of human faces, selecting a human face i in the plurality of human faces, wherein the human face i is any human face in the plurality of human faces;

Determine the angle value of the face i, the face shape, and the center points of the two eyes in the face i.

With reference to the first aspect of the embodiments of the present invention, in a second possible implementation manner of the first aspect, the determining the glasses picture corresponding to the glasses style according to the angle value includes:

According to the angle value, the glasses picture corresponding to the glasses style is searched from the image library.

With reference to the first aspect of the embodiments of the present invention, in a third possible implementation manner of the first aspect, the superimposing the zoomed glasses picture on the human face includes:

The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face.

In combination with the first aspect or any one of the first to third possible implementation manners of the embodiments of the present invention, in the fourth possible implementation manner of the first aspect, the glasses after the scaling process After superimposing the picture and the human face, the method also includes:

Obtain the scene mode selected by the user;

A picture of glasses corresponding to the scene mode is selected from a preset picture library and superimposed on the face of the person.

The second aspect of the embodiment of the present invention provides a mobile terminal, including:

an acquisition unit, configured to acquire an image input by a user;

a detection unit, configured to perform face detection on the image acquired by the acquisition unit;

The first determination unit is configured to determine the angle value of the human face, the shape of the face, and the center point of the two eyes of the human face when the detection unit detects the human face;

A second determination unit, configured to determine a target model picture corresponding to the angle value and face shape determined by the first determination unit;

The acquisition unit is also specifically used for:

Obtain the glasses style selected by the user;

A third determination unit, configured to determine the glasses picture corresponding to the glasses style acquired by the acquisition unit according to the angle value determined by the first determination unit;

The scaling unit is used to calculate the ratio according to the ratio between the second distance in the target model picture determined by the second determination unit and the first distance between the center points of the two eyes in the human face determined by the first determination unit. The glasses picture determined by the third determining unit is subjected to scaling processing, wherein the second distance is the distance between the center points of the two eyes of the model in the target model picture;

The first superimposing unit is configured to superimpose the glasses picture after scaling processing by the scaling unit and the human face detected by the detecting unit.

With reference to the second aspect of the embodiments of the present invention, in a first possible implementation manner of the second aspect, the first determination unit includes:

A selection unit, configured to select a face i among the plurality of faces when the detection unit detects a plurality of faces, wherein the face i is any one of the plurality of faces;

The first determination subunit is used to determine the angle value, face shape and center point of the two eyes of the face i selected by the selection unit.

With reference to the second aspect of the embodiments of the present invention, in a second possible implementation manner of the second aspect, the second determination unit is specifically configured to:

According to the angle value, the glasses picture corresponding to the glasses style is searched from the image library.

With reference to the second aspect of the embodiments of the present invention, in a third possible implementation manner of the second aspect, the superposition unit is specifically configured to:

The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face.

In combination with the second aspect of the embodiments of the present invention or any one of the first to third possible implementation manners, in the fourth possible implementation manner of the second aspect, the acquiring unit is further specifically configured to:

Obtain the scene mode selected by the user;

The mobile terminal also includes:

The second superimposing unit is configured to select a picture of glasses corresponding to the scene mode acquired by the acquisition unit from a preset picture library and superimpose it on the face recognized by the recognition unit.

Adopting the embodiment of the present invention has the following beneficial effects:

Obtain the image input by the user through the embodiment of the present invention; perform face detection on the image; when a face is detected, determine the angle value of the face, the shape of the face, and the center point of the two eyes of the face ; Determine the target model picture corresponding to the angle value and the face shape; Obtain the glasses style selected by the user; Determine the glasses picture corresponding to the glasses style according to the angle value; According to the second distance in the target model picture The proportional relationship between the first distance and the center point of the two eyes in the human face performs scaling processing on the glasses picture, wherein the second distance is the center of the two eyes of the model in the target model picture The distance between the points; the glasses picture after the scaling process is superimposed on the human face. Therefore, the user can more directly observe the wearing effect of the glasses, which improves the user experience.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

Fig. 1 is a schematic flow chart of the first embodiment of a method for trying on virtual glasses provided by an embodiment of the present invention;

Fig. 2 is a schematic flow chart of the second embodiment of a method for trying on virtual glasses provided by an embodiment of the present invention;

Fig. 3a is a schematic structural diagram of a first embodiment of a mobile terminal provided by an embodiment of the present invention;

Fig. 3b is another structural schematic diagram of the first embodiment of a mobile terminal provided by the embodiment of the present invention;

Fig. 3c is another structural schematic diagram of the first embodiment of a mobile terminal provided by the embodiment of the present invention;

Fig. 4 is a schematic structural diagram of a second embodiment of a mobile terminal provided by an embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Each will be described in detail below.

The terms "first", "second", "third" and "fourth" in the description and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order . Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or apparatuses.

The mobile terminal described in the embodiment of the present invention may include a smart phone (such as an Android phone, an iOS phone, a Windows Phone, etc.), a tablet computer, a handheld computer, a notebook computer, a mobile Internet device (MID, MobileInternetDevices) or a wearable device, etc., the above-mentioned The mobile terminal is only an example, not exhaustive, including but not limited to the above-mentioned mobile terminal.

Please refer to FIG. 1 , which is a schematic flowchart of a first embodiment of a method for virtual glasses provided by an embodiment of the present invention. The virtual glasses try-on method described in this embodiment includes the following steps:

S101. Acquire an image input by a user.

In this embodiment, the image input by the user may contain at least one human face, and the image may be a picture captured by a camera of the mobile terminal, a photo stored in the mobile terminal, or a photo on the Internet. The angle of the face in the image can be a frontal face, or a side face at any angle. Preferably, in this embodiment, the image may contain one and only one human face.

S102. Perform face detection on the image.

In a specific implementation, the mobile terminal may perform face detection on the image input by the user. The purpose of the face detection is to detect whether the picture contains a human face, or whether it contains one face or multiple faces.

Optionally, when the mobile terminal detects that the image does not contain a face image, it may remind the user to take another picture or select another picture.

Optionally, when the mobile terminal detects a human face image but does not detect human eyes, it can remind the user to take another picture or choose another picture. Further, when the user compares one eye, the user is prompted to Open the other eye.

S103. If a human face is detected, determine an angle value of the human face, a face shape, and a center point of two eyes of the human face.

In the specific implementation, when the mobile terminal only detects one human face, it can determine the angle value of the human face, the face shape and the center point of the two eyes in the human face, and can also determine the distance between the center points of the two eyes. distance.

Further, in the case that the mobile terminal detects multiple human faces, face i among the multiple human faces can be selected, wherein the human face i is any one of the multiple human faces; The angle value of i, the face shape and the center point of the two eyes of the face i.

Further, in the case that the mobile terminal detects multiple human faces, it can simultaneously determine the angle value of at least two human faces in the multiple human faces, the face shape and the center point of the two eyes of each human face in the at least two human faces .

S104. Determine a target model picture corresponding to the angle value and the face shape.

In a specific implementation, the mobile terminal can search the picture library according to the angle value and face shape. The picture library can be located in the mobile terminal or a server, and the picture matching the angle value and face shape is used as the target model picture.

S105. Obtain the glasses style selected by the user.

In a specific implementation, the categories of the glasses may be full-rim, half-rim and frameless. The glasses style should be a kind of glasses under any category of glasses.

Further, the categories of glasses may include but not limited to: fashion (500-800 yuan), light luxury (800-2000 yuan), luxury (2000-5000 yuan) and extreme (5000 yuan or more). The glasses style should be a kind of glasses under any category of glasses.

Further, the category of glasses may also include but not limited to: plates, metals, titanium metals and mixed materials. The glasses style should be a kind of glasses under any category of glasses.

Further, the categories of glasses may include but not limited to: Armani, Esperin, Azalo, Polaroid, Porsche, Landscape, Golf, Cargal, Victoria, Chanel, and Zoff. The glasses style should be a kind of glasses under any category of glasses.

Eyewear categories may also include, but are not limited to: Men's Sunglasses, Women's Sunglasses, Men's Optical, and Women's Optical. The glasses style should be a kind of glasses under any category of glasses.

S106. Determine the glasses picture corresponding to the glasses style according to the angle value.

In a specific implementation, the mobile terminal may search the picture library for glasses pictures corresponding to the glasses style according to the angle value. It should be noted that the picture library may contain multiple model pictures, and the model pictures may wear glasses of various styles. For example, for a certain type of glasses, the glasses can be photographed at any angle to obtain a series of glasses pictures corresponding to the glasses, and the glasses pictures can be named by angle values, so that the series of glasses pictures can be effectively distinguished. Optionally, a picture of glasses corresponding to the style of glasses is searched from a picture library. That is, the picture library stores pictures of glasses series of different styles, and each series picture of glasses contains pictures of glasses at any angle of a certain type of glasses.

S107. Perform scaling processing on the glasses picture according to the proportional relationship between the second distance in the target model picture and the first distance between the center points of the eyes of the human face, wherein the second distance is The distance between the center points of the two eyes of the model in the target model picture.

In a specific implementation, the distance between the center points of the two eyes of the face detected by the mobile terminal in the process of detecting the face may be the first distance, and the center point of the two eyes is the center point of each glasses. The second distance is the distance between the center points of the two eyes of the model in the target model picture, and the second distance matches the glasses picture. The zoom ratio of the glasses picture can be determined according to the proportional relationship between the first distance and the second distance. Assuming that the first distance is 1, the second distance is 2, and the second distance is displayed as twice the first distance, the scale of the glasses picture can be reduced by half.

S108. Superimpose the zoomed glasses picture with the human face.

In a specific implementation, the mobile terminal can superimpose the zoomed glasses picture on the face area, that is, determine the placement position of the glasses according to the center point of the two eyes in the face, and superimpose the glasses on the face area according to the placement position .

Obtain the image input by the user through the embodiment of the present invention; perform face detection on the image; when a face is detected, determine the angle value of the face, the shape of the face, and the center point of the two eyes of the face ; Determine the target model picture corresponding to the angle value and the face shape; Obtain the glasses style selected by the user; Determine the glasses picture corresponding to the glasses style according to the angle value; According to the second distance in the target model picture The proportional relationship between the first distance and the center point of the two eyes in the human face performs scaling processing on the glasses picture, wherein the second distance is the center of the two eyes of the model in the target model picture The distance between the points; the glasses picture after the scaling process is superimposed on the human face. Therefore, the user can more directly observe the wearing effect of the glasses, which improves the user experience.

Please refer to FIG. 2 , which is a schematic flowchart of a second embodiment of a method for trying on virtual glasses provided by an embodiment of the present invention. The virtual glasses try-on method described in this embodiment includes the following steps:

S201. Acquire an image input by a user.

In this embodiment, the image input by the user may contain at least one human face, and the image may be a picture captured by a camera of the mobile terminal, a photo stored in the mobile terminal, or a photo on the Internet. The angle of the face in the image can be a frontal face, or a side face at any angle. Preferably, in this embodiment, the image may contain one and only one human face.

S202. Perform face detection on the image.

In a specific implementation, the mobile terminal may perform face detection on the image input by the user. The purpose of the face detection is to detect whether the picture contains a human face, or whether it contains one face or multiple faces.

Optionally, when the mobile terminal detects that the image does not contain a face image, it may remind the user to take another picture or select another picture.

Optionally, when the mobile terminal detects a human face image but does not detect human eyes, it can remind the user to take another picture or choose another picture. Further, when the user compares one eye, the user is prompted to Open the other eye.

S203. If a human face is detected, determine an angle value of the human face, a face shape, and a center point of two eyes of the human face.

In the specific implementation, when the mobile terminal only detects one human face, it can determine the angle value of the human face, the face shape and the center point of the two eyes in the human face, and can also determine the distance between the center points of the two eyes. distance.

Further, in the case that the mobile terminal detects multiple human faces, face i among the multiple human faces can be selected, wherein the human face i is any one of the multiple human faces; The angle value of i, the face shape and the center point of the two eyes of the face i. The arbitrary face may include, but is not limited to: the face with the largest face area among the multiple faces, the face with the smallest face area, the face with the most complete face display, and the face that is the first to be detected in the face detection process. Detected faces and more.

Further, in the case that the mobile terminal detects multiple human faces, it can simultaneously determine the angle value of at least two human faces in the multiple human faces, the face shape and the center point of the two eyes of each human face in the at least two human faces .

S204. Determine a target model picture corresponding to the angle value and the face shape.

In a specific implementation, the mobile terminal can search the picture library according to the angle value and face shape. The picture library can be located in the mobile terminal or a server, and the picture matching the angle value and face shape is used as the target model picture.

S205. Obtain the glasses style selected by the user.

In a specific implementation, the categories of the glasses may be full-rim, half-rim and frameless. The glasses style should be a kind of glasses under any category of glasses.

Further, the categories of glasses may include but not limited to: fashion (500-800 yuan), light luxury (800-2000 yuan), luxury (2000-5000 yuan) and extreme (5000 yuan or more). The glasses style should be a kind of glasses under any category of glasses.

Further, the category of glasses may also include but not limited to: plates, metals, titanium metals and mixed materials. The glasses style should be a kind of glasses under any category of glasses.

Further, the categories of glasses may include but not limited to: Armani, Esperin, Azalo, Polaroid, Porsche, Landscape, Golf, Cargal, Victoria, Chanel, and Zoff. The glasses style should be a kind of glasses under any category of glasses.

Eyewear categories may also include, but are not limited to: Men's Sunglasses, Women's Sunglasses, Men's Optical, and Women's Optical. The glasses style should be a kind of glasses under any category of glasses.

S206. Determine the glasses picture corresponding to the glasses style according to the angle value.

In a specific implementation, the mobile terminal may search the picture library for glasses pictures corresponding to the glasses style according to the angle value. It should be noted that the picture library may contain multiple model pictures, and the model pictures may wear glasses of various styles. For example, for a certain type of glasses, the glasses can be photographed at any angle to obtain a series of glasses pictures corresponding to the glasses, and the glasses pictures can be named by angle values, so that the series of glasses pictures can be effectively distinguished. Optionally, a picture of glasses corresponding to the style of glasses is searched from a picture library. That is, the picture library stores pictures of glasses series of different styles, and each series picture of glasses contains pictures of glasses of any angle of a certain type of glasses.

S207. Perform scaling processing on the glasses picture according to the proportional relationship between the second distance in the target model picture and the first distance between the center points of the two eyes in the human face, wherein the second distance is The distance between the center points of the two eyes of the model in the target model picture.

In a specific implementation, the distance between the center points of the two eyes of the face detected by the mobile terminal in the process of detecting the face may be the first distance, and the center point of the two eyes is the center point of each glasses. The second distance is the distance between the center points of the two eyes of the model in the target model picture, and the second distance matches the glasses picture. The zoom ratio of the glasses picture can be determined according to the proportional relationship between the first distance and the second distance. Assuming that the first distance is 1, the second distance is 2, and the second distance is displayed as twice the first distance, the scale of the glasses picture can be reduced by half.

S208. Superimpose the zoomed glasses picture with the human face.

In a specific implementation, the mobile terminal can superimpose the zoomed glasses picture on the face area, that is, determine the placement position of the glasses according to the center point of the two eyes in the face, and superimpose the glasses on the face area according to the placement position .

S209. Obtain the scene mode selected by the user.

Optionally, the mobile terminal may obtain a scene mode selected by the user, and the scene mode may include but not limited to: coffee shop, park, square, clubhouse, seaside, sunset, and sunset.

S210. Select a picture of glasses corresponding to the scene mode from a preset picture library and superimpose it on the face of the person.

In a specific implementation, furthermore, the mobile terminal may select a picture of glasses corresponding to a scene mode from a preset picture library and superimpose it on the face image. The preset picture library may include one or more sets of picture libraries, for example, one picture library may be set for one scene.

Obtain the image input by the user through the embodiment of the present invention; perform face detection on the image; when a face is detected, determine the angle value of the face, the shape of the face, and the center point of the two eyes of the face ; Determine the target model picture corresponding to the angle value and the face shape; Obtain the glasses style selected by the user; Determine the glasses picture corresponding to the glasses style according to the angle value; According to the second distance in the target model picture The proportional relationship between the first distance and the center point of the two eyes in the human face performs scaling processing on the glasses picture, wherein the second distance is the center of the two eyes of the model in the target model picture The distance between the points; superimposing the glasses picture after the scaling process with the human face; obtaining the scene mode selected by the user; selecting the glasses picture corresponding to the scene mode from the preset picture library to be superimposed on the human face above the face image. Therefore, the user can more directly observe the wearing effect of the glasses, which improves the user experience.

Please refer to FIG. 3a-FIG. 3c, wherein FIG. 3a is a schematic structural diagram of a first embodiment of a mobile terminal provided by an embodiment of the present invention. The mobile terminal described in this embodiment in FIG. 3a includes: an acquisition unit 301, a detection unit 302, a first determination unit 303, a second determination unit 304, a third determination unit 305, a scaling unit 306, and a superposition unit 307, specifically as follows:

Acquisition unit 301, configured to acquire the image input by the user

A detection unit 302, configured to perform face detection on the image acquired by the acquisition unit 301;

The first determination unit 303 is configured to determine the angle value of the human face, the shape of the face, and the center point of the two eyes of the human face when the detection unit 302 detects the human face;

The second determination unit 304 is configured to determine a target model picture corresponding to the angle value and face shape determined by the first determination unit 303 .

The obtaining unit 301 is also specifically used for:

Obtain the glasses style selected by the user;

The third determination unit 305 is configured to determine the glasses picture corresponding to the glasses style acquired by the acquisition unit 301 according to the angle value determined by the first determination unit 303;

Scaling unit 306, configured according to the proportional relationship between the second distance in the target model picture determined by the second determination unit 304 and the first distance between the center points of the two eyes in the human face determined by the first determination unit Perform zoom processing on the glasses picture determined by the third determining unit 305, wherein the second distance is the distance between the center points of the eyes of the model in the target model picture;

The first superimposing unit 307 is configured to superimpose the glasses picture scaled by the scaling unit 306 with the human face detected by the detection unit 302 .

As a possible implementation manner, the second determining unit 304 is specifically configured to:

According to the angle value, the glasses picture corresponding to the glasses style is searched from the image library.

As a possible implementation manner, the first superimposing unit 307 is specifically configured to:

The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face.

As a possible implementation manner, as shown in FIG. 3b, the first determination unit 303 in FIG. 3a includes: a selection unit 3031 and a first determination subunit 3032, specifically as follows:

A selection unit 3031, configured to select a face i among the plurality of faces when the detection unit 302 detects a plurality of faces, wherein the face i is any one of the plurality of faces Face;

The first determining subunit 3032 is configured to determine the angle value, face shape and center point of the two eyes of the face i selected by the selection unit 3031 .

As a possible implementation manner, as shown in FIG. 3c, the acquiring unit in FIG. 3a or FIG. 3b is also specifically used for:

Obtain the scene mode selected by the user;

Mobile terminals also include:

The second superimposing unit is configured to superimpose the reflective scene image corresponding to the scene mode acquired by the acquiring unit 301 on the lens area of the glasses after being superimposed by the first superimposing unit 307 .

Through the mobile terminal described in the embodiment of the present invention, the image input by the user can be obtained; face detection is performed on the image; when a face is detected, the angle value of the face, the shape of the face and the face are determined the center point of the two eyes; determine the target model picture corresponding to the angle value and the face shape; obtain the glasses style selected by the user; determine the glasses picture corresponding to the glasses style according to the angle value; The proportional relationship between the second distance in the picture and the first distance between the center points of the two eyes in the human face performs scaling processing on the glasses picture, wherein the second distance is the distance in the target model picture The distance between the center points of the two eyes of the model; superimposing the zoomed glasses picture with the human face. Therefore, the user can more directly observe the wearing effect of the glasses, which improves the user experience.

Please refer to FIG. 4 , which is a schematic structural diagram of a second embodiment of a mobile terminal provided by an embodiment of the present invention. The mobile terminal described in this embodiment includes: at least one input device 1000; at least one output device 2000; at least one processor 3000, such as a CPU; and memory 4000, the above-mentioned input device 1000, output device 2000, processor 3000 and The memory 4000 is connected via a bus 5000 .

Wherein, the above-mentioned input device 1000 may specifically be a camera, a physical button, a touch screen, a touch pad or a stylus.

The aforementioned output device 2000 may specifically be a display screen.

The above-mentioned memory 4000 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a magnetic disk memory. The above-mentioned memory 4000 is used to store a set of program codes, and the above-mentioned input device 1000, output device 2000 and processor 3000 are used to call the program codes stored in the memory 4000, and perform the following operations:

The above-mentioned processor 3000 is used for

Get the image entered by the user;

Perform face detection on the image;

In the case of detecting a human face, determine the angle value of the human face, the face shape and the center point of the two eyes of the human face;

Determining a target model picture corresponding to the angle value and the face shape;

Obtain the glasses style selected by the user;

determining the glasses picture corresponding to the glasses style according to the angle value;

According to the proportional relationship between the second distance in the target model picture and the first distance between the center points of the two eyes in the face, the glasses picture is scaled, wherein the second distance is the The distance between the center points of the eyes of the model in the target model image;

and superimposing the zoomed glasses picture with the human face.

As a possible implementation manner, when a human face is detected, the processor 3000 determines the angle value of the human face, the shape of the face, the center point of the two eyes of the human face, and the center point of the two eyes The first distance between consists of:

In the case of detecting a plurality of human faces, selecting a human face i in the plurality of human faces, wherein the human face i is any human face in the plurality of human faces;

Determine the angle value of the face i, the face shape, and the center points of the two eyes in the face i.

As a possible implementation manner, the processor 3000 determining the glasses picture corresponding to the glasses style according to the angle value includes:

The glasses picture corresponding to the glasses style is searched from the image library according to the angle value.

As a possible implementation manner, the processor 3000 superimposing the zoomed glasses picture on the human face includes:

The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face.

As a possible implementation manner, after the processor 3000 superimposes the zoomed glasses picture on the human face, the method further includes:

Obtain the scene mode selected by the user;

A picture of glasses corresponding to the scene mode is selected from a preset picture library and superimposed on the face of the person.

In specific implementation, the input device 1000, the output device 2000 and the processor 3000 described in the embodiment of the present invention can execute the method described in the first embodiment and the second embodiment of a virtual glasses try-on method provided by the embodiment of the present invention. The described implementation manner may also execute the implementation manner of the terminal described in the first embodiment of a mobile terminal provided by the embodiment of the present invention, which will not be repeated here.

Through the mobile terminal described in the embodiment of the present invention, the image input by the user can be obtained; face detection is performed on the image; when a face is detected, the angle value of the face, the shape of the face and the face are determined the center point of the two eyes; determine the target model picture corresponding to the angle value and the face shape; obtain the glasses style selected by the user; determine the glasses picture corresponding to the glasses style according to the angle value; The proportional relationship between the second distance in the picture and the first distance between the center points of the two eyes in the human face performs scaling processing on the glasses picture, wherein the second distance is the distance in the target model picture The distance between the center points of the two eyes of the model; superimposing the zoomed glasses picture with the human face. Therefore, the user can more directly observe the wearing effect of the glasses, which improves the user experience.

An embodiment of the present invention also provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all steps of any one of the signal processing methods described in the above method embodiments when executed.

In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence. Because according to the present invention, certain steps may be carried out in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the above units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical or other forms.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the above integrated units are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, server, or network device, etc., specifically, a processor in the computer device) execute all or part of the steps of the above-mentioned methods in various embodiments of the present invention. Wherein, the aforementioned storage medium may include: U disk, mobile hard disk, magnetic disk, optical disc, read-only memory (English: Read-OnlyMemory, abbreviation: ROM) or random access memory (English: RandomAccessMemory, abbreviation: RAM), etc. Various media that can store program code.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions recorded in each embodiment are modified, or some of the technical features are replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (10)

1. A virtual glasses try-on method, characterized in that, comprising: Get the image entered by the user; Perform face detection on the image; In the case of detecting a human face, determine the angle value of the human face, the face shape and the center point of the two eyes of the human face; Determining a target model picture corresponding to the angle value and the face shape; Obtain the glasses style selected by the user; determining the glasses picture corresponding to the glasses style according to the angle value; According to the proportional relationship between the second distance in the target model picture and the first distance between the center points of the two eyes in the face, the glasses picture is scaled, wherein the second distance is the The distance between the center points of the eyes of the model in the target model image; superimposing the zoomed glasses picture with the human face. 2. The method according to claim 1, wherein, when a human face is detected, determine the angle value of the human face, the shape of the face and the center point of the two eyes of the human face and the The first distance between the center points of the eyes includes: In the case of detecting a plurality of human faces, selecting a human face i in the plurality of human faces, wherein the human face i is any human face in the plurality of human faces; Determine the angle value of the face i, the face shape, and the center points of the two eyes in the face i. 3. The method according to claim 1, wherein the determining the glasses picture corresponding to the glasses style according to the angle value comprises: According to the angle value, the glasses picture corresponding to the glasses style is searched from the image library. 4. The method according to claim 1, wherein said superimposing the glasses picture after said scaling process with said human face comprises: The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face. 5. The method according to any one of claims 1 to 4, wherein, after superimposing the zoomed glasses picture and the human face, the method further comprises: Obtain the scene mode selected by the user; A picture of glasses corresponding to the scene mode is selected from a preset picture library and superimposed on the face of the person. 6. A mobile terminal, characterized in that, comprising: an acquisition unit, configured to acquire an image input by a user; a detection unit, configured to perform face detection on the image acquired by the acquisition unit; The first determination unit is configured to determine the angle value of the human face, the shape of the face, and the center point of the two eyes of the human face when the detection unit detects the human face; A second determination unit, configured to determine a target model picture corresponding to the angle value and face shape determined by the first determination unit; The acquisition unit is also specifically used for: Obtain the glasses style selected by the user; A third determination unit, configured to determine the glasses picture corresponding to the glasses style acquired by the acquisition unit according to the angle value determined by the first determination unit; The scaling unit is used to calculate the ratio according to the ratio between the second distance in the target model picture determined by the second determination unit and the first distance between the center points of the two eyes in the human face determined by the first determination unit. The glasses picture determined by the third determining unit is subjected to scaling processing, wherein the second distance is the distance between the center points of the two eyes of the model in the target model picture; The first superimposing unit is configured to superimpose the glasses picture after scaling processing by the scaling unit with the human face detected by the detection unit. 7. The mobile terminal according to claim 6, wherein the first determining unit comprises: A selection unit, configured to select a face i among the plurality of faces when the detection unit detects a plurality of faces, wherein the face i is any one of the plurality of faces; The first determination subunit is used to determine the angle value, face shape and center point of the two eyes of the face i selected by the selection unit. 8. The mobile terminal according to claim 6, wherein the second determining unit is specifically configured to: According to the angle value, the glasses picture corresponding to the glasses style is searched from the image library. 9. The mobile terminal according to claim 6, wherein the superposition unit is specifically used for: The zoomed glasses picture is overlaid on the human face according to the positional relationship between the center points of the two eyes of the human face. 10. The mobile terminal according to any one of claims 6 to 9, wherein the acquiring unit is further specifically configured to: Obtain the scene mode selected by the user; The mobile terminal also includes: The second superimposing unit is configured to select a picture of glasses corresponding to the scene mode acquired by the acquiring unit from a preset picture library and superimpose it on the human face.