Image processing method and mobile terminal

Abstract

The invention provides an image processing method and a mobile terminal. The method includes: identifying the face type and facial features of the face in the target image, determining the first makeup type matching the face type and the facial features; determining the target user corresponding to the face, and determining the second makeup based on the makeup preferences of the target user type; according to the first makeup type and the second makeup type, determine the target makeup type; based on the target makeup type, perform makeup processing on the face in the target image. The present invention can combine the user's face shape and facial features as well as the user's preferences for makeup to apply makeup to the face in the image, thereby avoiding the time-consuming process of choosing a suitable makeup from the various makeups provided by the system. longer problem.

Description

technical field

[0001] The present invention relates to the technical field of image processing, in particular to an image processing method and a mobile terminal. Background technique

[0002] With the continuous development of science and technology, the current mobile terminals generally have the function of applying makeup to the captured face images. The camera function of the mobile terminal can provide a variety of makeup for the user to choose, and then use the makeup selected by the user to update the captured image. Apply makeup to the face in the

[0003] However, the makeup look selected by the user may not be suitable for the user, so the user needs to try many times before he can find a makeup look suitable for himself to apply makeup to the face area.

[0004] In the process of implementing the present invention, the inventors found that the related art schemes for applying makeup to the face of the image generally have the problems that it takes a long time ...

Examples

no. 1 example

[0030] refer to figure 1 , showing a flowchart of an image processing method according to an embodiment of the present invention, which is applied to a mobile terminal, and the method may specifically include the following steps:

[0031] Step 101, identifying the face type and facial features type of the face in the target image;

[0032] Among them, the face type includes but not limited to round face, heart-shaped face, melon-shaped face, diamond-shaped face, Chinese-character face and other face types.

[0033] The five sense organs include eyes, eyebrows, nose, ears and mouth. Therefore, the five senses type here means the type of each organ in the above five senses. For example, the type of eyes can include but not limited to big eyes with double eyelids, small eyes with double eyelids, phoenix eyes, single eyelids, etc.; the type of nose can include but not limited to high nose bridge and big nose wings, flat nose bridge and small nose wings, high nose bridge and smal...

no. 2 example

[0072] On the basis of the first embodiment, when step 101 is executed, the figure 2 shown in the method to achieve:

[0073] Step 201, performing face feature recognition on the two-dimensional RGB image, and determining a plurality of feature points;

[0074] Among them, the facial features in the two-dimensional RGB image can be detected, so as to determine various facial feature points in the image. For example, the feature points of facial features and face shape.

[0075] Wherein, the mobile terminal may have a 3D camera, and the method of the embodiment of the present invention may firstly control the 3D camera to take pictures of the user's face, so as to obtain a three-dimensional image, that is, a target image.

[0076] Of course, if the camera is a 2D camera and the target image is a two-dimensional RGB image, then a depth image corresponding to the two-dimensional RGB image and a three-dimensional point cloud image corresponding to the two-dimensional RGB image ...

no. 3 example

[0130] refer to image 3A flow chart showing an image processing method according to another embodiment of the present invention may specifically include the following steps:

[0131] Step 301: Carry out machine learning on the makeup selected by the user on the captured face image, and generate a first correspondence between the user and the type of makeup he likes, and a second correspondence between the user and the facial features;

[0132] Wherein, after the user uses the method of the embodiment of the present invention for multiple times to process the makeup and photographing of the face image, the method of the embodiment of the present invention can record and learn the makeup looks selected by the user each time, so as to determine the makeup that the user likes to use. Makeup type, generate the first corresponding relationship between the user and the favorite type of makeup.

[0133] In addition, in the embodiment of the present invention, the identity of the use...

technical field

[0001] The present invention relates to the technical field of image processing, in particular to an image processing method and a mobile terminal. Background technique

[0002] With the continuous development of science and technology, the current mobile terminals generally have the function of applying makeup to the captured face images. The camera function of the mobile terminal can provide a variety of makeup for the user to choose, and then use the makeup selected by the user to update the captured image. Apply makeup to the face in the

[0003] However, the makeup look selected by the user may not be suitable for the user, so the user needs to try many times before he can find a makeup look suitable for himself to apply makeup to the face area.

[0004] In the process of implementing the present invention, the inventors found that the related art schemes for applying makeup to the face of the image generally have the problems that it takes a long time ...

Examples

no. 1 example

[0030] refer to figure 1 , showing a flowchart of an image processing method according to an embodiment of the present invention, which is applied to a mobile terminal, and the method may specifically include the following steps:

[0031] Step 101, identifying the face type and facial features type of the face in the target image;

[0032] Among them, the face type includes but not limited to round face, heart-shaped face, melon-shaped face, diamond-shaped face, Chinese-character face and other face types.

[0033] The five sense organs include eyes, eyebrows, nose, ears and mouth. Therefore, the five senses type here means the type of each organ in the above five senses. For example, the type of eyes can include but not limited to big eyes with double eyelids, small eyes with double eyelids, phoenix eyes, single eyelids, etc.; the type of nose can include but not limited to high nose bridge and big nose wings, flat nose bridge and small nose wings, high nose bridge and smal...

no. 2 example

[0072] On the basis of the first embodiment, when step 101 is executed, the figure 2 shown in the method to achieve:

[0073] Step 201, performing face feature recognition on the two-dimensional RGB image, and determining a plurality of feature points;

[0074] Among them, the facial features in the two-dimensional RGB image can be detected, so as to determine various facial feature points in the image. For example, the feature points of facial features and face shape.

[0075] Wherein, the mobile terminal may have a 3D camera, and the method of the embodiment of the present invention may firstly control the 3D camera to take pictures of the user's face, so as to obtain a three-dimensional image, that is, a target image.

[0076] Of course, if the camera is a 2D camera and the target image is a two-dimensional RGB image, then a depth image corresponding to the two-dimensional RGB image and a three-dimensional point cloud image corresponding to the two-dimensional RGB image ...

no. 3 example

[0130] refer to image 3A flow chart showing an image processing method according to another embodiment of the present invention may specifically include the following steps:

[0131] Step 301: Carry out machine learning on the makeup selected by the user on the captured face image, and generate a first correspondence between the user and the type of makeup he likes, and a second correspondence between the user and the facial features;

[0132] Wherein, after the user uses the method of the embodiment of the present invention for multiple times to process the makeup and photographing of the face image, the method of the embodiment of the present invention can record and learn the makeup looks selected by the user each time, so as to determine the makeup that the user likes to use. Makeup type, generate the first corresponding relationship between the user and the favorite type of makeup.

[0133] In addition, in the embodiment of the present invention, the identity of the use...

Images