Face image deformation method and device, electronic equipment and storage medium
A face image, deformation coefficient technology, applied in image data processing, graphic image conversion, electrical digital data processing, etc., can solve the problem of not meeting the individual needs of users, and achieve the effect of high degree of freedom and increased viscosity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0076] Such as Figure 5 As shown, the above-mentioned region to be deformed in the face image is determined according to the initial trigger position of the trigger operation, including:
[0077] In step 201, the distance between the initial trigger position and a plurality of preset control areas is calculated.
[0078] In step 202, the preset control area with the smallest distance from the initial trigger position is determined as the area to be deformed.
[0079]In this embodiment, it can be understood that multiple control areas are set in the face image in advance, and each control area corresponds to a face area. For example, control area 1 corresponds to the left eye area of the face, and control area 2 corresponds to the left eye area of the face. The mouth area of the face, etc., different preset control areas can be calibrated by big data, or calibrated by the user according to the individual needs. Divide different preset control areas.
[0080] After the...
example 2
[0083] Such as Figure 7 As shown, the above-mentioned region to be deformed in the face image is determined according to the initial trigger position of the trigger operation, including:
[0084] In step 301, among the plurality of identification information preset on the face image, the target identification information corresponding to the initial trigger position is determined, wherein each identification information in the plurality of identification information corresponds to the target identification information on the face image. an image area of .
[0085] Wherein, the identification information may be in the form of an icon, a text, or a combination of one or more of dynamic effects. In this embodiment, such as Figure 8 As shown, a plurality of identification information is preset on the face image (multiple identification information may or may not be displayed), wherein each identification information is used as a control module of an image area in the face ima...
example 3
[0090] Such as Figure 9 As shown, the above-mentioned region to be deformed in the face image is determined according to the initial trigger position of the trigger operation, including:
[0091] Step 401, determine the key points of the target face in the face image according to the initial trigger position.
[0092] In this embodiment, the target face key point is determined in the face image according to the initial trigger position, and the target face key point can be the center point of the area corresponding to the initial trigger position, or a pre-trained convolutional neural network, such as Figure 10 As shown, the convolutional neural network can obtain multiple face key points (101 in the figure) after inputting the face image, and then determine the face key point associated with the initial trigger position as the target face key point , when the initial trigger position overlaps a key point of the face, this key point of the face is used as the key point of t...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More