Image processing method, device, equipment and medium
An image processing and processor technology, applied in the field of image processing, can solve problems such as uneven face contours, achieve the effects of less adjustment data, low computing power consumption, and increased speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] figure 1 It is a flow chart of an image processing method provided by Embodiment 1 of the present invention. This embodiment is applicable to solving the problem of face contour deformation in online videos such as live video broadcasting. The method can be provided by any embodiment of the present invention It can be implemented by an image processing device, which can be composed of hardware and / or software, and can generally be integrated into computer equipment.
[0033] Such as figure 1 As described, the image processing method provided in this embodiment includes the following steps:
[0034] S110. Recognize the face image to obtain face anchor points, and construct an original face mesh, where vertices of the original face mesh at least include the face anchor points.
[0035] The face image may refer to a static image, or may refer to an image frame of an online video such as a live video broadcast, where the face image includes a face.
[0036] Face position...
Embodiment 2
[0049] This embodiment is embodied on the basis of the above-mentioned embodiments, wherein, among the face contour anchor points, the target face contour anchor points that do not conform to the human face contour smoothing rule will be determined, specifically:
[0050] Vertically project the anchor point of the face contour onto the target reference line perpendicular to the central axis of the face;
[0051] Acquiring a human face contour anchor point in turn as the current human face contour anchor point in the human face contour anchor points;
[0052] Calculate respectively the first projection distance and the second projection distance between the current face contour anchor point and the previous face contour anchor point and the next face contour anchor point on the target reference line;
[0053] If the first projection distance and the second projection distance do not meet the smoothing law of the face contour on the side of the face where the current face contou...
Embodiment 3
[0089] This embodiment is embodied on the basis of the above-mentioned embodiments, wherein, the constructed face mesh is a triangular mesh; correspondingly, according to the mapping relationship between the target face mesh and the original face mesh, the original face Each pixel in the grid is correspondingly mapped to the target face grid, specifically:
[0090] Obtaining one of the original face grids sequentially as the current processing grid;
[0091] Obtaining a target deformation grid matching the current processing grid in the target face grid;
[0092] calculating a mapping relationship matrix between the current processing grid and the target deformation grid;
[0093] According to the mapping relationship matrix, each pixel point in the currently processed grid is mapped to the target deformed grid until the processing of all original grids is completed.
[0094] Such as Figure 7 As shown, the image processing method provided in this embodiment includes the fo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More