Unlock instant, AI-driven research and patent intelligence for your innovation.

Inter-frame filtering-based expression migration method and electronic equipment

An inter-frame filtering and expression migration technology, applied in the computer field, can solve problems affecting the accuracy and accuracy of expression migration.

Inactive Publication Date: 2017-11-10
PALMWIN INFORMATION TECH SHANGHAI
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Traditional expression transfer is generally based on the face image in the current video frame to directly drive the target image to achieve expression transfer, because a single frame of image is easily disturbed by various factors, which affects the accuracy and accuracy of expression transfer

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Inter-frame filtering-based expression migration method and electronic equipment
  • Inter-frame filtering-based expression migration method and electronic equipment
  • Inter-frame filtering-based expression migration method and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] An embodiment of the present invention provides an expression migration method based on inter-frame filtering, referring to figure 1 As shown, the method flow includes:

[0069] 102. Acquire face feature points in the current video frame.

[0070] Specifically, the process can be:

[0071] A method based on shape regression is used to locate facial landmarks in video frames. Face feature point positioning is based on face detection, and further locates the eyes, eyebrows, nose and mouth contours of the face. The feature points can be located by using the information near the feature points and the relationship between each feature point.

[0072] 104. Acquire the pose parameters of the face according to the feature points and the face feature points in the previous video frame.

[0073] Specifically, the process can be:

[0074] According to the positional relationship between the feature points in the current video frame and the corresponding feature points in the...

Embodiment 2

[0099] An embodiment of the present invention provides an expression migration method based on inter-frame filtering, referring to figure 2 As shown, the method flow includes:

[0100] 202. Acquire face feature points in the current video frame.

[0101] Specifically, the process can be:

[0102] A method based on shape regression is used to locate facial landmarks in video frames. Face feature point positioning is based on face detection, and further locates the eyes, eyebrows, nose and mouth contours of the face. The feature points can be located by using the information near the feature points and the relationship between each feature point.

[0103] 204. Acquire the pose parameters of the face according to the feature points and the face feature points in the previous video frame.

[0104] Specifically, the process can be:

[0105] According to the positional relationship between the feature points in the current video frame and the corresponding feature points in th...

Embodiment 3

[0146] An embodiment of the present invention provides an expression migration method based on inter-frame filtering, referring to image 3 As shown, the method flow includes:

[0147] 302. Acquire face feature points in the current video frame.

[0148] Specifically, the process can be:

[0149] A method based on shape regression is used to locate facial landmarks in video frames. Face feature point positioning is based on face detection, and further locates the eyes, eyebrows, nose and mouth contours of the face. The feature points can be located by using the information near the feature points and the relationship between each feature point.

[0150] 304. Acquire pose parameters of the human face according to the feature points and the facial feature points in previous video frames.

[0151] Specifically, the process can be:

[0152] According to the positional relationship between the feature points in the current video frame and the corresponding feature points in th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an inter-frame filtering-based expression migration method and electronic equipment. The method comprises the following steps of: obtaining feature points of a face in the current video frame; obtaining posture parameters of the face according to the feature points and feature points of a face in a previous video frame; carrying out inter-frame filtering on the current video frame according to the posture parameters so as to obtain an inter-frame filtered frame; obtaining feature points of a face in the inter-frame filtered frame; and carrying out expression migration on a target according to the feature points of the face in the inter-frame filtered frame. According to the method, the posture parameters of the face are obtained, inter-frame filtering is carried out on the current video frame according to the posture parameters, and expression migration is carried out on the target via the face in the inter-frame filtered frame, so that the posture parameters of the face can be obtained through the comparison between the previous frame and the current frame, thereby positioning the positions of the feature points of the face more accurately and avoiding the problem that the correctness of expression migration carried out by using the current video frame is relatively low.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an expression transfer method based on inter-frame filtering and electronic equipment. Background technique [0002] Traditional expression transfer is generally based on the face image in the current video frame to directly drive the target image to achieve expression transfer, because a single frame of image is easily disturbed by various factors, which affects the accuracy and accuracy of expression transfer . Contents of the invention [0003] In order to solve the above problems, the present invention provides an expression transfer method and electronic equipment based on inter-frame filtering. [0004] Described technical scheme is as follows: [0005] In the first aspect, a method for expression migration based on inter-frame filtering is provided, the method comprising: [0006] Obtain the face feature points in the current video frame; [0007] Obtaining the pos...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T5/50G06T17/00
CPCG06T5/50G06T17/00G06T2200/04G06T2207/20024G06T2207/20221G06T2207/30201
Inventor 武俊敏
Owner PALMWIN INFORMATION TECH SHANGHAI