Construction method and, device and equipment offor high-precision facial expression library, equipment and storage medium

A construction method and high-precision technology, applied in the field of image processing, can solve the problems of large amount of data, high construction cost of high-precision facial expression database, and large amount of data processing

Active Publication Date: 2020-09-11
TENCENT TECH (SHENZHEN) CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when using the above method to generate a high-precision facial expression library, it is necessary to use professional equipment to collect facial expression data, and because the facial expression data collected by professional equipment has a large amount of data, the subsequent data processing has a large amount of processing. It leads to high construction cost and low construction efficiency of high-precision facial expression library

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
  • Construction method and, device and equipment offor high-precision facial expression library, equipment and storage medium
  • Construction method and, device and equipment offor high-precision facial expression library, equipment and storage medium
  • Construction method and, device and equipment offor high-precision facial expression library, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0033] Computer vision (Computer Vision, CV) is a science that studies how to make machines "see". To put it further, it refers to the use of cameras and computers instead of human eyes to identify, track and measure machine vision, and further Graphics processing makes computer processing an image that is more suitable for human eyes to observe or sent to the instrument for detection. As a scientific discipline, computer vision studies related theories and technologies, trying to build artificial intelligence systems that can obtain information from images or multidimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, optical character rec...

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 a construction method and device and for a high-precision facial expression library, equipment and a storage mediumconstruction method, device and equipment of a high-precisionfacial expression library and a storage medium, and relates to the field of image processing. The method comprises the following steps: acquiring high-precision face data and low-precision face data;constructing an expression base based on the high-precision residual data of the high-precision face data; screening target low-precision residual error data from the low-precision residual error data based on a fitting result of the expression base to the low-precision residual error data of the low-precision face data, with the fitting error of the target low-precision residual error data beinghigher than the fitting error of other low-precision residual error data; and t. The expression base is iteratively updated through the target low-precision residual data and the high-precision residual data, so that a high-precision facial expression library can be obtained, and the high-precision facial expression library is the expression base obtained when iteration is ended. The data demandfor high-precision face data is reduced while the precision of the high-precision face expression library is ensured, so that the construction cost of the high-precision face expression library is reduced, and the construction efficiency of the high-precision face expression library is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of image processing, and in particular to a method, device, equipment and storage medium for constructing a high-precision facial expression database. Background technique [0002] With the research and progress of artificial intelligence technology, artificial intelligence technology has been researched and applied in many fields. Facial expression driving is a technology that drives virtual objects to simulate human facial expressions in the real world. It is widely used in scenarios such as animation expression generation and virtual character driving. [0003] In related technologies, before realizing the facial expression driving, it is necessary to build a facial expression library, so that the facial expression parameters collected and the facial expression library can be used to restore the facial expressions. Since the effect of facial expression restoration is closely related to ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/51G06F16/583G06K9/62
CPCG06F16/51G06F16/5854G06F18/2135Y02D10/00
Inventor 王盛林祥凯
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products