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

Feature extraction method and device and terminal equipment

A feature extraction and face feature technology, applied in the field of video processing, can solve the problems that video feature extraction results cannot accurately represent video character features, video feature extraction is inaccurate, etc.

Pending Publication Date: 2020-06-05
GUANGDONG OPPO MOBILE TELECOMM CORP LTD
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to propose a feature extraction method, device and terminal equipment to solve the problem that the video feature extraction is inaccurate when the existing technology is processing the video, resulting in that the video feature extraction result cannot accurately represent the characteristics of the video characters

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
  • Feature extraction method and device and terminal equipment
  • Feature extraction method and device and terminal equipment
  • Feature extraction method and device and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0045] It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

[0046] Herein, use of suffixes such as 'module', 'part' or 'unit' for denoting elements is only for facilitating description of the present invention and has no specific meaning by itself. Therefore, "module" and "...

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 is applicable to the technical field of video processing, and provides a feature extraction method and device and terminal equipment. The method comprises the following steps: extractinga key frame picture of a to-be-processed target video; obtaining N faces in the key frame picture, counting the number of video figures in the key frame picture according to the N faces, and obtaining N face features based on the key frame picture according to the N faces; de-noising the N face features to obtain M de-noised features; and performing clustering processing on the M denoising features according to the number of the video figures to obtain K clustering centers, and taking the denoising features in the same clustering center as user facial features of the same video figure. According to the invention, wrong clustering can be avoided, the feature identification accuracy based on the to-be-processed target video is improved, and the finally obtained user face features are in one-to-one correspondence with the video figures, i.e., the user face features can accurately represent the features of the video figures.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a feature extraction method, device and terminal equipment. Background technique [0002] Video can be regarded as a collection of multiple continuous images, and almost all the techniques used for images can be directly applied to video processing. However, the temporal dimension of video has pros and cons. The time dimension of video brings a lot of information compared to images. Taking frames as an example, it means the number of pictures transmitted in one second. Generally speaking, if the frame rate is lower than 15 frames per second, the user will play this video. There is a sense of pause. Therefore, a high number of video frames can greatly enrich the feature space. [0003] On the other hand, the higher the number of frames and the richer the features of the video, the more noise it may contain, such as lighting changes, motion blur, and so on. Whe...

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): G06K9/62G06F16/732G06F16/783
CPCG06F16/7328G06F16/784G06F18/211G06F18/23213
Inventor 彭冬炜
Owner GUANGDONG OPPO MOBILE TELECOMM CORP LTD