Automatic face annotation method and system

A technology of automatic labeling and face, which is applied in CCTV system, computer components, natural language data processing, etc.

Active Publication Date: 2015-11-25
TCL CORPORATION
View PDF9 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Facial recognition in an unconstrained environment is challenging due to large variations in orientation, brightness, and shape

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
  • Automatic face annotation method and system
  • Automatic face annotation method and system
  • Automatic face annotation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The parts shown in the drawings will be cited for specific description, elaborating specific technical implementations of the present invention. Numerals quoted in the specification represent corresponding parts in the drawings.

[0015] figure 1 It is the working system 100 in the specific embodiment of the present invention. Such as figure 1 As shown, the working system 100 includes: a TV 102 , a remote controller 104 , a server 106 , a user 108 , and a network system 110 . Of course other suitable devices may also be included.

[0016] The TV 102 can be any suitable type of TV, such as plasma TV, LCD TV, rear projection TV, smart TV or non-smart TV. The television 102 may also include a computing system, such as a personal computer, a PDA, or a smart phone. Further, the TV set 102 may also be any content demonstration device controlled by the remote controller 104 and capable of presenting multiple programs on one or more channels.

[0017] The remote control 1...

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

An automatic face annotation method is provided. The method includes dividing an input video into different sets of frames, extracting temporal and spatial information by employing camera take and shot boundary detection algorithms on the different sets of frames, and collecting weakly labeled data by crawling weakly labeled face images from social networks. The method also includes applying face detection together with an iterative refinement clustering algorithm to remove noise of the collected weakly labeled data, generating a labeled database containing refined labeled images, finding and labeling exact frames containing one or more face images in the input video matching any of the refined labeled images based on the labeled database, labeling remaining unlabeled face tracks in the input video by a semi-supervised learning algorithm to annotate the face images in the input video, and outputting the input video containing the annotated face images.

Description

technical field [0001] The invention relates to the technical field of video information and face labeling, in particular to a face automatic labeling method and system using semi-supervised learning in social network data video. Background technique [0002] With the rapid development of video capture equipment, in recent years, the rapid growth of network broadband and online and offline video sharing in various forms of social network video content has increased dramatically. With the above-mentioned development trend, there is a great demand for annotation in a large number of videos in a wide range of various applications. Manual video annotation is time-consuming and labor-intensive. Therefore, automatic annotation of videos has received a lot of attention in recent years. In videos, faces are the most important and frequently occurring objects, however, automatic human body annotation can be applied in many aspects, such as security, rich content generation, medical...

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): H04N21/44H04N7/18G06K9/00G06K9/62
CPCG06F17/24G06F17/30G06K9/00G06K9/62G06T5/00H04N7/18H04N21/44008G06V40/172G06V20/41G06F18/2155G06V20/30G06V20/49G06T5/002G06T2207/10016G06T2207/30201G06F16/21G06F16/951G06F16/5846G06F40/169G06V40/161G06F18/2411
Inventor 彭亮杨益敏汪灏泓
Owner TCL CORPORATION
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap