Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for automatically carrying out facial recognition

A face recognition and face technology, applied in the information field, can solve problems such as high cost, difficulty in increasing character matching, and uncontrollable actual results

Inactive Publication Date: 2013-06-12
SHANGHAI YUANLIAN ADVERTISEMENT
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]1. Various factors such as the editor's personal experience, concentration and mental state all affect the accuracy of character records
That is, artificial identification of people, the actual result is uncontrollable
[0005]2. In the face of massive video in human society, watching and identifying each minute one by one, in actual operation, on the one hand, the cost is extremely high, on the other hand, it can only Limited video programs are recorded
[0006]3. An actor who is not well-known when editing and recording video characters will need to manually carry out a lot of repetitive labor when the program that the actor starred in needs to be sorted out in the future. possible quests that are difficult to add to character matching

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
  • Method for automatically carrying out facial recognition
  • Method for automatically carrying out facial recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] See figure 1 As shown, this figure is a flow chart of the steps of the method for automatically performing video face recognition.

[0026] Step 1. Before the video program is identified, at first the facial portrait data of the person to be identified is extracted from the database through the network, and stored in the memory of the computer performing the identification operation;

[0027] Step 2. Use any existing software to implement the following functions:

[0028] 1. Scan the video frame by frame, extract the information of each frame and convert the pixels in the frame into digital information;

[0029] 2. Match the digital information of the video frame with the facial portrait data stored in the memory;

[0030] 3. If the facial portrait data is encrypted, it should be compared after decryption;

[0031] 4. If special information is digitally stored in the facial portrait data, corresponding comparisons should be made, such as the distance between the eyes...

Embodiment 2

[0034] See figure 2 As shown, this figure is a flow chart of the steps of setting up a facial portrait database in the method for automatically performing video facial recognition.

[0035] Step 1. First, digitize the facial portraits of the people who need to be identified, and collect as many facial portraits as possible from different angles in different periods;

[0036] Step 2. Through the computer, any existing software can be used to digitize the image information, that is, to convert the pixels in the photo into digital information for storage.

[0037] During the implementation of this step, the following points should be paid attention to:

[0038] 1. It should be recognized and stored according to the outline of the face, not the frame of the photo;

[0039] 2. The digital results should be combined with the design of the database;

[0040] 3. You can add the collection of portrait-specific information according to your own application, such as the distance betw...

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 provides a method for automatically carrying out facial recognition. The method comprises the following steps of firstly extracting face portrait data of a person to be identified from a face portrait database through a network by utilizing an information extracting module, and saving the face portrait data into an internal memory of a computer for carrying out recognition computation; secondly by utilizing a scanning and comparing module, scanning a video to be identified frame by frame, carrying out code matching comparison on the data of each frame and the human face information data saved in the internal memory in the information extracting module, and importing associated data into an information recording module if the code matching comparison succeeds; and finally by utilizing the information recording module, saving information such as saved successfully compared video names and matching time in the scanning and comparing module into the database. The method for automatically carrying out facial recognition disclosed by the invention has the advantages of construction, video recognition, record and storage of the face portrait database of movie and television stars and famous persons in video programs.

Description

technical field [0001] The invention relates to the field of information technology, in particular to a method for automatic facial recognition. Background technique [0002] With the explosive increase of digital video, and the accelerated pace of people's life. Because watching a video will consume a lot of people's time, people urgently need to know which characters appear in the video and whether they are the characters they are interested in and love before watching the video. [0003] Traditionally, editors manually watch the video and record the people involved in the video to obtain a list of characters appearing in the video program. However, this method has the following disadvantages: [0004] 1. Various factors such as the editor's personal experience, concentration, and mental state all affect the accuracy of character records. That is, people are identified manually, and the actual result is uncontrollable. [0005] 2. Faced with the massive amount of video...

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): G06K9/00
Inventor 江兰曹虹蕾
Owner SHANGHAI YUANLIAN ADVERTISEMENT
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com