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

Fast Video Face Recognition Method Based on Big Data Processing

A big data processing and face recognition technology, applied in the field of video face recognition, can solve the problems of low recognition accuracy and slow recognition speed of face recognition methods

Active Publication Date: 2016-05-18
贵州华城楼宇科技有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention aims to solve the problems of slow recognition speed and low recognition accuracy of existing face recognition methods, thereby providing a fast video face recognition method based on big data processing

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
  • Fast Video Face Recognition Method Based on Big Data Processing
  • Fast Video Face Recognition Method Based on Big Data Processing

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0077] The specific embodiment one, based on the fast video face recognition method of big data processing, it comprises the following steps:

[0078] Step 1, set up face recognition database; Described database comprises image database and P sub-databases, and described P is a positive integer; Described P sub-databases are respectively embedded in P memories;

[0079] The image database is used to store the collected face images and corresponding local face feature serial data;

[0080] Each sub-database is used to store partial face feature serial data, and the method for obtaining each partial face feature serial data in each sub-database is:

[0081] Step A1, read a face image in the image database;

[0082] Step A2, take the pixel at the center between the two eyebrows of the face on the face image as the origin, take the horizontal direction as the X axis, take the vertical direction as the Y axis, and take the plane direction formed by the vertical X axis and the Y ax...

specific Embodiment approach 2

[0149] Embodiment 2. The difference between this embodiment and the fast video face recognition method based on big data processing described in Embodiment 1 is that in step B1, C wireless access points AP in each cluster jointly select a wireless access point The principle of pointing an AP as a cluster head is as follows: the preset wireless access point AP with the highest security level is the cluster head.

[0150] The specific application scenario of this embodiment is, for example, in a public security system, where each sub-server is set up in a public security bureau at each level, and is used to store the serial data of local facial features of persons within the jurisdiction. The server of the public security system with the highest level (such as the General Public Security Bureau) is selected as the cluster head.

specific Embodiment approach 3

[0151] Embodiment 3. The difference between this embodiment and the fast video face recognition method based on big data processing described in Embodiment 1 is that in step 5, the information in the broadcast request signal includes the ID of the initiating wireless access point AP and the serial data of the local facial features to be recognized.

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

A fast video face recognition method based on big data processing relates to the field of video face recognition. The purpose of the method is to solve the problems of slow recognition speed and low recognition accuracy of existing face recognition methods. In the present invention, by establishing a face recognition database, the image database is used to store the collected face images and the corresponding partial face feature serial data; and generate a partial face feature serial data for all portraits, and store them in a distributed manner in a different memory. When face recognition is required, face images are collected, and corresponding local face feature serial data are generated from the collected face images, and matching and recognition are performed by level. The invention is suitable for fast face recognition.

Description

technical field [0001] The invention relates to the field of video face recognition. Background technique [0002] Biometric recognition technology has been widely used in the field of security in recent years, and face recognition technology, as one of the efficient means, has also been widely studied. Compared with other biometric technologies, such as iris recognition and fingerprint recognition, face recognition technology has become a research and application hotspot due to its friendliness and convenience. For face recognition technology, the main direction of current research, one is accuracy; [0003] For ordinary face recognition, the current research at home and abroad has solved this problem well, such as: "Realistic 3D People Based on Multi-angle Photos" published by Huang Fu, Pan Guangzhen and others on "Electronic Test" in 2010 "Research on Face Modeling"; [0004] In 2009, Zhao Xiaogang et al published "A Review of Specific 3D Face Modeling Methods" on "Com...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/165G06V40/171G06V40/172G06V20/40
Inventor 陈文何明建舒宇顾莲军黄华杰陈志顺徐世斌
Owner 贵州华城楼宇科技有限公司