Method for acquiring human-face image, human-face discrimination and discriminating system

A face image and recognition system technology, which is applied in face image generation, face recognition method and its system field, can solve the problems of low recognition rate, limited application field, poor user acceptance, etc., and achieve the best recognition effect, face The effect of image stabilization

Active Publication Date: 2008-01-09
北京中科奥森科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some of these methods require three-dimensional modeling of the face, while others assume the shape of the face, and these limitations make the operability of face recognition technology greatly reduced, and it is difficult to achieve good results
[0037] In the application of face image recognition technology, a face recognition access control and attendance system has been disclosed, such as Chinese patent ZL99117360.x, but this patent only discloses how to use face image recognition technology to apply in access control and attendance systems , did not conduct in-depth analysis on the effects and stability of face image acquisition, recognition and processing, such as the influence of changes in skin tone, facial hair, hairstyle, glasses, expressions, posture and light
The recognition rate of the scheme is still low in the case of light changes, so its application field is also limited.
[0038] In addition, due to the high recognition rate of iris recognition technology, there is also the use of iris recognition for identity verification, for example, the product of Iridian company in the United States, but the infrared iris image acquisition device is relatively complicated and has high manufacturing cost, so it is widely used in many occasions. limit
Although Chinese patent ZL99110825.6 also discloses a small portable opto-mechanical device, this device also has problems such as use and inconvenient use by users.
Because the iris alignment mark is too small, the user is required to cooperate too closely to adjust the relative angle and position of the eye and the camera device, which is inconvenient to use and operate, resulting in poor user acceptance
In addition, such image acquisition, recognition and processing systems have problems in installation, maintenance and automation control

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 acquiring human-face image, human-face discrimination and discriminating system
  • Method for acquiring human-face image, human-face discrimination and discriminating system
  • Method for acquiring human-face image, human-face discrimination and discriminating system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0098] In Fig. 4a, the implementation method of the face image recognition system of the present invention is disclosed, including the following steps:

[0099] Step S100, start the face recognition system 420;

[0100] Step S110, the human body approaches the face recognition system 420, triggers the infrared sensor switch 426, and makes the active light source 421 irradiate the face area;

[0101] Step S120, the imaging device 422 tracks the human face along with the area illuminated by the active light source 421 to shoot;

[0102] Step S130, the imaging device 422 transmits at least one frame of image captured to the image data processing system (such as a PC, or a data processor) 430;

[0103] Step S140, the data processor 430 searches, detects and locates human eyes and / or human faces from the frame image;

[0104] Step S150, judging whether the detection of human eyes and / or human face is successful? , if yes, execute step S160, otherwise execute step S130;

[0105]...

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 method and system of getting human face images, which use initiative lamp-house to irradiate the token area of human face; during identifying the faces, using electron image collection means used in the initiative lamp house to take photos in order to get corresponding images, and further, transmitting the said images to corresponding electron handle device to take the process of identifying the human faces. The invention can efficiently reduce that the change of light influence on the human face images in different condition of irradiation. On using, using initiative lamp house to irradiate the human faces, so as to preciously identify the faces in various irradiation conditions. In the imaging of the human faces, as the influence of beam intensity of initiative lamp house is stronger than beam intensity of environment lamp-house, hence collected faces' images is most stable, and getting the best results of computer identifying.

Description

technical field [0001] The invention relates to the technical field of computer image recognition and processing, in particular to a face image generation, face recognition method and system thereof, which use active light sources for face illumination during the face recognition process. Background technique [0002] Face recognition is a biometric recognition technology based on computer, image processing, pattern recognition and other technologies. In recent years, especially after the 9.11 terrorist attack on the United States, all countries in the world put safety first. Therefore, face recognition technology has received more attention than before. [0003] Biometric technology is a high-tech identification technology that mainly relies on the physical characteristics of the human body for identity verification. Human body characteristics such as fingerprints, palm prints, iris, deoxyribose nucleic acid (DNA) and facial appearance have the uniqueness and stability inh...

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): G06K9/00G03B15/02G06K9/78
CPCG06K9/00255G06V40/166
Inventor 高奇
Owner 北京中科奥森科技有限公司
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