A living body detection method applied to face recognition
A technology of liveness detection and face recognition, which is applied in the field of liveness detection of face recognition, can solve problems such as unfriendliness, increase cost, increase equipment, etc., and achieve high-definition photos or high-definition video to deceive the face recognition system, and the success rate High and stable effect
Active Publication Date: 2018-12-14
南京理工科技园股份有限公司
View PDF3 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In practical applications, the last category is the best, but it is not friendly and requires user participation
The second type of method needs to increase equipment and increase the cost of spending
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0049] join Figure 1 to Figure 3 , a living body detection method for face recognition of the present invention, specifically comprising the following steps:
[0050] Step 1. Model the background of the captured face, specifically adopt the method of average frame, that is, select multiple background pictures, perform image preprocessing, and then calculate the average frame; the number of background pictures is greater than or equal to ten, and perform image preprocessing The processing is specifically to denoise and grayscale the image.
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
Login to View More Abstract
The invention discloses a living body detection method applied to face recognition. The method includes: modeling the background of the current recognition environment; face detection, obtaining the position and size of the face, and at the same time serving as the initial stage for the next detection of the face Position; use the SSIM method to calculate the similarity between the background of the input face image and the modeled background image; when a face is detected, use ultrasonic waves to measure the distance between the camera and obstacles, and use the logistic regression model to obtain classification probability values f; SSIM value and f value are linearly combined to obtain the final result R, and when R is less than a certain threshold, it is considered a spoofing attack. The method of the invention has high detection success rate and good stability.
Description
technical field [0001] The invention belongs to the field of biological feature recognition security, in particular to a living body detection method applied to face recognition. Background technique [0002] With the rapid development and wide application of face recognition technology, its security has also been severely challenged. Spoofing attacks are still a fatal threat to face recognition systems. Generally speaking, in the field of face recognition, there are three methods of fraud: [0003] a. Use photos of legitimate users; [0004] b. Use videos of legitimate users; [0005] c. Use the 3D model of the legitimate user. [0006] Photo attack is the cheapest and most convenient method of deception, because face images are very easy to obtain, such as downloading from the Internet, secretly taking pictures with cameras, etc. Intruders can rotate, move and warp the photo to create a real-life look like a legitimate user to trick the facial recognition system. At ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/161
Inventor 李德强陈晗婧许小强李千目侯君孙千然
Owner 南京理工科技园股份有限公司