Liveness detection system and method based on face identification
A technology of living body detection and face recognition, applied in the field of face recognition, can solve the problems of high equipment cost and restricted use occasions, and achieve the effect of small calculation amount, wide application range and good user experience.
Active Publication Date: 2017-09-01
武汉神目信息技术有限公司
View PDF5 Cites 25 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method requires at least two cameras to collect face images during detection, the cost of equipment is high, and the application occasions are severely restricted
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 Construction
[0055] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0056] Such as figure 1 As shown, as a first aspect of the present invention, a kind of living body detection method based on face recognition is provided, comprising the following steps:
[0057] S1, taking multiple pictures of live faces and photo faces from far to near, and then training a classification model through a convolutional neural network;
[0058] Specifically, in order to realize liveness detection in the process of face recognition, it is first necessary to train live faces and photo faces to obtain a classification model of which is a live face and which is a photo face.
[0059] S2. Collect the image of the face to be recognized, and input it into the above classification model to obtain the recognition result.
[0060] Specifically, after the classification model is obtained, the picture of the face to be recognized is collected and...
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 liveness detection system and method based on face identification. The method is characterized by carrying out training through a convolutional neural network to obtain a corresponding classification model; and then, carrying out liveness or non-liveness judgment on a face picture to be identified by inputting the picture to be identified to the classification model to obtain an identification result. The method can realize liveness detection without manual feature analysis of the picture nor specific command action coordination, so that user experience is good; in the use process, liveness detection can be realized by utilizing only one device having a shooting function, such as a mobile phone, to carry out different distances of face image collection, and thus use range is wide; and besides, compared with an optical-flow-method live detection method, the method in the invention can collect a plurality of pictures from far to near and does not need to collect consecutive video frames, so that the amount of target data to be processed is far less than that of the optical-flow-method live detection method, calculation amount is small, and the method is better in real-time performance and practicality.
Description
technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition-based living body detection system and a method thereof. Background technique [0002] In the biometric system, in order to prevent malicious parties from forging and stealing other people's biometrics for identity authentication, the biometric system needs to have the function of living body detection, that is, to judge whether the submitted biometrics come from a living individual. [0003] General biometric living detection technology utilizes people's physiological characteristics. For example, living fingerprint detection can be based on information such as finger temperature, perspiration, and electrical conductivity. Live face detection can be based on information such as head movement, breathing, and red-eye effect. , live iris detection can be based on iris vibration characteristics, eyelashes and eyelid movement information, pupil contraction...
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 IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06V40/172G06F18/2411G06F18/214
Inventor 郑山奇卓越姚琪黄瑞罗畅刘靖峰
Owner 武汉神目信息技术有限公司