A method and system for living body detection based on improved optical flow method
A technology of living body detection and optical flow method, which is applied in deception detection, instruments, biological neural network models, etc., can solve the problems of insufficient utilization of image information, need for eigenvalue information, low popularity, etc., to improve accuracy and speed up. The effect of calculating speed and improving recognition accuracy
Active Publication Date: 2022-07-15
金现代信息产业股份有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method can avoid relatively simple movements such as the up, down, left and right directions of the entire photo, and the recognition rate of attacks on the front, rear and rotation of the camera is relatively low.
And using SVM to classify whether it is a living body detection requires artificial feature value information of photos, and the utilization rate of image information is not sufficient
The third method adopts the 3D living body detection method, which requires special hardware equipment support. At that time, a large number of camera equipment did not support 3D imaging, and the popularity was not high, so it could only be applied in specific application fields.
[0004] At the same time, in the prior art, normalization is often used for image processing for face recognition in images, which brings large calculation errors
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
[0029] In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0030] like figure 1 As shown, a method for detecting a living body based on an improved optical flow method, the method may include the following steps:
[0031] S1. Use the MTCNN algorithm to identify the face area in the image;
[0032] S2. Reduce the image to an image size of 320*240;
[0033] S3. Use the improved o...
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 based on an improved optical flow method. The method includes: identifying a face area in an image; using the improved optical flow method to calculate the optical flow of the face area to generate a feature matrix ; Use the MobilenetV2 model to extract the feature information of the matrix, and judge whether it is a living body through deep learning. Also included is a liveness detection system based on an improved optical flow method. Solve the attack mode of photo rotation and forward and backward motion in the common optical flow detection. The recognition accuracy of the model is improved.
Description
technical field [0001] The invention relates to the technical field of living body detection, in particular to a living body detection method and system based on an improved optical flow method. Background technique [0002] At present, there are several methods for live detection in face recognition: 1. Let the user blink, shake his head, or let the user read a piece of speech according to the prompts for detection. 2. According to the optical flow method, the temporal change and correlation of the pixel intensity data in the image sequence are used to determine the "motion" of the respective pixel positions, and then the SVM and other methods are used to detect. 3. Use 3D technology for live detection. [0003] Using the first method for live detection requires the user to cooperate according to the prompts, and the rejection rate is relatively high. For example, if the user reacts slowly when following the prompts, he will miss the actions prompted by the system, or the ...
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): G06V40/40G06V40/16G06V10/82G06N3/04
Inventor 崔文斌周建朋刘林陈希展
Owner 金现代信息产业股份有限公司