Eye movement detection method and device and living body recognition method and system

Abstract

The invention discloses an eye movement detection method, which comprises the steps of extracting a plurality of video frames from a human face video to be detected; acquiring a plurality of key point position of the eye in each of the video frames extracted from the human face video to be detected; acquiring the eye length and the eye width of the eye in each of the extracted video frames according to the plurality of key point positions of the eye, and acquiring an eye value of the corresponding video frame through calculating the ratio of the eye length and the eye width; and judging a movement condition of the eye in the human face video to be detected based on the eye value of each of the extracted video frames. Correspondingly, the invention further discloses an eye movement detection device. The eye movement detection method and device disclosed by the invention are simple in calculation, high in efficiency and low in requirement for hardware equipment.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to an eye movement detection method and device, and a living body recognition method and system. Background technique [0002] With the development of face recognition technology, more and more scenes need to use face detection to quickly identify a person's identity. However, criminals will use pictures or videos instead of real people for face recognition, so the security of the entire face recognition system cannot be guaranteed. The live face recognition can detect that the current face to be tested is a live face rather than a face in a photo or video, thereby ensuring the security of the face recognition system. When performing face recognition, the detection of the eye movement of the face to be tested helps to identify whether the face is a living body. [0003] The existing technology usually collects face images through a camera, and uses the comparison of the image featu...

AI Technical Summary

Problems solved by technology

[0003] The existing technology usually collects face images through a camera, and uses the comparison of the image features of the eyes when the eyes are open and closed to realize the state of the eyes. In this solution, the movement of the face will increase the error, and the direct contrast grayscale features are easily affected by light, and the accuracy is low.

Images