The invention discloses a face recognition method and
system for a binocular camera, and relates to the field of face
feature recognition. The method comprises the following steps: S01, a left cameraand a right camera of an eye camera simultaneously complete face two-dimensional
image acquisition; S02, performing two-dimensional feature on the two-dimensional image by using an active shape modeltechnology in a processor; S03, obtaining three-dimensional coordinates of the feature points by combining camera calibration parameters; S04, sending the calibrated three-dimensional coordinates to acomparison
data platform; s05, performing identification by using a
data platform neural network; s06, feeding back an identification result to the processor; and S07, the processor controlling the equipment to execute related operation. According to the method, the left camera and the right camera in the binocular cameras are used for collecting different face images, two-dimensional feature point calibration is carried out, calibrated parameters are used for constructing three-dimensional features, the three-dimensional features are input into the neural network for recognition, and compared with existing two-dimensional recognition, the recognition accuracy is improved, and the situation that pictures are used for deception is avoided.