The invention provides a biopsy method for use in human face identification and belongs to the technical field of mode identification. The algorithm provided by the invention comprises: firstly, giving a 'please-face-the-camera-with-face' prompt to a user logging in regardless of the current posture of the user, finding the face and eye socket areas by using an Adaboost human face sorter during the posture correction of the user, determining upper and low eyelids and left and right eye corners by using differential projection and precisely framing the positions of the eye sockets; secondly, computing optical flow field of two adjacent frames in an input video sequence by using an LK algorithm; and thirdly, further processing obtained optical flow data to obtain an optical flow amplitude, acquiring the number of the pixels with high amplitude, computing the specific gravity of the pixels with high amplitude, and determining eye movement if the proportion is big. Experiments show that for a real human face, eye movement can be detected easily due to a heavy optical flow generated on the eyes in a posture correction and eye twinkling process, while for a picture, eyes only perform a micro movement no matter how the picture moves or translations. When the method is used for biopsy, a better effect can be obtained.