The invention provides a face identification method and a face identification system using the same, which belong to the field of face identification. The face identification method comprises the steps of: detecting a face when reading in an initial frame; extracting eigenvalues of feature points of a central part of the face; positioning the feature points of the face; constructing geometric feature vectors based on the face feature points; initializing a Kalman filter, and determining an initial state; calculating a kernel histogram of a target model, and reading a next frame; predicting a face iteration starting position, and calculating a candidate model kernel histogram according to the predicted position; calculating the maximum similarity between the kernel histogram and the candidate model kernel histogram by utilizing a Bhattacharyya coefficient; finding a next candidate position according to the similarity; and extracting vector eigenvalues, comparing the extracted eigenvalues with an eigenvalue system, and returning an identification result.