A technique evaluating liveness in short face image sequences is presented. The intended purpose of the proposed system is to assist in a biometric authentication framework, by adding liveness awareness in a non-intrusive manner. Analysing the trajectories of single parts of a live face reveal valuable information to discriminate it against a spoofed one. The proposed system uses a lightweight novel optical flow, which is especially applicable in face motion estimation based on the structure tensor and a few frames. It uses a model-based local Gabor decomposition and SVM experts for face part detection. An alternative approach for face part detection using optical flow pattern matching is introduced as well. Experimental results on the proposed system are presented.