Infrared (IR) face recognition is getting wide attention with its increased number of applications as it provides numerous advantages over visual face recognition. As IR images are invariant to different illumination conditions they can provide robust thermal characteristics. The paper proposes a thermal IR based face recognition system using Zernike moments ZM and Multi Layer Perceptron Neural Network. The recognition experiment was performed using the images obtained from Terravic Facial IR Database with variations in poses (front, left and right) and environments (indoor/outdoor). The proposed method shows that the combination of magnitudes of ZM obtained from orders zero to two as feature vector provides the best average recognition accuracy of 89.5% and false acceptance rate of 0.356%. © Springer International Publishing AG 2018.