Thermal-Visual Facial Feature Extraction Based on Nostril Mask

This paper aims to present facial features extraction by integrating 2 different sensors that will be used in the estimation of internal mental state. Thermal infrared and visible camera are being used in the stimulus experiment by measuring three facial areas of sympathetic importance which is periorbital, supraorbital and maxillary through purely imaging means in thermal infrared spectrums. The development of Automatic Thermal Face, Supraorbital, Periorbital, Maxillary and Nostril Detection to be used for estimation of internal state is also presented. Several faces samples were taken in real time in our experimental setup to measure the effectiveness of our method. Almost 98% of correct measurement of ROI and temperature was detected. In this paper, a new method for detecting facial feature in both thermal and visual is also presented by applying Nostril Mask, which allows one to find facial feature namely nose area in thermal and visual. Graph Cut algorithm is applied to remove unwanted ROI and correctly detect precise temperature values. Extraction of thermal-visual facial feature images is done by using Scale Invariant Feature Transform (SIFT) Feature detector and extractor to verify the method of using nostril mask. Based on the experiment conducted, it shows 88.6% of correct matching.