Thermal Infrared Face Segmentation: A New Pose Invariant Method

摘要

This paper presents a method for automatic segmentation of images of faces captured in Long Wavelength Infrared (LWIR), allowing a wide range of face rotations, expressions and artifacts (such as glasses and hats). The paper presents a novel high accurate approach and compares its performance against three other previously published methods. The proposed approach is based on statistical modeling of pixel intensities and active contour application, although several other image processing operations are also performed. Experiments were performed on a total of 699 test images from three public available databases. The obtained results improve on previous existing methods up to 29.5% for the first measure error (E_1) and up to 34.7% for the second measure (E_2), depending on the method and database.