Thermal physiological pose-based moment invariants for face identification

This paper presents the implementation of moment invariants with respect to centroid point (obtained from registered image database) for thermal physiological-based face identification system. Seeded region growing method was applied for background filtering. Sequentially, anisotropic diffusion was employed prior to image decomposition to reduce the effect of noise. The system decomposes a background filtered thermal image into several thermal regions via multi-valued threshold method. The lowest valued thermal region is omitted from further processes to assure no background scenery was taken into account. In our previous work, we only considered frontal mugshot images as registered images, therefore, in this paper we include mid-profiles and left and right profile in the registered database. This is to overcome for images with angular pose that exceeds 45 degrees to the left and right. Since our registered database now comprehends several pose, the formerly calculated moment invariants (with respect to centroid points obtain from frontal mugshot images) is now calculated with respect to centroid points obtained from every profile in the registered database. Due to multiple angular pose available in the registered database, customized and simple pose estimation is introduced in this paper. The pose estimation utilizes information previously obtained during the pre-processes, thus avoiding additional steps that is required if current available pose estimation methods were to be employed. This system employs minimum distance measurement method for classification purposes. The encouraging performance of this system is represented by a cumulative match characteristic curve (also known as the CMC curve) at the end of this paper.