Illumination-invariant face recognition from a single image across extreme pose using a dual dimension AAM ensemble in the thermal infrared spectrum

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in practice. While inherently insensitive to visible spectrum illumination changes, IR data introduces specific challenges of its own, most notably sensitivity to factors which affect facial heat emission patterns, e.g. emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, when comparing two thermal IR images of faces, we mutually normalize their poses and facial expressions by using an active appearance model (AAM) to generate synthetic images of the two faces with a neutral facial expression and in the same view (the average of the two input views). This is achieved by piecewise affine warping which follows AAM fitting. A major contribution of our work is the use of an AAM ensemble in which each AAM is specialized to a particular range of poses and a particular region of the thermal IR face space. Combined with the contributions from our previous work which addressed the problem of reliable AAM fitting in the thermal IR spectrum, and the development of a person-specific representation robust to transient changes in the pattern of facial temperature emissions, the proposed ensemble framework accurately matches faces across the full range of yaw from frontal to profile, even in the presence of scale variation (e.g. due to the varying distance of a subject from the camera). The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces and a newly acquired data set of thermal IR motion videos. Our approach achieved perfect recognition performance on both data sets, significantly outperforming the current state of the art methods even when they are trained with multiple images spanning a range of head views.

An illumination invariant face recognition system for access control using video

Illumination and pose invariance are the most challenging aspects of face recognition. In this paper we describe a fully automatic face recognition system that uses video information to achieve illumination and pose robustness. In the proposed method, highly nonlinear manifolds of face motion are approximated using three Gaussian pose clusters. Pose robustness is achieved by comparing the corresponding pose clusters and probabilistically combining the results to derive a measure of similarity between two manifolds. Illumination is normalized on a per-pose basis. Region-based gamma intensity correction is used to correct for coarse illumination changes, while further refinement is achieved by combining a learnt linear manifold of illumination variation with constraints on face pattern distribution, derived from video. Comparative experimental evaluation is presented and the proposed method is shown to greatly outperform state-of-the-art algorithms. Consistent recognition rates of 94-100% are achieved across dramatic changes in illumination.

A delay-dependent functional observer for linear time-invariant systems with input delay

A delay-dependent functional observer is designed for linear time-invariant (LTI) systems with time-varying input delay. Compared to delay-free observers, delay-dependent functional observers are less conservative and cover more systems. The designed functional observer is with minimum possible order (minimal). Necessary and sufficient conditions of the existence of the observer and asymptomatic stability of it are illustrated. The proposed observer is extended to multiple input delayed systems with time-varying delays. An algorithm is developed for designing of the minimal order observer based on the methodology of this paper. Two numerical examples and simulations are used to support our proposed methodology.

Explicit invariant solutions associated with nonlinear atmospheric flows in a thin rotating spherical shell with and without west-to-east jets perturbations

A class of non-stationary exact solutions of two-dimensional nonlinear Navier–Stokes (NS) equations within a thin rotating spherical shell were found as invariant and approximately invariant solutions. The model is used to describe a simple zonally averaged atmospheric circulation caused by the difference in temperature between the equator and the poles. Coriolis effects are generated by pseudoforces, which support the stable west-to-east flows providing the achievable meteorological flows. The model is superimposed by a stationary latitude dependent flow. Under the assumption of no friction, the perturbed model describes zonal west-to-east flows in the upper atmosphere between the Ferrel and Polar cells. In terms of nonlinear modeling for the NS equations, two small parameters are chosen for the viscosity and the rate of the earth’s rotation and exact solutions in terms of elementary functions are found using approximate symmetry analysis. It is shown that approximately invariant solutions are also valid in the absence of the flow perturbation to a zonally averaged mean flow.