Many state estimation algorithms assume that measurements are zero-mean Gaussian. This is an explicit assumption in the Kalman Filter and its nonlinear variants [28, 3] and implicitly built-into the optimization problem of bundle adjustment algorithms [21] and outlier-rejection algorithms [5]. With extensive calibration with respect to temperature and mechanical alignment, the zero-mean Gaussian assumption is sufficient for the measurements of sensors such as inertial measurement units (IMUs) [30, 27], even if it is still not completely true: Extended Kalman Filters (EKFs) that rely on these IMUs are deployed on safety-critical systems actively in use. Even though several well-known algorithms for Simultaneous Localization and Mapping (SLAM) rely on the often-deployed EKF (e.g.

The recent availability of low-power neural accelerator hardware, combined with improvements in end-to-end neural facial recognition algorithms provides, enabling technology for on-device facial authentication. The present research work examines the effects of directional lighting on a State-of-Art(SoA) neural face recognizer. A synthetic re-lighting technique is used to augment data samples due to the lack of public data-sets with sufficient directional lighting variations. Top lighting and its variants (top-left, top-right) are found to have minimal effect on accuracy, while bottom-left or bottom-right directional lighting has the most pronounced effects. Following the fine-tuning of network weights, the face recognition model is shown to achieve close to the original Receiver Operating Characteristic curve (ROC)performance across all lighting conditions and demonstrates an ability to generalize beyond the lighting augmentations used in the fine-tuning data-set. This work shows that an SoA neural face recognition model can be tuned to compensate for directional lighting effects, removing the need for a pre-processing step before applying facial recognition.