Abstract: A computer-implemented method for automatically orienting product containers includes acquiring a reference product label image associated with a batch of product containers on a production line and using a trained deep learning model to compute a perceptual center of the reference product label image based on perceptually relevant label features of the reference product label image. A production line camera acquires an image slice of the respective product label of individual product containers in the batch of product containers. A rotation angle for rotating an individual product container is computed based on the acquired image slice of the respective product label and a label center determined based on the computed perceptual center of the reference product label image. The computed rotation angle is communicated to a controller to effect a rotation of the individual product container.

Abstract: The present disclosure describes a method for determining the condensate location within an HID lamp. The method involves monitoring current and voltage waveforms during the glow phase of lamp starting. If the voltage drop during the glow phase is low with a corresponding high current, then the volatile component of the lamp fill has condensed on the electrodes during the previous cool down period. If the voltage drop is high and current is low then most of the condensate has localized on the arc tube wall. An automated detection apparatus is used to carry out the measurements to determine condensate location.