Vision feedback for automated nanohandling

The handling of nanoscale objects is a field with high prospects and good perspectives. This paper presents different necessary image processing methods and algorithms, which are needed to enable the reliable automation of nanohandling processes. The imaging sensor used to gain access to the nanoscale world is the scanning electron microscope (SEM). Tasks to be fulfilled on image data from the SEM include object recognition, object tracking and depth estimation. All these algorithms are discussed and validated.