Physical object protection includes all techniques to identify or authenticate objects to determine their origin. In this thesis we envision an approach based on the microscopic surface structure of an object. These so called micro-structures are both unique to the object and currently non-cloneable and thus serve as natural identifiers. Moreover, micro-structure based security schemes have relatively cheap enrollment, and are noninvasive, leaving the original object untouched. This thesis contains a number of methods to allow micro-structure identification using a hand-held mobile phone, without any modification to the object or the device. Primarily, a novel descriptor was designed to robustly identify distorted micro-structures: SketchPrint. It requires no training, is relatively stable yet information rich, and needs but a small number of enrolled descriptor vectors per sample. As it both captures geometrical and micro-structure information from its region of interest, it does not require any exhaustive geometrical re-ranking or aggregation.