Abstract: This paper deals with an adaptive sub sampling process that is an example of a more general class of data processing. Our approach consists of spanning a Z -tree over the image. The Z -tree is the bin-tree built from the 1D pixel sequence obtained through a peculiar scan called the Peano traversal. A conditional rotation operator, defined to manipulate the Z -tree, supports the peano scan adaptation. Iterating rotations before tree inversion allows to rebuild various mosa?c versions of a same initial image. In the application outlined here, a fair stress is put on the way spatial redundancies are highlighted by this image shuffling process. This helps reconstructing various versions from the initial data where both edges and regions are simultaneously detected.