Abstract

In this paper, we proposed a fast image matching algorithm based on  the normalized cross correlation (NCC) by applying the winner-update strategy  on the Walsh-Hadamard transform. Walsh-Hadamard transform is an orthogo- nal transformation that is easy to compute and has nice energy packing capabil- ity. Based on the Cauchy-Schwarz inequality, we derive a novel upper bound  for the cross-correlation of image matching in the Walsh-Hadamard domain.  Applying this upper bound with the winner update search strategy can skip un- necessary calculation, thus significantly reducing the computational burden of  NCC-based pattern matching. Experimental results show the proposed algo- rithm is very efficient for NCC-based image matching under different lighting  conditions and noise levels.