The easy block Hadamard transform: A new adaptive directional Hadamard transform for sparse image representation

In order to get an efficient image representation, we introduce a new locally adaptive Hadamard transform, called Easy Block Hadamard Transform (EBHT). EBHT is a type of directional Hadamard transform, which can be adapted to the image geometry in each block. Firstly, the image is divided into eight equal-sized squares and the adaptive directional Hadamard filter is employed to get the low-pass data and high-pass data. In the further level of the filter bank algorithm, we just divide the low-pass image into four equal-sized squares. EBHT is very simple, but effective. Numerical results show the excellent efficiency of the EBHT for sparse image representation.