The Hyperanalytic Wavelet Packets - A solution to increase the directional selectivity in image analysis
Corina Naforniţa, Alexandru Isar, Ioan Nafornita · 2012
We propose a solution to increase the directional selectivity in image analysis based on wavelets theory. The classical two dimensional (2d) Discrete Wavelet Transform (2d-DWT) has a poor directional selectivity, separating only three directions. The directional selectivity can be improved by using 2d Discrete Wavelet Packets Transform (2d-DWPT). Neither one is able to separate directions with opposite orientations. This separation can be done by using a complex wavelet or wavelet packets transform, such as Hyperanalytic Wavelet Packets Transform (HWPT). We analyze the directional selectivity of the HWPT and we propose an algorithm for the detection of the principal directions in a given image.