fast bidimensional empirical mode decomposition

Fast bidimensional empirical mode decomposition (BEMD) is a signal processing technique that decomposes a two-dimensional signal into its intrinsic mode functions (IMFs). BEMD is an extension of the one-dimensional EMD algorithm, which decomposes a one-dimensional signal into its IMFs.

The BEMD algorithm is an iterative process that uses a sifting process to extract the IMFs of the signal. The algorithm starts by identifying the extrema (maxima and minima) of the signal and connecting them with cubic spline curves. The average of the upper and lower envelopes of the signal is then subtracted from the signal to obtain the first IMF. The process is repeated on the residual signal to obtain the second IMF, and so on, until the residual signal is a monotonic function.

The BEMD algorithm can be computationally expensive, especially for large signals. To overcome this limitation, fast BEMD algorithms have been developed, which use a reduced number of sifting iterations and an optimized sifting process. These algorithms can significantly reduce the computational time of the BEMD algorithm while maintaining its accuracy.

BEMD has applications in image processing, signal denoising, feature extraction, and pattern recognition. It has been used in diverse fields such as medical imaging, remote sensing, and speech recognition.