The Wavelet Filter command allows you to selectively emphasize or de-emphasize image details in a certain spatial frequency domain. It is similar to a "graphic equalizer" for a stereo, except it works on images. You can selectively emphasize or reduce high-frequency, mid-frequency, or low-frequency detail.
A Wavelet transform is similar to a Fast Fourier Transform (FFT), in that it breaks a signal or image down into frequency components. Those components can be modified and transformed back to produce a filtered image. The wavelets have an advantage over Fourier methods in that the wavelet extends over a finite distance, thus making it easier to model transient features (e.g. a single star). There is no single definition for the shape of a wavelet; rather, wavelets are a group of wave shapes that meet certain mathematical criteria.
Wavelets are commonly used for processing lunar and planetary images, although they can be used on any type of image.