Combining Laplacian images of different spatial frequencies (scales): implications for remote sensing image analysis

The author proposes a solution to the longstanding problem of how to combine the different scales of analysis in multifrequency image analysis. The premise for combining different scales of analysis is that the absolute value of the result of the difference of two Gaussian filters (DOG) will be at a maximum at different parts of an object for the DOGS passing the spatial frequencies composing those parts. Combining images derived from a DOGS passing a range of frequencies (called Laplacian images or the Laplacian pyramid) is performed by taking the maximum absolute value among the values in the Laplacian image being combined (for each pixel) to form what is called a multifrequency Laplacian image. The rationale for the development of a multifrequency Laplacian pyramid and its implications for multifrequency image analysis and remote-sensing image classification are discussed