What is the "General Wishart" classification?

Hi everyone!
I have to use SNAP for the polarimetric classification of some ALOS-2 datasets, because it mysteriously doesn’t work in PolSARPro for this data. While doing the unsupervised classification, I came across the option of a “General Wishart” classification, which is not explained or even mentioned in the help documents. This forum and the web in general also didn’t deliver any useful information. Maybe someone here can explain?

I’m also looking for the H/A/Alpha Wishart classification, which doesn’t seem to exist?


The “General Wishart” classification basically generalized the unsupervised PolSAR classification algorithm proposed by Lee et al. in [1]. In Lee’s algorithm, the pixels are first divided into three categories of surface, volume and double bounce scattering by applying the Freeman-Durden decomposition. Then 30 clusters are created in each category with approximately equal number of pixels based on the backscattering power of surface, volume and double bounce. Finally the clusters in each category are merged to a pre-selected number of classes based on Wishart distance between clusters.

In the “general Wishart” classification, the initial decomposition method is generalized from Freeman-Durden method to other decomposition method, such as Sinclair decomposition, Yamaguchi decomposition etc. The rest of the algorithm is the same as Lee’s algorithm.

[1] J.S. Lee, M.R. Grunes, and E. Pottier, "Unsupervised terrain classification preserving polarimetric scattering characteristics", IEEE Transaction on Geoscience and Remote Sensing, Vol. 42, No. 4, April 2004.

1 Like