A novel method is proposed for the supervised classification of multifrequency polarimetric synthetic aperture radar(Pol SAR) images. The coherency matrices in P-, L-, and C-bands are mapped onto a 9×9 matrix Ω based on the eigenvalue decomposition of the coherency matrix of each band. A boxcar filter is then performed on the matrix Ω. The filtered data are put into a complex Wishart classifier. Finally, the effectiveness of the proposed method is demonstrated with JPL/AIRSAR multifrequency Pol SAR data acquired over the Flevoland area. A novel method is proposed for the supervised classification of multifrequency polarimetric synthetic aperture radar (Pol SAR) images. The coherency matrices in P-, L-, and C-bands are mapped onto a 9 × 9 matrix Ω based on the eigenvalue decomposition of The coherency matrix of each band. A boxcar filter is then performed on the matrix Ω. The filtered data are put into a complex Wishart classifier. Finally, the effectiveness of the proposed method is demonstrated with JPL / AIRSAR multifrequency Pol SAR data acquired over the Flevoland area.