Transform coding based on the Karhunen-Loeve transform (KLT), the discrete cosine transform (DCT), and the discrete wavelet transform (DWT) is well-understood for optical images. Transform coding applied to synthetic aperture radar (SAR) data, however, has not been well studied. This paper shows the results of compressing SAR images when it is available in polar formats. We compare the compression results based on six performance criteria-mean-squared error (MSE), mean absolute error, peak signal-to-noise ratio (SNR), energy compaction, transform gain, and compression ratio (CR).