With the recent increase in the availability of quad polarization radar data, the need to assess the utility of these datasets for land cover/use classification is important. The relative classification accuracies of four land covers/uses in Bangladesh using spaceborne quad polarization radar from the Japanese ALOS PALSAR system and optical Landsat Thematic Mapper (TM) data were evaluated. In addition, the utility of radar texture and sensor fusion were analyzed. Supervised signature extraction and classification (maximum likelihood) were used to classify different land covers/uses followed by an accuracy assessment. The original four-band radar had an overall accuracy of 91%. Variance texture was the most useful of the four measures examined, but did not improve overall or individual class accuracies over the original radar. Landsat provided a higher overall classification accuracy (94%) as compared to radar. The merger of Landsat with the original radar increased overall accuracy to 99%, which indicates the advantages of sensor integration.