The spectral reflectance of rice and barnyard-grass was determined in the range from 350 to 2500nm using the Analytical Spectral Device Full Range FieldSpec Pro (ASD) on laboratory. The discrimination analysis was carried out with the statistical software package SAS. The spectral reflectance at the green peak (555nm) was chosen as denominator, and wavelength ratios were calculated as variables to discriminate. Wavelength ratios were selected using the STEPDISC procedure. With the selected variables, the discrimination models were developed using the DISCRIM procedure in SAS. Four wavelength ratios including 395/555, 535/555, 705/555 and 1105/555, were utilized to gain good classification performance (100% accuracy) for distinguishing barnyard-grass from rice. The ratio of spectral reflectance at 705nm in the red edge to spectral reflectance at 555nm contributes more to the discrimination model.  