According to the fact that farmers often picked unripe watermelon and treated them with high concentration ethylene to quicken ripeness, classification experiments on the two classes of watermelon mentioned above were conducted based on the Vis/NIR spectroscopy diffuse transmittance technique. In the discriminant analysis, a method to classify them by diffuse transmittance ration at two wavelengths was adopted to discriminate them. Result of mistake ratio 32.5% for samples without ethylene treatment and 20% for ethylene treatment samples indicated that this method could discriminate the two classes of watermelons roughly. Mahalanobis distance and partial least square methods were also used here for discriminant analysis and satisfied results were obtained. The first derivative spectra with Norris derivative filtering of samples without being ethylene-treated using Mahalanobis distance discriminant analysis got the result of mistake ratio 1.67% for calibration set, no mistake for prediction set and no mistake for samples being ethylene treated. No mistake took place for the second derivative spectra using partial least square method. In discriminant analysis, spectral data pretreatment methods influence the discriminant results and it should be selected according to the analysis methods.