Next we use color moments [7] and texture-based features [5] to diagnose the type of disease in an infected leaf. Using co-occurrence matrix, we have obtained values for the following texture-based features: inertia, correlation, energy and homogeneity. Table 2 demonstrates the use of the color and texture features. It can be observed that the combination of these features can separate the 4 categories of diseased wheat leaves-R, MR, MS, S.