Classification results of SVM models developed on optimal wavelengths with 3000 and 1100 samples of each variety in the calibration set.

Samples of each variety in the calibration set		Calibration				Prediction
		1	2	3	Accuracy	1	2	3	Accuracy
3000	1	2743	39	218	91.43%	1099	58	143	84.54%
	2	39	2906	55	96.87%	56	1162	82	89.38%
	3	181	52	2767	92.23%	117	36	1147	88.23%
	Total				93.51%				87.38%
1100	1	995	17	88	90.45%	1079	58	163	83.00%
	2	11	1072	17	97.45%	69	1156	75	88.92%
	3	83	22	995	90.45%	160	50	1090	83.85%
	Total				92.79%				85.26%