SVM Classification Method of Waxy Corn Seeds with Different Vitality Levels Based on Hyperspectral Imaging

Table 6

The classification accuracy of SVM models using different processing methods based on feature wavelengths.

Methods	Number of correct recognition	Training accuracy (%)	Testing accuracy (%)	RMSE
2nd-derivative-SVM	20	96.5278	95.8333	0.0385	0.9218
SNV-SVM	133	94.4444	93.75	0.0424	0.855
MSC-SVM	144	100	97.9167	0.018	0.875
S-G smoothing-SVM	138	95.8333	91.6667	0.0359	0.864
1st-derivative-SVM	126	91.4766.5	89.2501	0.05	0.834
2nd-derivative-SVM	139	96.5278	95.8333	0.0343	0.888