Fruit Classification Model Based on Residual Filtering Network for Smart Community Robot

Table 2

Comparison with different features using SVM.

	Accuracy (Avg)	Recall (Avg)	F1 score (Avg)	Precision (Avg)
RFN-SVM	99.955%	99.958%	99.962%	99.967%
RGB-SVM	92.415%	92.296%	92.188%	92.772%
CNN-SVM	97.166%	96.825%	96.944%	97.472%