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

Table 5

Comparison with different features using KNN.

	Accuracy (Avg)	Recall (Avg)	F1 score (Avg)	Precision (Avg)
RFN-KNN	99.926%	99.931%	99.927%	99.923%
RGB-KNN	92.553%	92.464%	92.368%	92.613%
CNN-KNN	98.677%	98.565%	98.531%	98.569%