Wood Species Recognition Based on Visible and Near-Infrared Spectral Analysis Using Fuzzy Reasoning and Decision-Level Fusion

Table 14

Wood classification performance comparisons with state-of-the-art schemes.

Reference	Model	ORA (%)
[35]	I-BGLAM	72.32
[36]	LBP	68.68
[19, 37]	SPPD	7.32
	SPPD + I-BGLAM	32.68
	Fuzzy + SPPD + BGLAM	34.68
[18]	GA	25.68
	GA + KDA	29.00
[38]	VGG16	83.36
[39]	SqueezeNet	86.28
[40]	ResNet18	94.40
[41]	GoogLeNet	92.80
[42]	CNN	83.00
Our scheme	FRC + improved D-S fusion	94.76

ORA: overall recognition accuracy; TR: time requirement; I-BGLAM: improved basic gray-level aura matrix; LBP: local binary pattern; SPPD: statistical property of pore distribution; GA: genetic algorithm; KDA: kernel discriminant analysis; CNN: convolutional neural network; FRC: fuzzy reasoning classifier; D-S: Dempster–Shafer.