Intelligent Identification of Coal Crack in CT Images Based on Deep Learning

Table 4

Comparison of performance of our method and others.

Methods	Acc (%)	mAcc (%)	MIoU (%)	FWIoU (%)
Proposed method	98.6	95.4	89.4	97.7
FCN-32s-vgg16 [10]	97.6	85.4	76.7	93.3
PSPNet-res50 [12]	97.0	80.4	75.1	92.9
U-net-res50 [13]	98.5	94.2	86.5	97.2