From: Classification of hyperspectral imagery with neural networks: comparison to conventional tools
194-band | 30-band | 13-band | ||||
---|---|---|---|---|---|---|
User | Producer | User | Producer | User | Producer | |
Class | Accuracy | Accuracy | Accuracy | |||
A | 96.81 | 97.74 | 96.87 | 99.68 | ||
B | 96.97 | 16.00 | 87.23 | 61.50 | ||
C | 58.08 | 84.50 | 80.44 | 90.50 | ||
D | 62.86 | 94.29 | 87.34 | 95.24 | ||
E | 35.52 | 98.10 | 41.50 | 100.00 | ||
F | 54.00 | 67.50 | 10.93 | 100.00 | ||
G | 14.87 | 83.82 | 48.89 | 50.87 | ||
H | 100.00 | 5.91 | 77.51 | 73.64 | ||
I | 82.08 | 87.00 | 36.72 | 94.00 | ||
J | 100.00 | 1.20 | 0.00 | 0.00 | ||
K | 80.00 | 8.00 | 98.55 | 54.40 | ||
L | 32.47 | 99.53 | 66.88 | 97.20 | ||
M | 54.55 | 6.00 | 100.00 | 2.50 | ||
N | 92.73 | 17.00 | 100.00 | 6.33 | ||
O | 56.20 | 65.81 | 49.31 | 69.03 | ||
P | 95.42 | 76.33 | 71.32 | 90.33 | ||
Q | 100.00 | 12.27 | 100.00 | 17.73 | ||
R | 100.00 | 68.00 | 100.00 | 32.00 | ||
S | 96.88 | 51.67 | 93.33 | 46.67 | ||
T | 100.00 | 30.77 | 85.71 | 92.31 | ||
U | 93.24 | 34.50 | 80.39 | 82.00 | ||
V | 51.47 | 70.00 | 100.00 | 26.00 | ||
W | 89.66 | 13.00 | 65.70 | 79.50 | ||
Accuracy (%) = N/A | Accuracy (%) = 49.72 | Accuracy (%) = 63.23 | ||||
κ = N/A | κ = 0.4713 | κ = 0.6136 |