Table 1 Classification results of anomalies with CAEs, HOG, and VGG features

From: Unsupervised anomaly detection with compact deep features for wind turbine blade images taken by a drone

Feature	Precision	Recall	F1 score
CAEs	0.101	0.344	0.156
HOG	0.164	0.263	0.202
VGG16 layer3 +PCA	0.546	0.224	0.318
VGG16 layer1 +PCA	0.630	0.496	0.555

Back to article page