Fig. 8

The ROC and PR curves for the CS-ResCNN method and representative conventional methods. a The ROC curves and AUC values for the CS-ResCNN method and five compared methods: ResCNN, SIFT-UNDER, COTE-UNDER, WT-UNDER and LBP-UNDER. b The PR curves for the CS-ResCNN method and the five compared methods. ROC, receiver operating characteristic curve; AUC, area under the ROC curve; PR, precision–recall; CS-ResCNN, cost-sensitive residual convolutional neural network; ResCNN, native residual convolutional neural network; UNDER, under-sampling; WT, wavelet transformation; LBP, local binary pattern; SIFT, scale-invariant feature transform; COTE, color and texture features