Table 6 Performance of ELM classifier with the features extracted from spatial-encoder, FFT-encoder and dual-autoencoder for HAM10000 and ISIC-2017 dataset.

From: Skin cancer detection through attention guided dual autoencoder approach with extreme learning machine

Features extracted from the bottleneck layer of

%Accuracy (HAM10000)

%Accuracy (ISIC-2017)

Spatial Autoencoder

94.27

85.11

FFT-Autoencoder

93.76

83.09

Combined feature (spatial Autoencoder + FFT-Autoencoder)

97.66

86.68

Back to article page