Skip to main content
. 2018 Feb 1;8:2128. doi: 10.1038/s41598-018-20037-5

Table 3.

The results of the same experiments with LOM images are provided in this table.

Method Input Data Data Training Strategy Test Accuracy
CIFARNet cropped object LOM from scratch 51,27%
VGG-19- DeCAF-RBF-kernel SVM cropped object LOM 56.56%
VGG-16 cropped object LOM fine tuning 60,02%
MVFCNN cropped patch LOM fine tuning 70.14%
MVFCNN cropped patch SEM fine tuning 93.94%

he results show inferior performance using LOM instead of SEM images.