view article

Figure 6
The performance of the FCNN, SVM and CNN was tested on two data sets. Data set 1 was collected during the same data collection run as the training data sets, while data set 2 was acquired at a different time point but with a similar beam alignment. Integrated images of scan points, selected classes, predictions and differences (red) are shown for each approach. The final column represents the confusion matrices.

Journal logoFOUNDATIONS
ADVANCES
ISSN: 2053-2733
Follow Acta Cryst. A
Sign up for e-alerts
Follow Acta Cryst. on Twitter
Follow us on facebook
Sign up for RSS feeds