Skip to main content
. 2020 Oct 29;25(5):1735–1746. doi: 10.1109/JBHI.2020.3034863

Fig. 2.

Fig. 2.

Our Bangladesh data set is divided into two sets according to annotation scheme: (a) Polygon set, cell outlines annotated by polygons for network training, contains 165 images from 33 patients, each patient contributes with 5 images, total number of RBCs is 34,213. (b) Point set, annotated by placing a dot on each cell, used for network evaluation, contains 800 images from 160 patients, each patient contributes with 5 images, total number of RBCs is 162,450.