Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 3 Comparison of wndchrm accuracy to application-specific classifiers

From: Wndchrm – an open source utility for biological image analysis

Classification Accuracy
Dataset Benchmark
accuracy (%)
Accuracy of
wndchrm (%)
Hela [29] 83 86
Pollen [30] 79 96
CHO [31] 87 95
  1. HeLa dataset [32], consists of fluorescence microscopy images of HeLa cells using 10 different labels, Pollen dataset [30], shows geometric features of pollen grains, and the CHO dataset [31], features fluorescence microscopy images of different sub-cellular compartments.